Image processing method and device, electronic equipment and storage medium

Abstract

An image processing method and device, electronic equipment and storage medium are disclosed. The image processing method comprises: collecting a target image to be processed; selecting a target base texture class corresponding to the target image from a base texture library, the base texture library comprising a plurality of base texture classes; determining whether the image quality and exposure intensity of the target image meet preset conditions; if the image quality and exposure intensity of the target image meet the preset conditions, obtaining an update coefficient according to the image quality and exposure intensity, and updating the target base texture class in proportion according to the update coefficient; and performing floating proportional updating on the base texture library in the case that the image quality and exposure intensity of the target image meet the requirements, so that the base texture library can better reflect the real state of the current base texture. The image processing device and electronic equipment can execute the aforementioned image processing method, and the storage medium stores a computer program executable by a processor to complete the aforementioned image processing method.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of fingerprint identification, and in particular to an image processing method and device, an electronic device and a storage medium. BACKGROUND

[0002] With the continuous development of fingerprint identification technology, under-screen fingerprint identification technology is favored by manufacturers due to its unique advantages. Among them, optical fingerprint identification technology has gradually become the mainstream of the market, and is widely used in daily attendance machines, access control, and smart phones of major brands. For example, the principle of under-screen optical fingerprint identification of a smart phone is to use the refraction and reflection of light. When the finger presses the screen, the OLED (Organic Light Emitting Diode) screen emits light to illuminate the finger area, and the reflected light of the illuminated finger area returns through the gap between the screen pixels to the optical fingerprint module close to the screen. After the optical fingerprint module collects the fingerprint image according to the reflected light, it can be determined whether the fingerprint in the collected image is consistent with the pre-recorded fingerprint, thereby realizing fingerprint identification.

[0003] Under-screen optical fingerprint identification can largely avoid the interference of ambient light and has better stability in extreme environments. The fingerprint image collected by using under-screen optical fingerprint technology usually contains both fingerprint information and ridge information, as shown in Figure 1a To obtain a fingerprint image, the ridge information must be removed. At present, most image processing methods for under-screen optical fingerprint identification are to pre-collect ridges in different states, as shown in Figure 1b Some of the data are used to complete the ridge removal, for example, the fingerprint image collected as shown in Figure 1a is subtracted from the pre-collected ridge as shown in Figure 1b , to obtain a fingerprint image without ridge information as shown in Figures 2a to 2c However, in actual use, the current ridge information in the collected fingerprint image will be different from the pre-collected ridge, for example, the current ridge information changes due to changes in factors such as collection method, time, light intensity, and sensor performance. When the ridge is removed, the residual ridge becomes obvious, and in Figures 2a to 2c introducing error features 101 to 103, it can be seen that with the changes in the above factors, the error features 101, 102 and 103 become more and more obvious, thereby increasing the failure acceptance rate (FAR, Failure Acceptance Rate) and the failure rejection rate (FRR, Failure Rejection rate), which adversely affects the identification rate.

[0004] Therefore, an improved image processing method is expected to solve the above problems. SUMMARY

[0005] In view of the above problems, the purpose of the present application is to provide an image processing method and device, electronic equipment and storage medium, which can better remove the effect of the bottom line and update the related information of the bottom line in real time each time the target image is collected.

[0006] According to an aspect of the present application, an image processing method is provided, comprising: collecting a target image to be processed; selecting a target bottom line class corresponding to the target image from a bottom line library, wherein the bottom line library comprises a plurality of bottom line classes; determining whether the image quality and exposure intensity of the target image meet a preset condition; if the image quality and exposure intensity of the target image meet the preset condition, obtaining an update coefficient according to the image quality and exposure intensity, and updating the target bottom line class in proportion according to the update coefficient.

[0007] Optionally, the step of determining whether the image quality and exposure intensity of the target image meet a preset condition further comprises: obtaining a target bottom line according to the target bottom line class, and obtaining a bottom line-removed image according to the target image and the target bottom line.

[0008] Optionally, the step of obtaining a target bottom line according to the target bottom line class comprises: calculating the mean value of a selected bottom line image in the target bottom line class to obtain the target bottom line.

[0009] Optionally, the step of obtaining a bottom line-removed image based on the target bottom line and the target image comprises: subtracting the target bottom line from the target image to obtain the bottom line-removed image.

[0010] Optionally, the step of collecting a target image to be processed further comprises: collecting a plurality of bottom line images, and classifying the plurality of bottom line images into different bottom line classes according to their exposure intensities to obtain the bottom line library.

[0011] Optionally, the step of collecting a plurality of bottom line images comprises: collecting bottom line images under a plurality of different light intensities at equal intervals, and classifying the bottom line images under the plurality of different light intensities into a plurality of different bottom line classes corresponding thereto to generate the bottom line library.

