Object recognition method, apparatus, electronic device and fingerprint recognition module

Abstract

The present application relates to an object recognition method, apparatus, electronic device, and fingerprint recognition module for a spectral-based analysis device. The object recognition method for the spectral-based analysis device includes: obtaining reference spectral response data of a reference object by an image sensor of the spectral-based analysis device; obtaining recognition spectral response data of an object to be recognized by the image sensor of the spectral-based analysis device; and determining a recognition result of the object to be recognized based on a comparison result between the reference spectral response data and the recognition spectral response data. In this way, it is not necessary to know the transmission spectrum of the filter structure of the spectral-based analysis device, reducing the calculation error and calculation amount and improving the spatial resolution.

Description

Technical Field

[0001] This application relates to the field of spectral analysis technology. More specifically, it relates to an object recognition method, device, electronic device, and fingerprint recognition module for a spectral-based analysis device. Background Art

[0002] In currently used miniaturized spectrometers / spectral imaging technologies, a common approach is to use a filter and a photodetector array (area array or line array) to detect physical signals, and then perform data processing to varying degrees to obtain a spectrum. Here, the filter can be a narrowband, broadband, periodic, etc. filtering method in the frequency domain or wavelength domain. The simplest way in different degrees of data processing is to directly multiply the read data by a fixed coefficient as the spectral intensity restored for the corresponding wavelength. The spectrum restored using this method can be used for object recognition (such as distinguishing a human finger from rubber, etc.). It can also distinguish the properties of an object (such as whether the colors of two fabrics are the same, or whether a plant leaf is healthy, etc.).

[0003] However, current object recognition technologies based on spectrometers / spectral imagers all require spectrum restoration and then object or object property recognition and discrimination, which have the following disadvantages:

[0004] First, the transmission spectrum of the filter structure needs to be known. Miniaturized spectrometers / spectral imagers often need to obtain the final spectrum based on the transmission spectra of different filter structures. In many cases, it is difficult or even impossible to accurately measure the transmission spectrum. In this case, the spectrum cannot be restored. And due to reasons such as inconsistent processes, the transmission spectra of each device may not be exactly the same, and it is more cumbersome to measure the transmission of each device.

[0005] Second, more errors are introduced. Since for the discrimination of many objects or object characteristics, the spectrum itself contains richer information. Restoring the spectrum and then using the spectrum for object recognition or object characteristic discrimination will go through two calculations, introducing more errors.

[0006] Third, for spectral imaging applications, the spatial resolution is low. For spectral imaging applications, it is often carried out on the premise that the spectral change is small in a small restored area. However, many actual applications do not meet this condition, making spectrum restoration impossible.

[0007] Therefore, it is desirable to provide an improved object recognition solution based on spectral analysis. Summary of the Invention

[0008] To solve the above technical problems, the present application is proposed. Embodiments of the present application provide an object recognition method, device, electronic device, and fingerprint recognition module for a spectrum-based analysis device, which can directly perform object recognition based on the spectral response data of a reference object and an object to be recognized by an image sensor of the spectrum-based analysis device, thereby eliminating the need for the transmission spectrum of the filter structure of the spectrum-based analysis device that is known, reducing the calculation error and calculation amount, and improving the spatial resolution.

[0009] According to one aspect of the present application, there is provided an object recognition method for a spectrum-based analysis device, including: obtaining reference spectral response data of a reference object by an image sensor of the spectrum-based analysis device; obtaining recognition spectral response data of an object to be recognized by the image sensor of the spectrum-based analysis device; and determining an identification result of the object to be recognized based on a comparison result between the reference spectral response data and the recognition spectral response data.

[0010] In the above object recognition method for a spectrum-based analysis device, obtaining reference spectral response data of a reference object by an image sensor of the spectrum-based analysis device includes: detecting the reference object with the spectrum-based analysis device; and recording the reference spectral response data of the reference object by the image sensor of the spectrum-based analysis device.

[0011] In the above object recognition method for a spectrum-based analysis device, obtaining recognition spectral response data of an object to be recognized by the image sensor of the spectrum-based analysis device includes: detecting the object to be recognized with the spectrum-based analysis device; and recording the recognition spectral response data of the object to be recognized by the image sensor of the spectrum-based analysis device.

[0012] In the above object recognition method for a spectrum-based analysis device, determining an identification result of the object to be recognized based on a comparison result between the reference spectral response data and the recognition spectral response data includes: forming a binary array corresponding to each pixel unit of the image sensor by respectively using a first value corresponding to each pixel unit of the reference spectral response data and a second value corresponding to each pixel unit of the recognition spectral response data; mapping the first values and the second values in a plurality of binary arrays to a rectangular coordinate system as the abscissa and ordinate of the rectangular coordinate system to obtain a plurality of data points on the rectangular coordinate system; fitting a straight line based on the plurality of data points on the rectangular coordinate system; and determining an identification result of the object to be recognized based on the distances between the plurality of data points and the straight line.

[0013] In the above object recognition method for a spectral-based analysis device, determining the recognition result of the object to be recognized based on the distances between the multiple data points and the straight line includes: determining the average value or the root mean square value of the multiple distances from the multiple data points to the straight line; determining whether the average value or the root mean square value of the multiple distances is greater than a predetermined threshold; and, in response to the average value or the root mean square value of the multiple distances being less than or equal to the predetermined threshold, determining that the object to be recognized is the same as or has the same characteristics as the reference object.

[0014] In the above object recognition method for a spectral-based analysis device, determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data includes: comparing the reference spectral response data and the recognition spectral response data through a neural network model or a decision tree model; and determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data.

[0015] In the above object recognition method for a spectral-based analysis device, determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data includes: determining a first part of the data in the reference spectral response data and a second part of the data in the recognition spectral response data corresponding to the first part of the data; and determining the recognition result of the object to be recognized based on the comparison result between the first part of the data and the second part of the data.

[0016] In the above object recognition method for a spectral-based analysis device, determining the first part of the data in the reference spectral response data and the second part of the data in the recognition spectral response data corresponding to the first part of the data includes: determining first effective information in the reference spectral response data and second effective information in the recognition spectral response data based on a predetermined algorithm; and determining the first part of the data and the second part of the data based on the first effective information and the second effective information.

[0017] In the above object recognition method for a spectral-based analysis device, determining the first effective information in the reference spectral response data includes: in response to the effective information in the reference spectral response data obtained by a single measurement not corresponding to the second effective information in the recognition spectral response data, obtaining multiple reference spectral response data through multiple measurements; and determining the first effective information based on the multiple reference spectral response data.

[0018] In the above object recognition method for a spectrum-based analysis device, the image sensor includes a first sensing unit corresponding to the modulation unit of the light modulation layer and a second sensing unit corresponding to the non-modulation unit of the light modulation layer. The method further includes: obtaining first auxiliary information of the second sensing unit of the image sensor for the reference object; obtaining second auxiliary information of the second sensing unit of the image sensor for the object to be recognized; and determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data includes: using the first auxiliary information and the second auxiliary information as references, and determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data.

[0019] In the above object recognition method for a spectrum-based analysis device, using the first auxiliary information and the second auxiliary information as references, and determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data includes: using the first auxiliary information and the second auxiliary information as references, determining first valid information in the reference spectral response data and second valid information in the recognition spectral response data; determining first partial data in the reference spectral response data and second partial data in the recognition spectral response data based on the first valid information and the second valid information; and determining the recognition result of the object to be recognized based on the comparison result between the first partial data and the second partial data.

[0020] In the above object recognition method for a spectrum-based analysis device, using the first auxiliary information and the second auxiliary information as references, and determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data includes: using the first auxiliary information and the second auxiliary information as references, obtaining qualified reference spectral response data and recognition spectral response data by changing the acquisition environments of the reference spectral response data and the recognition spectral response data; and determining the recognition result of the object to be recognized based on the comparison result between the qualified reference spectral response data and the recognition spectral response data.

[0021] In the above object recognition method for a spectral-based analysis device, using the first auxiliary information and the second auxiliary information as references, the recognition result of the object to be recognized is determined based on the comparison result between the reference spectral response data and the recognition spectral response data, including: using the first auxiliary information and the second auxiliary information as references, correcting the acquired reference spectral response data and the recognition spectral response data to obtain the corrected reference spectral response data and the recognition spectral response data; and determining the recognition result of the object to be recognized based on the comparison result between the corrected reference spectral response data and the recognition spectral response data.

[0022] In the above object recognition method for a spectral-based analysis device, determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data includes: normalizing the reference spectral response data and the recognition spectral response data respectively to obtain first normalized data and second normalized data; and determining the recognition result of the object to be recognized based on the comparison result between the first normalized data and the second normalized data.

[0023] In the above object recognition method for a spectral-based analysis device, obtaining the reference spectral response data of the image sensor of the spectral-based analysis device for a reference object includes: obtaining multiple reference spectral response data of the image sensor of the spectral-based analysis device for multiple standard reference objects or standard reference objects with multiple characteristics respectively.

[0024] In the above object recognition method for a spectral-based analysis device, the multiple reference spectral response data are stored in the spectral-based analysis device or in the cloud.

[0025] According to another aspect of the present application, there is provided an object recognition device for a spectral-based analysis device, including: a reference data acquisition unit for acquiring the reference spectral response data of the image sensor of the spectral-based analysis device for a reference object; an identification data acquisition unit for acquiring the identification spectral response data of the image sensor of the spectral-based analysis device for the object to be recognized; and a comparison and identification unit for determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the identification spectral response data.

[0026] According to still another aspect of the present application, there is provided an electronic device, including: a processor; and a memory in which computer program instructions are stored, and when the computer program instructions run on the processor, the processor is caused to execute the above-mentioned object recognition method for a spectral-based analysis device.

[0027] According to another aspect of the present application, there is provided a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a computing device, they are operable to execute the object recognition method for a spectral-based analysis device as described above.

[0028] According to another aspect of the present application, there is provided a fingerprint recognition module, including: an optical system; a spectral chip for generating reference spectral response data for a reference fingerprint and recognition spectral response data for a fingerprint to be recognized; and a recognition module for determining whether the fingerprint to be recognized matches the reference fingerprint based on a comparison result between the reference spectral response data and the recognition spectral response data.

[0029] In the above fingerprint recognition module, the spectral chip is used to generate reference spectral response data for the edge and / or four corners of the reference fingerprint and recognition spectral response data for the edge and / or four corners of the fingerprint to be recognized, as well as reference image data for the center of the reference fingerprint and recognition image data for the center of the fingerprint to be recognized; and the recognition module is used to determine whether the fingerprint to be recognized matches the reference fingerprint based on a first comparison result between the reference spectral response data and the recognition spectral response data, and a second comparison result between the reference image data and the recognition image data.

[0030] In the above fingerprint recognition module, the recognition module includes: a data division sub-unit for dividing the reference spectral response data into first partial reference spectral response data and second partial reference spectral response data corresponding to different parts of the fingerprint, and dividing the recognition spectral response data into first partial recognition spectral response data and second partial recognition spectral response data corresponding to the different parts of the fingerprint; a first comparison sub-unit for comparing the first partial reference spectral response data with the first partial recognition spectral response data in a first manner to obtain a first comparison result; a second comparison sub-unit for comparing the second partial reference spectral response data with the second partial recognition spectral response data in a second manner to obtain a second comparison result; and a fingerprint matching sub-unit for determining whether the fingerprint to be recognized matches the reference fingerprint based on the first comparison result and the second comparison result.

[0031] The object recognition method, device, and electronic device for a spectral-based analysis device, and the fingerprint recognition module provided by the present application can directly perform object recognition based on the spectral response data of a reference object and an object to be recognized by an image sensor of the spectral-based analysis device, without the need to perform spectral restoration from the spectral response data, and thus without the need to know the transmission spectrum of the filter structure of the spectral-based analysis device.

[0032] Moreover, since the object recognition method, apparatus, and electronic device for a spectral-based analysis device provided by this application, as well as the fingerprint recognition module, do not require spectral recovery, the computational error and computational amount in the object recognition process are reduced. Accordingly, the object recognition speed is increased, and the computational unit is simplified or the power consumption of the computational unit is reduced.

[0033] In addition, since the object recognition method, apparatus, and electronic device for a spectral-based analysis device provided by this application, as well as the fingerprint recognition module, do not require spectral recovery and require less information compared to spectral recovery, the spatial resolution can be improved, or a smaller area image sensor can be used to achieve it. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] By reading the following detailed description of the preferred specific embodiments, various other advantages and benefits of this application will become clear to those of ordinary skill in the art. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not considered to be a limitation of this application. Obviously, the following described drawings are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. Moreover, throughout the drawings, the same reference numerals are used to represent the same components.

[0035] Figure 1 The flowchart of the object recognition method for a spectral-based analysis device according to an embodiment of this application is illustrated;

[0036] Figure 2 The exemplary configuration diagram of a miniaturized spectral-based analysis device according to an embodiment of this application is illustrated;

[0037] Figure 3 The schematic diagram of the regression comparison method of the object recognition method for a spectral-based analysis device according to an embodiment of this application is illustrated;

[0038] Figure 4 The schematic diagram of an example of the filter structure of the object recognition method for a spectral-based analysis device according to an embodiment of this application is illustrated;

[0039] Figure 5 The block diagram of the object recognition apparatus for a spectral-based analysis device according to an embodiment of this application is illustrated;

[0040] Figure 6 The block diagram of the electronic device according to an embodiment of this application is illustrated;

[0041] Figure 7 The schematic block diagram of the fingerprint recognition module according to an embodiment of this application is illustrated;

[0042] Figure 8 The figure shows an imaging schematic diagram of a fingerprint recognition module according to an embodiment of the present application. Detailed implementation manners

[0043] Next, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein.

[0044] Exemplary method

[0045] Figure 1 The figure shows a flowchart of an object recognition method for a spectral-based analysis device according to an embodiment of the present application.

[0046] As Figure 1 shown, the object recognition method for a spectral-based analysis device according to an embodiment of the present application includes the following steps:

[0047] Step S110, obtaining reference spectral response data of an image sensor of the spectral-based analysis device for a reference object.

[0048] Here, a configuration example of the spectral-based analysis device according to an embodiment of the present application is as Figure 2 shown. Figure 2 The figure shows an exemplary configuration diagram of a spectral-based analysis device according to an embodiment of the present application. As Figure 2 shown, in the spectral-based analysis device according to an embodiment of the present application, the optical system is optional and may be an optical system such as a lens assembly or a light homogenizing assembly. The filter structure is a filter structure with filtering methods such as narrowband, broadband, and periodic in the frequency domain or wavelength domain. The through-spectra of different wavelengths of the filter structure at each location are not completely the same. The filter structure may be a structure or material with filtering characteristics such as a metasurface, a photonic crystal, a nanorod, a multilayer film, a dye, a quantum dot, a MEMS (microelectromechanical system), an FP etalon (FP etalon), a cavity layer, a waveguide layer, a diffraction element, etc. For example, in an embodiment of the present application, the filter structure may be a light modulation layer in Chinese Patent CN201921223201.2, and in the technical solution according to an embodiment of the present application, the filtering characteristics at each location do not have to be known. In addition, in the technical solution according to an embodiment of the present application, there may also be no filter structure. In this way, each point of the image sensor array has different spectral responses, such as quantum dots and nanowire solutions, etc., which can all achieve this structure.