[0012] Optionally, the step of collecting a plurality of bottom line images comprises: collecting bottom line images under three different light intensities at equal intervals, and classifying the bottom line images under the three different light intensities into three different bottom line classes to generate the bottom line library.

[0013] Optionally, the step of determining whether the image quality and exposure intensity of the target image meet a preset condition comprises: when the image quality is greater than a first preset value and the exposure intensity is within a first preset range, determining that the image quality and exposure intensity of the target image meet the preset condition.

[0014] Optionally, the obtaining the update coefficient according to the image quality and the exposure intensity comprises: the update coefficient comprises an upper limit and a lower limit, the image quality and the exposure intensity are normalized, then the difference is obtained, and then the intermediate coefficient is obtained by multiplying the difference by the upper limit of the update coefficient; when the intermediate coefficient is less than or equal to the lower limit of the update coefficient, the value of the update coefficient is the lower limit of the update coefficient; when the value of the intermediate coefficient is between the upper limit and the lower limit of the update coefficient, the value of the update coefficient is the intermediate coefficient; and when the value of the intermediate coefficient is greater than or equal to the upper limit of the update coefficient, the value of the update coefficient is the upper limit of the update coefficient.

[0015] Optionally, the image quality is determined according to any one or a combination of several of the signal-to-noise ratio, the directionality, and the bad point of the target image.

[0016] Optionally, the normalization of the exposure intensity comprises: calculating the quotient of the absolute value of the difference between the exposure intensity and a signal target value and the signal target value; and the signal target value is selected from the first preset range.

[0017] Optionally, the updating the target base class in proportion according to the update coefficient comprises: adjusting the target image and the target base class to the same light intensity; and performing weighted summation on each base in the target image and the target base class respectively, wherein the weight of the target image is the update coefficient a, and the weight of each base in the target base class is 1-a.

[0018] According to another aspect of the present application, an image processing device is provided, comprising: an acquisition unit configured to acquire a target image and base information; a storage unit configured to store a base library comprising a plurality of base classes; and a control unit configured to select a target base class from the base library, determine whether the image quality of the target image and the exposure intensity meet a preset condition, obtain an update coefficient according to the image quality and the exposure intensity if the image quality of the target image and the exposure intensity meet the preset condition, and update the target base class in proportion according to the update coefficient.

[0019] Optionally, the control unit is further configured to obtain a target base according to the target base class, and obtain a base-removed image according to the target image and the target base.

[0020] Optionally, the acquisition unit is further configured to be capable of acquiring environmental parameters, wherein the environmental parameters comprise any one or several of the exposure intensity and the temperature.

[0021] According to still another aspect of the present application, there is provided an electronic device comprising: a storage medium storing program instructions executable; and a processor invoking the program instructions to perform the image processing method as described above.

[0022] According to still another aspect of the present application, there is provided a computer readable storage medium storing a computer program executable by a processor to perform the image processing method as described above.

[0023] The image processing method of the present application embodiment judges whether the image quality and the exposure intensity of the target image meet the preset conditions after the target image is collected, and only when both the image quality and the exposure intensity meet the requirements, the floating proportional update is performed on one or more ground classes, i.e. the update coefficient is obtained according to the image quality and the exposure intensity, and one or more target ground classes are updated in proportion according to the update coefficient, so that the ground library can better reflect the real state of the current ground.

[0024] Optionally, the image processing method of the present application embodiment collects the ground by using the method of calculating the ground at various exposure intensities with equal intervals, and the one or more ground classes in the ground library are updated in real time at each time of collecting the target image to offset the influence of other factors, so that a relatively clean fingerprint image can be obtained. The image processing method of the present application embodiment can reduce the residual ground information, thereby effectively improving the accuracy of the final fingerprint identification.

[0025] Optionally, in the image processing method of the present application embodiment, the one or more ground classes in the ground library are updated in real time in the process of collecting the target image subsequently, so as to offset the influence of other factors, and the ground library includes a fixed number of ground classes, and each ground class includes a fixed number of ground images, so that the number of ground classes or the number of ground images in each ground class does not need to be dynamically adjusted, and the storage and calling are easier. BRIEF DESCRIPTION OF DRAWINGS

[0026] The above and other objects, features and advantages of the present application will become more apparent from the following description of the preferred embodiments of the present application taken with reference to the accompanying drawings, in which:

[0027] Figure 1a A target image collected is shown;

[0028] Figure 1b A ground image collected in advance is shown;

[0029] Figures 2a to 2c A fingerprint image obtained by using the image processing method according to the prior art is shown;

[0030] Figure 3 A configuration stage of the image processing method of the present application embodiment is shown;

[0031] Figure 4a A method for removing a background shown in the image processing method according to the embodiment of the present application is shown;

[0032] Figure 4b A method for updating a background shown in the image processing method according to the embodiment of the present application is shown;

[0033] Figures 5a to 5c A fingerprint image obtained by the image processing method according to the embodiment of the present application is shown;

[0034] Figure 6 An image processing device according to the embodiment of the present application is shown;

[0035] Figure 7 An electronic device according to the embodiment of the present application is shown. DETAILED DESCRIPTION

[0036] Various embodiments of the present application will be described in detail below with reference to the accompanying drawings. In the various drawings, the same elements or modules are denoted by the same or similar reference numerals. For the sake of clarity, each part in the drawings is not drawn to scale.