[0049] Continue to refer to Figure 2, the image sensor (i.e., the light detector array) can be a CMOS image sensor (CIS), a CCD, an array of light detectors, etc. Additionally, the optional data processing unit can be a processing unit such as an MCU, a CPU, a GPU, an FPGA, an NPU, an ASIC, etc., which can export the data generated by the image sensor to the outside for processing. It should be noted that in individual scenario applications, a light source may be required to illuminate the object to be measured so that it can be better received by the spectral-based analysis device. Therefore, in some embodiments, the spectral-based analysis device further includes a light source for providing light to illuminate the object to be measured.

[0050] Here, those skilled in the art can understand that the spectral-based analysis device according to the embodiments of the present application uses the spectral response data of the reference object and the object to be recognized to perform object recognition, and it does not need to recover the spectrum. In the prior art, the device for recovering the spectrum is usually called a spectrometer. Therefore, the spectral-based analysis device according to the embodiments of the present application is not completely equivalent to the spectrometer in the prior art. In addition, in many applications, the image sensor also plays a role in spectral imaging, such as in the spectral imager described above. However, those skilled in the art can also understand that not all spectrometers can use an image sensor to perform spectral recovery or spectral imaging (because the spectral recovery of some spectrometers is not based on an image sensor), and at the same time, not all spectral recovery or spectral imaging can be called a spectrometer. Accordingly, the spectral-based analysis device according to the embodiments of the present application is not completely equivalent to the spectral imager in the prior art.

[0051] At the same time, the spectral-based analysis device according to the embodiments of the present application can be a part of an existing spectrometer or spectral imager. That is, after the spectral-based analysis device according to the embodiments of the present application obtains the spectral response data, the existing spectrometer or spectral imager can further use the spectral response data to recover the spectrum or perform spectral imaging.

[0052] In the embodiments of the present application, through the spectral-based analysis device, the reference spectral response data of the image sensor to the reference object can be obtained. Here, the reference object can be various standard objects, or standard objects with various characteristics. And the reference spectral response data of the image sensor to the reference object is the electrical signal at each pixel position directly output by the image sensor, generally a current value.

[0053] Moreover, in the embodiments of the present application, the reference spectral response data of the image sensor of the spectral-based analysis device to the reference object can be collected during the object recognition process or pre-stored in the database for object recognition. For example, when collecting data, first, the spectral-based analysis device is used to detect the reference object, and then the reference spectral response data of the image sensor of the spectral-based analysis device to the reference object is recorded.

[0054] That is, in the object recognition method for the spectral-based analysis device according to the embodiments of the present application, obtaining the reference spectral response data of the image sensor of the spectral-based analysis device to the reference object includes: detecting the reference object with the spectral-based analysis device; and recording the reference spectral response data of the image sensor of the spectral-based analysis device to the reference object.

[0055] For better understanding, the present invention takes the spectral chip in CN201921223201.2 as an example for illustration. The spectral chip includes a light modulation layer and an image sensing layer. The light modulation layer includes at least one modulation unit, and the modulation unit is correspondingly arranged on the light sensing path of at least one sensing unit of the light detection layer. Thus, the sensing unit can receive the light signal modulated by the modulation unit and output the corresponding electrical signal, that is, obtain the spectral response. Therefore, such a spectral chip can correspond to the spectral-based analysis device according to the embodiments of the present application.

[0056] Step S120, obtain the recognition spectral response data of the image sensor of the spectral-based analysis device to the object to be recognized. Similar to the data collection process of the reference object, when collecting the recognition spectral response data, first, the spectral-based analysis device is used to detect the object to be recognized, and then the recognition spectral response data of the image sensor of the spectral-based analysis device to the object to be recognized is recorded.

[0057] That is, in the object recognition method for the spectral-based analysis device according to the embodiments of the present application, obtaining the recognition spectral response data of the image sensor of the spectral-based analysis device to the object to be recognized includes: detecting the object to be recognized with the spectral-based analysis device; and recording the recognition spectral response data of the image sensor of the spectral-based analysis device to the object to be recognized.

[0058] Step S130: Determine the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data. That is, in the embodiments of the present application, it is not necessary to perform spectral restoration based on the reference spectral response data and the recognition spectral response data. For example, it is not necessary to restore spectral data such as reflectivity or absorptivity at different wavelengths, but directly compare the reference spectral response data with the recognition spectral response data to determine the recognition result of the object to be recognized. Specifically, the recognition result may be whether the object to be recognized is a standard object or whether the characteristics of the object to be recognized are heterogeneous from the characteristics of the standard object.

[0059] Therefore, through the object recognition method for a spectral-based analysis device according to the embodiments of the present application, object recognition can be directly performed based on the spectral response data of the reference object and the object to be recognized by the image sensor of the spectral-based analysis device, without the need to perform spectral restoration from the spectral response data, and thus without the need to know the transmission spectrum of the filter structure of the spectral-based analysis device.

[0060] Moreover, since the object recognition method for a spectral-based analysis device according to the embodiments of the present application does not require spectral restoration during the object recognition process, the calculation error and calculation amount during the object recognition process are reduced. Accordingly, the object recognition speed is accelerated, and the calculation unit is simplified or the power consumption of the calculation unit is reduced.

[0061] In addition, since the object recognition method for a spectral-based analysis device according to the embodiments of the present application does not require spectral restoration, compared with the solution of restoring the spectrum, less information is required during the object recognition process. It can be understood that in the embodiments of the present application, since spectral restoration is not required, the number of effective pixel units can be reduced to a certain extent to complete the recognition. Therefore, the spatial resolution of the object data collected can be improved, or an image sensor with a smaller area can be used to achieve object recognition.

[0062] Of course, those skilled in the art can understand that in the object recognition method for a spectral-based analysis device according to the embodiments of the present application, the spectral response data of the reference object and the object to be recognized are directly used by the image sensor to perform object recognition. This does not limit that the spectral-based analysis device according to the embodiments of the present application further includes a calculation unit for further processing the spectral response data to obtain other spectral-related information for realizing other applications.

[0063] Next, various examples of comparing the reference spectral response data with the recognition spectral response data in the object recognition method for a spectral-based analysis device according to the embodiments of the present application will be described in detail.

[0064] In a first example, a regression method can be used to compare the reference spectral response data with the identified spectral response data. Specifically, if the object to be identified and the reference object are the same object, their spectral response data should be exactly the same or substantially the same. In this way, the responses of the reference object and the object to be identified can be used as the x and y axis coordinates respectively. If the object to be identified and the reference object are the same object (or have the same characteristics), the response points should generally fall on the straight line passing through the two points (0,0) and (1,1), as shown in Figure 3 (a) of. However, in the actual object recognition process, due to reasons such as noise and some differences in the spectral responses of the objects themselves, the response points will deviate from this straight line, but still be near the straight line, as shown in Figure 3 (b) of. If they are not the same object or objects with different characteristics, the response points will deviate significantly from the above straight line, as shown in Figure 3 (c) of. Here, Figure 3 FIG. shows a schematic diagram of a regression comparison method for an object recognition method of a spectral-based analysis device according to an embodiment of the present application.

[0065] Specifically, in the actual regression calculation process, a certain threshold α can be set. When the average distance of all points from the straight line is greater than α, it is considered that the object to be identified is different from the reference object, and when the average distance of all points from the straight line is less than α, it is considered that the object to be identified is the same as the reference object. Of course, in addition to using the average value of the distances, other parameters such as the mean square value of the distances can also be used.