[0037] It should be understood that, in the following description, "circuitry" can comprise a single or multiple components of hardware, programmable circuitry, state machine circuitry, and / or elements storing instructions for execution by programmable circuitry. When an element or circuitry is referred to as being "connected to" another element or "connected between" two nodes, it can be directly coupled or connected to the other element or there can be intervening elements between the elements, the connection between the elements can be physical, logical, or a combination thereof. In contrast, when an element is referred to as being "directly coupled to" or "directly connected to" another element, it implies that there are no intervening elements present.

[0038] Meanwhile, some words are used in the patent specification and claims to refer to certain components. It should be understood by those of ordinary skill in the art that the same component can be referred to by different names by hardware manufacturers. The patent specification and claims do not distinguish components by name, but by functional differences between components.

[0039] Moreover, in this document, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0040] At present, the image processing method is to pre-acquire different state underlines, and to complete the underlining removal work by using part of the data. However, the underlining information will change due to the change of the acquisition mode and the parameters such as time, light intensity, and sensor performance. Therefore, the first problem to be solved is how to construct the underlining library, such as Figure 3 Figure 3 The configuration stage of the image processing method of the embodiment of the present application is shown, which comprises:

[0041] In step S10, 100 underlines in different states under different influence factors are acquired, and the mean values thereof are calculated respectively. The influence factors include time, exposure intensity, screen scratches, residual fingerprints, sensor performance, and the like. The acquired underlines are not limited to 100, and can be flexibly adjusted according to the requirements of the identification speed and accuracy and the like.

[0042] For example, when the exposure intensity is selected as the influence factor, the exposure intensity is divided into multiple interval segments or points, for example, the exposure intensity is divided into two segments, three segments, or four segments, and 100 underlining images mark1 to mark 100 are acquired respectively, and the underlining mark_n of the current state is calculated according to the formula.

[0043] In the embodiment, the exposure intensity is divided into three segments as an example. The underlining mark_l under low exposure intensity, the underlining mark_n under moderate exposure intensity, and the underlining mark_h under high exposure intensity are calculated respectively according to the above method.

[0044] In step S20, the underlines in different states under the same influence factor are adjusted to the same light intensity, and the similarity thereof is calculated. Step S20 comprises two steps:

[0045] ​First step: adjust two footprints of different states under the same influence factor to the same light intensity, and subtract the difference to obtain a difference image, and divide the difference image into m*n rectangular regions, preferably, the size of each rectangular region is k*k pixels. When the same influence factor includes more than two different states, a single loop is performed for two-by-two comparison of multiple different states.

[0046] The difference image mark-diff is equal to the difference between the first state footprint mark1 and the product of the second state footprint mark2 and the correlation coefficient coeff, that is

[0047] mark_diff = mark1-mark2*coeff

[0048] Wherein, the correlation coefficient coeff is equal to the quotient of the mean value of the selected region brightness of the first state footprint mark1 and the second state footprint mark2, preferably, the selected region is selected from the central position center of the image, that is

[0049]

[0050] Second step: calculate the mean and standard deviation of each rectangular region respectively, and obtain m rows and n columns of matrix as consistency verification matrix, so as to calculate the similarity of the first footprint mark1 and the second footprint mark2.

[0051] Step S30: according to the similarity obtained in step S20, the weight of each influence factor is determined. If the similarity of the same influence factor under different states is small, it means that the influence factor has little effect on the footprint, otherwise, the influence is large.

[0052] According to the initial weight of each influence factor obtained in step S30, the footprint update strategy, update model and footprint removal method can be further designed, and after being processed by a fixed filtering method, a classical recognition algorithm is used for recognition statistics ROC curve (Receiver Operator characteristic Curve, Receiver Operator characteristic Curve). Further, according to the ROC curve, an analysis model is established to analyze the feasibility of different update models in the following image processing methods, whether each parameter needs to be fine-tuned, so as to obtain the optimal model and parameter, and at the same time, a large amount of data set recognition test comparison can be carried out to verify the advantages and disadvantages of different models and parameters and the applicable scenarios.