[0066] Therefore, in the object recognition method of a spectral-based analysis device according to an embodiment of the present application, determining the recognition result of the object to be identified based on the comparison result of the reference spectral response data and the identified spectral response data includes: respectively forming a binary array corresponding to each pixel unit by using the first value corresponding to each pixel unit of the image sensor in the reference spectral response data and the second value corresponding to each pixel unit in the identified spectral response data; mapping the first value and the second value in the multiple binary arrays to the x and y coordinates of a rectangular coordinate system to obtain multiple data points on the rectangular coordinate system; fitting a straight line based on the multiple data points on the rectangular coordinate system; and determining the recognition result of the object to be identified based on the distances between the multiple data points and the straight line.

[0067] Moreover, in the above object recognition method for the spectral-based analysis device, determining the recognition result of the object to be recognized based on the distances between the multiple data points and the straight line includes: determining the average value or the root mean square value of the multiple distances from the multiple data points to the straight line; determining whether the average value or the root mean square value of the multiple distances is greater than a predetermined threshold; and, in response to the average value or the root mean square value of the multiple distances being less than or equal to the predetermined threshold, determining that the object to be recognized is the same as or has the same characteristics as the reference object.

[0068] In addition, in the first example, the KL divergence method, as well as methods such as artificial neural networks and decision trees, can also be used to implement the comparison between the reference spectral response data and the recognition spectral response data.

[0069] Specifically, for the artificial neural network method, when in use, the reference spectral response data obtained from the reference object and the recognition spectral response data obtained from the object to be recognized are respectively used as the inputs of the neural network. According to the similarity between the two, for example, whether the output distance (such as the Euclidean distance, etc.) exceeds the threshold, to determine whether the reference object and the object to be recognized are the same. In addition, when training the neural network, for example, triplet inputs can be used, with two being the inputs of the reference object and one being the input of another object. And when using triplet inputs for training, the loss function for training the neural network is to make the difference between "the distance between the outputs of the two reference object inputs after passing through the neural network" and "the distance between the outputs of one reference object and one other object after passing through the neural network" as large as possible.

[0070] For the decision tree-based algorithm, a possible implementation is that, according to the trained tree model, each input will sequentially pass through some nodes, and each node will discriminate on specific features of the input and then pass it to the next node, and finally output to a leaf node, and the label of the output is the label of the leaf node where it terminates. Therefore, the root of the tree model is based on the sequential discrimination of the features contained in the data. When training a single tree model, each node of the tree uses a certain feature as the splitting feature and determines the optimal splitting feature based on the change in the Gini coefficient before and after splitting. The random forest is an ensemble technique that reselects K new data sets by sampling the original data set with replacement multiple times to train the classifier, that is, training multiple trees, and the final result is the synthesis of the results of multiple trees.

[0071] Therefore, in the object recognition method for a spectral-based analysis device according to an embodiment of the present application, determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data includes: comparing the reference spectral response data and the recognition spectral response data through a neural network model or a decision tree model; and determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data.

[0072] In the second example, instead of comparing all the data in the reference spectral response data and the recognition spectral response data, only a part of the data is compared. That is, instead of comparing the output electrical signal values of all the pixel points of the image sensor, the values of some points are used for comparison. For example, for Figure 2 the miniaturized spectral-based analysis device shown, there may be a situation where the optical structure has poor light uniformity, which may cause the spectra of the light reaching different positions of the filter to be different (including different intensities). Correspondingly, when analyzing the characteristics of a leaf, the spectral imaging information of the vein part will be determined as invalid information, and the spectral imaging response information of this part cannot be used to compare with the spectral imaging response information of the leaf. In addition, it may also be due to the reason of the object itself. For example, when testing a fingerprint, due to the grooves of the fingerprint, no valid information can be obtained at the grooves.

[0073] Therefore, in the second example, first, a predetermined algorithm is used to determine which of the spectral response data obtained by the image sensor are valid information, and then the reference spectral response data of the valid information part is compared with the recognition spectral response data.

[0074] Of course, those skilled in the art can understand that in the case where the resolution of the image sensor is very high, due to the large number of pixel points, for the consideration of the calculation amount, part of the data in the reference spectral response data and the recognition spectral response data, such as the data of some rows and some columns, can also be used for comparison.

[0075] In addition, the predetermined algorithm for determining whether it is valid information can be threshold determination, or methods such as pattern matching, transformers, neural networks, etc., to determine whether it is valid information according to the image data. And for the threshold determination method, a suitable threshold t can be set. When the value of a certain pixel in the spectral response data exceeds t, it is considered a valid pixel and used as the data to be determined, otherwise the data of this pixel is discarded.

[0076] In addition, if it cannot be guaranteed that the reference object and the object to be recognized have the same valid pixel positions or that the pixel positions are exactly aligned, multiple measurements can be performed when measuring the reference object. Moreover, based on the results of the multiple measurements, the valid value of the pixel point is comprehensively obtained. For example, one method to obtain the valid value is to take the mean of all measured values exceeding the threshold to obtain the final measurement result.

[0077] Therefore, in the object recognition method for a spectral-based analysis device according to an embodiment of the present application, determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data includes: determining a first part of data in the reference spectral response data and a second part of data in the recognition spectral response data corresponding to the first part of data; and determining the recognition result of the object to be recognized based on the comparison result between the first part of data and the second part of data.

[0078] Moreover, in the above object recognition method for a spectral-based analysis device, determining a first part of data in the reference spectral response data and a second part of data in the recognition spectral response data corresponding to the first part of data includes: determining first valid information in the reference spectral response data and second valid information in the recognition spectral response data based on a predetermined algorithm; and determining the first part of data and the second part of data based on the first valid information and the second valid information.

[0079] In addition, in the above object recognition method for a spectral-based analysis device, determining the first valid information in the reference spectral response data includes: in response to the valid information in the reference spectral response data obtained by a single measurement not corresponding to the second valid information in the recognition spectral response data, obtaining multiple reference spectral response data through multiple measurements; and determining the first valid information based on the multiple reference spectral response data.

[0080] It is worth mentioning that the method mentioned in the second example can be used in the first example. Specifically, in the first example, there may be some measurement errors, resulting in relatively large deviations in the values obtained by individual sensing units, which will cause a large distance when represented on the coordinate axis, thus resulting in a possibly large average value. Therefore, in the first example, the reasonable error value judged in the second example is introduced and excluded as invalid data, thereby improving the accuracy.

[0081] In view of the above problems, in the embodiments of the present application, a variant example based on the first example is further proposed, that is, instead of judging by the average distance. In this variant example, first, a threshold β is set. When the distance between a point and a straight line is greater than β, the point is considered an invalid point; when the distance between the point and the straight line is less than β, the point is considered a valid point. Further, the proportion of valid points is calculated, that is, the number of valid points / (the number of valid points + the number of invalid points). When the proportion is greater than or equal to 75%, it is considered that the object to be recognized is the same as the reference object. Of course, for individual scenarios with high precision requirements, the proportion should be greater than or equal to 85%, or even 90%.

[0082] In the third example, the filter structure in the spectral analysis device may not completely cover the image sensor, that is, a part of the area of the image sensor in the spectral analysis device is used to receive spectral information, and a part of the area is used to receive light intensity information (image information). Specifically, as Figure 4 shown, the spectral analysis device includes a spectral chip, and the spectral chip includes a light modulation layer 1100, an image sensing layer 1200, and an optional signal processing circuit layer 1300 that are sequentially stacked along the thickness direction. Here, Figure 4 FIG. illustrates an example of a filter structure of an object recognition method for a spectral analysis device according to an embodiment of the present application.

[0083] Specifically, at least one modulation unit 1101 and at least one non-modulation unit 1102 are distributed on the surface of the light modulation layer 1100. A plurality of sensing units 1201 are distributed on the surface of the image sensing layer 1200, and each modulation unit 1101 and each non-modulation unit 1102 respectively correspond to at least one sensing unit 1201 along the thickness direction. Each modulation unit 1101 and each non-modulation unit 1102 respectively form a pixel point of the spectral chip 1000 with the corresponding sensing unit 1201. The modulation unit 1101 of the light modulation layer 1100 is configured to modulate the imaging light entering the corresponding sensing unit 1201, and the corresponding sensing unit 1201 is adapted to obtain the spectral information of the imaging light. Moreover, the non-modulation unit 1102 of the light modulation layer 1100 is configured not to modulate the imaging light entering the corresponding sensing unit 1201, and the corresponding sensing unit 1201 is adapted to obtain the light intensity information of the imaging light.

[0084] The signal processing circuit layer 1300 is electrically connected to the sensing unit 1201. The signal processing circuit layer 1300 is configured to obtain the electrical signal output by the sensing unit 1201, such as the spectral response data as described above. The thickness of the optical modulation layer 1100 is 60 nm to 1200 nm. The optical modulation layer 1100 can be directly fabricated on the image sensing layer 1200. Specifically, one or more layers of materials can be directly grown on the image sensing layer 1200 and then the modulation units are fabricated by etching, or the modulation units are directly etched on the image sensing layer 1200, thereby obtaining the optical modulation layer 1100.

[0085] In this case, it can be considered that the image sensor has a sub-region structure. Therefore, the object recognition method of the spectral-based analysis device according to the embodiments of the present application can be considered to be implemented using the sub-region technology. That is, the filter structure corresponding to a part of the image sensor is an all-pass filter structure or an RGB filter structure. The output data of the image sensor corresponding to this part of the filter structure is light intensity data (non-spectral information). This part of the information can be used to generate an image of the object to be measured. In addition, these non-spectral information can also assist in the screening of the spectral data in the second example as described above.

[0086] For example, during the fingerprint unlocking process, the non-spectral information can be used to detect the fingerprint of the finger for fingerprint recognition, that is, the non-spectral information will generate a fingerprint image. The spectral information can use the method in the second example to identify whether the fingerprint to be recognized is a live fingerprint. Only when both the fingerprint image and the live fingerprint conditions are satisfied can the fingerprint unlocking be achieved. Optionally, during fingerprint recognition, the screening described in the second example can also be assisted by using image information. Since the non-spectral information can determine where there are grooves and where there are ridges, the spectral information corresponding to the groove area can be excluded (because the light intensity is too weak), and only the spectral information corresponding to the ridges is used for comparison and judgment.

[0087] In addition, for example, in the case of uneven illumination light intensity, the non-spectral area can detect the magnitude of the ambient light intensity in this area, and then correct the light intensity detected by the spectral pixel area according to the ambient light intensity. For example, if the ambient light intensity in the area is less than the standard ambient light intensity, the input of the spectral pixel area is increased and then compared; if the ambient light intensity in the area is greater than the standard ambient light intensity, the input of the spectral pixel area is decreased and then compared.

[0088] For another example, when identifying an object with contours and shapes, the contours and shapes of the object can be detected first through the information in the non-spectral area, and the contours and shapes in the spectral area can be predicted, and then the light intensity of the incident spectral area can be inferred. According to this predicted light intensity, the original reading of the spectral area is corrected and then compared. For example, in the case of fingerprint recognition, the image information can determine whether it is the center of the gully, the center of the texture, or between the texture and the gully. In this way, the intensity of the incident light can be predicted, and then the light intensity can be modified accordingly for comparison. This can increase the amount of spectral information used for comparison and make the spectral information more accurately represented.

[0089] That is, the light intensity information (non-spectral information) can be used for imaging and also for assisting in obtaining more accurate spectral information.

[0090] Therefore, in the object recognition method for a spectral-based analysis device according to an embodiment of the present application, the image sensor includes a first sensing unit corresponding to a modulation unit of a light modulation layer and a second sensing unit corresponding to a non-modulation unit of the light modulation layer, and the method further includes: obtaining first auxiliary information of the second sensing unit of the image sensor for the reference object; obtaining second auxiliary information of the second sensing unit of the image sensor for the object to be recognized; and determining the recognition result of the object to be recognized based on the comparison result of the reference spectral response data with the recognition spectral response data includes: using the first auxiliary information and the second auxiliary information as a reference, and determining the recognition result of the object to be recognized based on the comparison result of the reference spectral response data with the recognition spectral response data.

[0091] Furthermore, in the above-mentioned object recognition method for a spectral-based analysis device, the first auxiliary information and the second auxiliary information are used as references, and the recognition result of the object to be recognized is determined based on the comparison result of the reference spectral response data and the identification spectral response data, including: using the first auxiliary information and the second auxiliary information as references, determining the first valid information in the reference spectral response data and the second valid information in the identification spectral response data; determining the first part of the data in the reference spectral response data and the second part of the data in the identification spectral response data based on the first valid information and the second valid information; and, determining the recognition result of the object to be recognized based on the comparison result of the first part of the data and the second part of the data.

[0092] In addition, in the above object recognition method for a spectrum-based analysis device, using the first auxiliary information and the second auxiliary information as references, determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data includes: using the first auxiliary information and the second auxiliary information as references, obtaining qualified reference spectral response data and recognition spectral response data by changing the acquisition environments of the reference spectral response data and the recognition spectral response data; and determining the recognition result of the object to be recognized based on the comparison result between the qualified reference spectral response data and the recognition spectral response data.

[0093] In addition, in the above object recognition method for a spectrum-based analysis device, using the first auxiliary information and the second auxiliary information as references, determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data includes: using the first auxiliary information and the second auxiliary information as references, correcting the acquired reference spectral response data and recognition spectral response data to obtain corrected reference spectral response data and recognition spectral response data; and determining the recognition result of the object to be recognized based on the comparison result between the corrected reference spectral response data and the recognition spectral response data.

[0094] In the fourth example, a normalization process of the spectral response data can be added, thereby solving problems such as the change in illumination intensity of a light source (such as ambient light or an active light source, etc.).

[0095] In addition, those skilled in the art can understand that when applied in combination with the second example or the third example, the normalization process can be performed before or after data screening.

[0096] Moreover, there are various normalization methods, such as performing a linear transformation on the original data. There are also various methods for the coefficients of the linear transformation. For example, the maximum value is transformed into 1, the minimum value is transformed into 0, and other values are linearly transformed accordingly. That is, if the output values of all pixels of an image sensor are x i , where i represents the label, then its linear transformation is

[0097]

[0098] For another example, the average value μ and the standard deviation σ of the measured values are obtained. For the measured x value, a transformation y = (x - μ) / σ is performed to obtain the normalized value.

[0099] Therefore, in the object recognition method for a spectral-based analysis device according to an embodiment of the present application, determining the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data includes: normalizing the reference spectral response data and the recognition spectral response data respectively to obtain first normalized data and second normalized data; and determining the recognition result of the object to be recognized based on the comparison result between the first normalized data and the second normalized data.

[0100] In the fifth example, when entering a reference object, multiple standard reference objects or standard reference objects with multiple characteristics can be entered. During object recognition, the information of the object to be recognized is compared with the information of multiple entered objects to obtain which standard reference object (or none of them) or to judge the characteristics. It should be noted that the information of the multiple standard objects can be entered into the terminal product, i.e., the spectral-based analysis device, or a mobile terminal, such as a computer, a mobile phone, etc., or can also be entered into the cloud and retrieved according to requirements.

[0101] Therefore, in the object recognition method for a spectral-based analysis device according to an embodiment of the present application, obtaining the reference spectral response data of the image sensor of the spectral-based analysis device for a reference object includes: obtaining multiple reference spectral response data of the image sensor of the spectral-based analysis device for multiple standard reference objects or standard reference objects with multiple characteristics respectively.

[0102] Moreover, in the above object recognition method for a spectral-based analysis device, the multiple reference spectral response data are stored in the spectral-based analysis device, a mobile terminal or the cloud.

[0103] Exemplary device

[0104] Figure 5 The block diagram of an object recognition device for a spectral-based analysis device according to an embodiment of the present application is illustrated.

[0105] As Figure 5 shown, the object recognition device 200 for a spectral-based analysis device according to an embodiment of the present application includes: a reference data acquisition unit 210, configured to obtain the reference spectral response data of the image sensor of the spectral-based analysis device for a reference object; an identification data acquisition unit 220, configured to obtain the identification spectral response data of the image sensor of the spectral-based analysis device for the object to be recognized; and a comparison and identification unit 230, configured to determine the recognition result of the object to be recognized based on the comparison result between the reference spectral response data acquired by the reference data acquisition unit 210 and the identification spectral response data acquired by the identification data acquisition unit 220.

[0106] In one example, in the object recognition device 200 for the spectral-based analysis device described above, the reference data acquisition unit 210 is configured to: detect the reference object with the spectral-based analysis device; and record the reference spectral response data of the reference object by the image sensor of the spectral-based analysis device.

[0107] In one example, in the object recognition device 200 for the spectral-based analysis device described above, the recognition data acquisition unit 220 is configured to: detect the object to be recognized with the spectral-based analysis device; and record the recognition spectral response data of the object to be recognized by the image sensor of the spectral-based analysis device.

[0108] In one example, in the object recognition device 200 for the spectral-based analysis device described above, the comparison and recognition unit 230 is configured to: form a binary array corresponding to each pixel unit by respectively taking the first value corresponding to each pixel unit of the image sensor in the reference spectral response data and the second value corresponding to each pixel unit in the recognition spectral response data; map the first value and the second value in the multiple binary arrays to the rectangular coordinate system as the abscissa and ordinate of the rectangular coordinate system to obtain multiple data points on the rectangular coordinate system; fit a straight line based on the multiple data points on the rectangular coordinate system; and determine the recognition result of the object to be recognized based on the distances between the multiple data points and the straight line.

[0109] In one example, in the object recognition device 200 for the spectral-based analysis device described above, the comparison and recognition unit 230 determines the recognition result of the object to be recognized based on the distances between the multiple data points and the straight line, including: determining the average value or the root mean square value of the multiple distances from the multiple data points to the straight line; determining whether the average value or the root mean square value of the multiple distances is greater than a predetermined threshold; and in response to the average value or the root mean square value of the multiple distances being less than or equal to the predetermined threshold, determining that the object to be recognized is the same as or has the same characteristics as the reference object.

[0110] In one example, in the object recognition device 200 for the spectral-based analysis device described above, the comparison and recognition unit 230 is configured to: compare the reference spectral response data with the recognition spectral response data through a neural network model or a decision tree model; and determine the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data.

[0111] In one example, in the object recognition device 200 for the above-mentioned spectrum-based analysis device, the comparison and recognition unit 230 is configured to: determine a first part of data in the reference spectrum response data and a second part of data in the recognition spectrum response data corresponding to the first part of data; and determine the recognition result of the object to be recognized based on the comparison result between the first part of data and the second part of data.

[0112] In one example, in the object recognition device 200 for the above-mentioned spectrum-based analysis device, the comparison and recognition unit 230 determines the first part of data in the reference spectrum response data and the second part of data in the recognition spectrum response data corresponding to the first part of data, including: determining first effective information in the reference spectrum response data and second effective information in the recognition spectrum response data based on a predetermined algorithm; and determining the first part of data and the second part of data based on the first effective information and the second effective information.

[0113] In one example, in the object recognition device 200 for the above-mentioned spectrum-based analysis device, the comparison and recognition unit 230 determines the first effective information in the reference spectrum response data, including: in response to the effective information obtained from a single measurement in the reference spectrum response data not corresponding to the second effective information in the recognition spectrum response data, obtaining a plurality of reference spectrum response data through multiple measurements; and determining the first effective information based on the plurality of reference spectrum response data.

[0114] In one example, in the object recognition device 200 for the above-mentioned spectrum-based analysis device, the image sensor includes a first sensing unit corresponding to a modulation unit of a light modulation layer and a second sensing unit corresponding to a non-modulation unit of the light modulation layer. The device further includes: an auxiliary information acquisition unit, configured to acquire first auxiliary information of the second sensing unit of the image sensor for the reference object and second auxiliary information of the second sensing unit of the image sensor for the object to be recognized; and the comparison and recognition unit 230 is configured to: use the first auxiliary information and the second auxiliary information as references, and determine the recognition result of the object to be recognized based on the comparison result between the reference spectrum response data and the recognition spectrum response data.

[0115] In one example, in the object recognition device 200 for the above-mentioned spectrum-based analysis device, the comparison and recognition unit 230 uses the first auxiliary information and the second auxiliary information as references, and determines the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data, including: using the first auxiliary information and the second auxiliary information as references, determining the first valid information in the reference spectral response data and the second valid information in the recognition spectral response data; determining the first partial data in the reference spectral response data and the second partial data in the recognition spectral response data based on the first valid information and the second valid information; and determining the recognition result of the object to be recognized based on the comparison result between the first partial data and the second partial data.

[0116] In one example, in the object recognition device 200 for the above-mentioned spectrum-based analysis device, the comparison and recognition unit 230 uses the first auxiliary information and the second auxiliary information as references, and determines the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data, including: using the first auxiliary information and the second auxiliary information as references, obtaining qualified reference spectral response data and recognition spectral response data by changing the acquisition environments of the reference spectral response data and the recognition spectral response data; and determining the recognition result of the object to be recognized based on the comparison result between the qualified reference spectral response data and the recognition spectral response data.

[0117] In one example, in the object recognition device 200 for the above-mentioned spectrum-based analysis device, the comparison and recognition unit 230 uses the first auxiliary information and the second auxiliary information as references, and determines the recognition result of the object to be recognized based on the comparison result between the reference spectral response data and the recognition spectral response data, including: using the first auxiliary information and the second auxiliary information as references, correcting the acquired reference spectral response data and recognition spectral response data to obtain corrected reference spectral response data and recognition spectral response data; and determining the recognition result of the object to be recognized based on the comparison result between the corrected reference spectral response data and the recognition spectral response data.

[0118] In one example, in the object recognition device 200 for the above-mentioned spectrum-based analysis device, the comparison and recognition unit 230 is configured to: normalize the reference spectral response data and the recognition spectral response data respectively to obtain first normalized data and second normalized data; and determine the recognition result of the object to be recognized based on the comparison result between the first normalized data and the second normalized data.

[0119] In one example, in the object recognition device 200 for the spectral-based analysis device described above, the reference data acquisition unit 210 is configured to: acquire multiple reference spectral response data of the image sensor of the spectral-based analysis device for multiple standard reference objects or standard reference objects with multiple characteristics respectively.

[0120] In one example, in the object recognition device 200 for the spectral-based analysis device described above, the multiple reference spectral response data are stored in the spectral-based analysis device, a mobile terminal, or the cloud.

[0121] Here, those skilled in the art can understand that the specific functions and operations of each unit and module in the object recognition device 200 for the spectral-based analysis device described above have been introduced in detail in the object recognition method for the spectral-based analysis device described above, and thus, the repeated description thereof will be omitted. Figures 1 to 4 As described above, the object recognition device 200 for the spectral-based analysis device according to the embodiments of the present application can be implemented in various terminal devices, such as a spectral-based analysis device, a mobile terminal, or a server set in the cloud. In one example, the object recognition device 200 for the spectral-based analysis device according to the embodiments of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the object recognition device 200 for the spectral-based analysis device can be a software module in the operating system of the terminal device, or can be an application program developed for the terminal device; of course, the object recognition device 200 for the spectral-based analysis device can also be one of the numerous hardware modules of the terminal device.

[0122] Alternatively, in another example, the object recognition device 200 for the spectral-based analysis device and the terminal device can also be separate devices, and the object recognition device 200 for the spectral-based analysis device can be connected to the terminal device through a wired and / or wireless network and transmit interaction information in accordance with a predefined data format.

[0123]

[0124] Exemplary electronic device

[0125] Figure 6 Next, reference is made to to describe the electronic device according to the embodiments of the present application.

[0126] Figure 6 The block diagram of the electronic device according to the embodiments of the present application is illustrated.

[0127] Figure 6 As Figure 6As shown, the electronic device 10 includes one or more processors 11 and a memory 12.

[0128] The processor 11 can be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and can control other components in the electronic device 10 to perform desired functions.

[0129] The memory 12 can include one or more computer program products, and the computer program products can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory can include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory can include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions can be stored on the computer-readable storage media, and the processor 11 can run the program instructions to implement the object recognition method for the spectral-based analysis device and / or other desired functions of the various embodiments of the present application described above. Various contents such as reference spectral response data, recognition spectral response data, comparison results, etc. can also be stored in the computer-readable storage media.

[0130] In one example, the electronic device 10 can further include: an input device 13 and an output device 14, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0131] For example, the input device 13 can be, for example, a keyboard, a mouse, etc.

[0132] The output device 14 can output various information to the outside, such as the recognition result of the object to be recognized. The output device 14 can include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0133] Of course, for simplicity, Figure 6 only some of the components related to the present application in the electronic device 10 are shown, and components such as buses, input / output interfaces, etc. are omitted. In addition, according to specific application scenarios, the electronic device 10 can further include any other appropriate components.

[0134] Exemplary computer program product and computer-readable storage medium

[0135] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions that, when run by a processor, cause the processor to execute the steps in the object recognition method for a spectral-based analysis device according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0136] The computer program product can be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present application. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The programming code can be executed entirely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0137] Furthermore, an embodiment of the present application may also be a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are run by a processor, the processor is caused to execute the steps in the object recognition method for a spectral-based analysis device according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0138] The computer-readable storage medium may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0139] Exemplary fingerprint recognition module

[0140] An application example of the object recognition method, apparatus, and electronic device for a spectral-based analysis device according to an embodiment of the present application is a fingerprint recognition module.

[0141] Figure 7 A schematic block diagram of a fingerprint recognition module according to an embodiment of the present application is illustrated.

[0142] As Figure 7As shown, the fingerprint recognition module 300 according to an embodiment of the present application includes: an optical system 310; a spectral chip 320 for generating reference spectral response data for a reference fingerprint and recognition spectral response data for a fingerprint to be recognized; and a recognition module 330 for determining whether the fingerprint to be recognized matches the reference fingerprint based on a comparison result between the reference spectral response data and the recognition spectral response data. Here, for example, the recognition module 330 may be specifically implemented as the object recognition device or the electronic device of the spectral-based analysis device according to an embodiment of the present application as described above.

[0143] In the fingerprint recognition module according to an embodiment of the present application, the fingerprint image passing through the optical system will appear clear in the center and blurred around, as Figure 8 shown. Figure 8 The figure illustrates an imaging schematic diagram of the fingerprint recognition module according to an embodiment of the present application. Here, the optical system 310 of the fingerprint recognition module is generally a lens assembly. In this case, the edge pixels can be used to obtain spectral response data because the edge has better light homogenization characteristics, and the spectra of the light received by each pixel point are more consistent. For the part with a clear central image, a traditional intensity detector or an RGB detector can be used to detect the fingerprint pattern to achieve the simultaneous recognition of the fingerprint pattern and the live body information. It can be understood that in this case, at least part of the filter structure is disposed at the edge and / or four corners of the image sensor. Since the edge and / or four corners have better light homogenization characteristics, the spectral information can be made more accurate. Therefore, those skilled in the art can understand that due to the light homogenization characteristics, the imaging effect is poor at the edge and / or four corners. Therefore, the fingerprint recognition module according to an embodiment of the present application can cleverly turn the disadvantage into an advantage.

[0144] Therefore, in the fingerprint recognition module according to an embodiment of the present application, the spectral chip is used to generate reference spectral response data for the edge and / or four corners of the reference fingerprint and recognition spectral response data for the edge and / or four corners of the fingerprint to be recognized, as well as reference image data for the center of the reference fingerprint and recognition image data for the center of the fingerprint to be recognized; and the recognition module is used to determine whether the fingerprint to be recognized matches the reference fingerprint based on a first comparison result between the reference spectral response data and the recognition spectral response data, and a second comparison result between the reference image data and the recognition image data.

[0145] It should be noted that in the fingerprint recognition module according to the embodiments of the present application, a light filtering structure may also be provided on the image sensor in the central region, that is, spectral response data may also be obtained in the central region of the spectral chip. However, the processing methods for obtaining and comparing spectral response data in the central part may be different from those in the edge. For example, the comparison method similar to the first example described above is adopted at the edge, while the comparison method of the third example described above is adopted at the center.

[0146] Therefore, in the fingerprint recognition module according to the embodiments of the present application, the recognition module includes: a data division sub-unit, configured to divide the reference spectral response data into a first part of reference spectral response data and a second part of reference spectral response data corresponding to different parts of the fingerprint, and divide the recognition spectral response data into a first part of recognition spectral response data and a second part of recognition spectral response data corresponding to the different parts of the fingerprint; a first comparison sub-unit, configured to compare the first part of reference spectral response data with the first part of recognition spectral response data in a first manner to obtain a first comparison result; a second comparison sub-unit, configured to compare the second part of reference spectral response data with the second part of recognition spectral response data in a second manner to obtain a second comparison result; and a fingerprint matching sub-unit, configured to determine whether the fingerprint to be recognized matches the reference fingerprint based on the first comparison result and the second comparison result.

[0147] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, advantages, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, advantages, effects, etc. are essential for each embodiment of the present application. In addition, the above-disclosed specific details are only for the purpose of illustration and easy understanding, rather than limitations. The above details do not limit the present application to necessarily adopt the above specific details for implementation.

[0148] The block diagrams of the devices, apparatuses, equipment, and systems involved in the present application are only illustrative examples and do not intend to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any way. Words such as "including", "comprising", "having", etc. are open-ended words, meaning "including but not limited to", and can be used interchangeably with each other. The words "or" and "and" used herein refer to the word "and / or", and can be used interchangeably with each other, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to", and can be used interchangeably with each other.

[0149] It should also be noted that in the devices, equipment, and methods of the present application, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations shall be regarded as equivalent solutions of the present application.

[0150] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

[0151] The above description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for object recognition in a spectroscopy-based analysis device, characterized in that, Including: Obtaining reference spectral response data of a reference object by an image sensor of the spectral-based analysis device; Obtaining identification spectral response data of an object to be identified by the image sensor of the spectral-based analysis device; And Determining an identification result of the object to be identified based on a comparison result between the reference spectral response data and the identification spectral response data, including: Forming a binary array corresponding to each pixel unit by respectively using a first value corresponding to each pixel unit of the image sensor in the reference spectral response data and a second value corresponding to each pixel unit in the identification spectral response data; Mapping the first values and the second values in multiple binary arrays to a rectangular coordinate system as the abscissa and ordinate of the rectangular coordinate system to obtain multiple data points on the rectangular coordinate system; Fitting a straight line based on the multiple data points on the rectangular coordinate system; and Determining the identification result of the object to be identified based on distances between the multiple data points and the straight line.

2. The object recognition method for a spectral-based analysis device according to claim 1, characterized in that, Obtaining reference spectral response data of a reference object by an image sensor of the spectral-based analysis device includes: Detecting the reference object by the spectral-based analysis device; and Recording the reference spectral response data of the reference object by the image sensor of the spectral-based analysis device.

3. The object recognition method for a spectral-based analysis device according to claim 1, characterized in that, Obtaining identification spectral response data of an object to be identified by the image sensor of the spectral-based analysis device includes: Detecting the object to be identified by the spectral-based analysis device; and Recording the identification spectral response data of the object to be identified by the image sensor of the spectral-based analysis device.

4. The object recognition method for a spectral-based analysis device according to claim 1, characterized in that, Determining the identification result of the object to be identified based on distances between the multiple data points and the straight line includes: Determining an average value or a root mean square value of multiple distances from the multiple data points to the straight line; Determining whether the average value or the root mean square value of the multiple distances is greater than a predetermined threshold; and In response to the average value or the root mean square value of the multiple distances being less than or equal to the predetermined threshold, determining that the object to be identified is the same as or has the same characteristics as the reference object.

5. The object recognition method for a spectroscopic analysis device according to claim 1, characterized in that, The image sensor includes a first sensing unit corresponding to a modulation unit of a light modulation layer and a second sensing unit corresponding to a non-modulation unit of the light modulation layer, and the method further includes: Obtaining first auxiliary information of the second sensing unit of the image sensor for the reference object; Obtaining second auxiliary information of the second sensing unit of the image sensor for the object to be identified; and Determining the identification result of the object to be identified based on a comparison result between the reference spectral response data and the identification spectral response data includes: Using the first auxiliary information and the second auxiliary information as references, and determining the identification result of the object to be identified based on a comparison result between the reference spectral response data and the identification spectral response data.

6. The object recognition method for a spectral-based analysis device according to claim 5, characterized in that, Using the first auxiliary information and the second auxiliary information as references, and determining the identification result of the object to be identified based on a comparison result between the reference spectral response data and the identification spectral response data, including: Using the first auxiliary information and the second auxiliary information as references, determine the first valid information in the reference spectral response data and the second valid information in the identification spectral response data; Based on the first valid information and the second valid information, determine the first part of the data in the reference spectral response data and the second part of the data in the identification spectral response data; and Based on the comparison result of the first part of the data and the second part of the data, determine the identification result of the object to be identified.

7. The object recognition method for a spectral-based analysis device according to claim 5, characterized in that, Using the first auxiliary information and the second auxiliary information as references, determining the identification result of the object to be identified based on the comparison result between the reference spectral response data and the identification spectral response data includes: Using the first auxiliary information and the second auxiliary information as references, obtain the qualified reference spectral response data and the identification spectral response data by changing the acquisition environment of the reference spectral response data and the identification spectral response data; and Based on the comparison result of the qualified reference spectral response data and the identification spectral response data, determine the identification result of the object to be identified.

8. The object recognition method for a spectral-based analysis device according to claim 5, characterized in that, Using the first auxiliary information and the second auxiliary information as references, determining the identification result of the object to be identified based on the comparison result between the reference spectral response data and the identification spectral response data includes: Using the first auxiliary information and the second auxiliary information as references, correct the acquired reference spectral response data and the identification spectral response data to obtain the corrected reference spectral response data and the identification spectral response data; and Based on the comparison result of the corrected reference spectral response data and the identification spectral response data, determine the identification result of the object to be identified.

9. The object recognition method for a spectral-based analysis device according to claim 1, characterized in that, Obtaining the reference spectral response data of the image sensor of the spectral-based analysis device for a reference object includes: Obtain multiple reference spectral response data of the image sensor of the spectral-based analysis device for multiple standard reference objects or standard reference objects with multiple characteristics respectively.

10. The object recognition method for a spectral-based analysis device according to claim 9, characterized in that, The multiple reference spectral response data are stored in the spectral-based analysis device or in the cloud.

11. An object recognition device for a spectral-based analysis apparatus, characterized in that, Includes: A reference data acquisition unit for acquiring the reference spectral response data of the image sensor of the spectral-based analysis device for a reference object; An identification data acquisition unit for acquiring the identification spectral response data of the image sensor of the spectral-based analysis device for the object to be identified; A comparison and identification unit for determining the identification result of the object to be identified based on the comparison result between the reference spectral response data and the identification spectral response data, including: Form a binary array corresponding to each pixel unit by respectively combining the first value corresponding to each pixel unit of the image sensor in the reference spectral response data with the second value corresponding to each pixel unit in the identification spectral response data; Map the first value and the second value in the multiple binary arrays as the abscissa and ordinate of a rectangular coordinate system into the rectangular coordinate system to obtain multiple data points on the rectangular coordinate system; Fitting a straight line based on the multiple data points on the rectangular coordinate system; and Determining an identification result of the object to be identified based on the distances between the multiple data points and the straight line.

12. An electronic device, characterized in that, Comprising:[[]]END]] A processor; And A memory in which computer program instructions are stored, and when the computer program instructions are run on the processor, the processor is caused to execute the object identification method for a spectral-based analysis device according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, Computer program instructions are stored on the computer-readable storage medium, and when the computer program instructions are executed by a computing device, they are operable to execute the object identification method for a spectral-based analysis device according to any one of claims 1-10.

14. A fingerprint recognition module, characterized in that, Comprising:[[]]END]] An optical system; A spectral chip for generating reference spectral response data for a reference fingerprint and identification spectral response data for a fingerprint to be identified; And An identification module for determining whether the fingerprint to be identified matches the reference fingerprint based on a comparison result between the reference spectral response data and the identification spectral response data, comprising:[[]]END]] Forming a binary array corresponding to each pixel unit by respectively combining a first value corresponding to each pixel unit of the image sensor in the reference spectral response data with a second value corresponding to each pixel unit in the identification spectral response data; Mapping the first values and the second values in the multiple binary arrays to the rectangular coordinate system as the abscissa and ordinate of the rectangular coordinate system to obtain multiple data points on the rectangular coordinate system; Fitting a straight line based on the multiple data points on the rectangular coordinate system; and Determining whether the fingerprint to be identified matches the reference fingerprint based on the distances between the multiple data points and the straight line.

15. The fingerprint identification module according to claim 14, wherein The spectral chip is used for generating reference spectral response data for the edge and / or four corners of the reference fingerprint and identification spectral response data for the edge and / or four corners of the fingerprint to be identified, as well as reference image data for the center of the reference fingerprint and identification image data for the center of the fingerprint to be identified; And The identification module is used for determining whether the fingerprint to be identified matches the reference fingerprint based on a first comparison result between the reference spectral response data and the identification spectral response data, and a second comparison result between the reference image data and the identification image data.

16. The fingerprint recognition module according to claim 14, wherein The identification module comprises:[[]]END]] A data division sub-unit for dividing the reference spectral response data into a first part of reference spectral response data and a second part of reference spectral response data corresponding to different parts of the fingerprint, and dividing the identification spectral response data into a first part of identification spectral response data and a second part of identification spectral response data corresponding to the different parts of the fingerprint; A first comparison sub-unit for comparing the first part of reference spectral response data with the first part of identification spectral response data in a first manner to obtain a first comparison result; A second comparison subunit, configured to compare the second part of the reference spectral response data and the second part of the identified spectral response data in a second manner to obtain a second comparison result; and A fingerprint matching subunit, configured to determine whether the fingerprint to be identified matches the reference fingerprint based on the first comparison result and the second comparison result.

Images