[0053] The embodiment of the application adopts the method of calculating the footprints under three different exposure intensities at equal intervals to collect footprints, so as to construct a footprint library. In actual use, the method of calculating footprints under two or four different exposure intensities can also be used to collect footprints. In the actual footprint removal process, a segmented linear footprint removal method is used to reduce errors, as shown in Figure 4a .Figure 4a The method for removing the background texture of the image processing method of the embodiment of the present application is shown, comprising:

[0054] Step S40: Collect the target image image to be processed, and select the target background texture class from the background texture library according to the exposure intensity signal of the target image image. The target image image includes a fingerprint image containing background texture information, a palmprint image containing background texture information, and other types of images containing background texture information for biometric recognition.

[0055] In this embodiment, the background texture library includes three different exposure intensity first, second and third background texture classes at equal intervals. In actual use, the number of background texture classes can be flexibly adjusted according to the requirements of recognition accuracy and recognition speed.

[0056] After the target image image to be processed is collected, the exposure intensity signal of the target image image is calculated, so that the corresponding target background texture class is selected from the background texture library.

[0057] In a feasible embodiment, in order to further reduce the error, the background texture library can include more than three different exposure intensity background texture classes at equal intervals. When the number of background texture classes is large, the exposure intensity difference between adjacent two background texture classes is small, and the exposure intensity accuracy calculated according to the target image image is not high enough, which may select an inappropriate background texture class as the target background texture class, increase the error, and lead to a decrease in recognition accuracy. In order to avoid this situation, when the target image image to be processed is collected in step S40, the environmental parameters including exposure intensity, temperature and other parameters are also collected. The exposure intensity in the collected environmental parameters and the exposure intensity calculated according to the target image image are combined to improve the selection accuracy of the target background texture class, thereby improving the accuracy of the final fingerprint recognition.

[0058] Step S50: Obtain the background texture removed image based on the target background texture class and the target image image. First, calculate the exposure intensity range of the selected region in the target image image, for example, calculate the exposure intensity range of the central region of the target image image, subtract the product of the target background texture mark and the light intensity coefficient in the corresponding range, and obtain the background texture removed image mark_remove, that is,

[0059]

[0060] The target background texture class includes a plurality of pre-collected background texture images, for example, and the mean value of part or all of the background texture images is calculated to obtain the target background texture mark. The light intensity coefficient represents the ratio of the exposure intensity range of the selected area of ​​the target image to the exposure intensity range of the selected area of ​​the target texture mark.

[0061] Furthermore, the image processing method of this embodiment also includes a method for updating a texture library, such as... Figure 4b As shown.

[0062] Figure 4b The image processing method of the present invention, which includes a shading update method, is illustrated in the embodiment of the present invention.

[0063] Step S40: Acquire the target image to be processed, and select the target texture class from the texture library based on the exposure intensity signal of the target image. The target image includes fingerprint images containing texture information, palm print images containing texture information, and other types of images containing texture information used for biometric identification.

[0064] In this embodiment, the background pattern library includes three background pattern classes with three different exposure intensities at equal intervals. In actual use, the number of background pattern classes can be flexibly adjusted according to the requirements of recognition accuracy and recognition speed.

[0065] After acquiring the target image to be processed, the exposure intensity signal of the target image is calculated based on the target image image, and then the corresponding target texture class is selected from the texture library.

[0066] In one feasible embodiment, to further reduce errors, the pattern library may include multiple pattern classes with three or more different exposure intensities at equal intervals. When the number of pattern classes is large, the difference in exposure intensity between adjacent pattern classes is small, and the accuracy of the exposure intensity calculated based on the target image is not high enough. This may lead to the selection of an unsuitable pattern class as the target pattern class, increasing the error and causing a decrease in recognition accuracy. To avoid this situation, when acquiring the target image to be processed in step S40, environmental parameters, including exposure intensity and temperature, are also acquired. The exposure intensity in the acquired environmental parameters is combined with the exposure intensity calculated based on the target image to improve the selection accuracy of the target pattern class, thereby improving the final fingerprint recognition accuracy.

[0067] Step S60: Determine whether the target pattern class needs to be updated according to the image quality quality of the target image image and the exposure intensity signal. When the image quality quality is greater than a first preset value and the exposure intensity signal is within a first preset range, jump to step S71; if the image quality quality is less than the first preset value or the exposure intensity signal is not within the first preset range, jump to step S72.

[0068] wherein the image quality quality is quantified according to the signal-to-noise ratio, directionality, bad points and other parameters of the target image, for example, the image quality quality is quantified in the form of a percentage system, and if one or more parameters of the target image are lower than the normal level, a certain score is deducted. If the image quality quality is lower than the first preset value, the current image cannot meet the update requirement in at least one aspect. In addition, the exposure intensity signal calculated according to the target image should also be within the first preset range, if the exposure intensity signal is less than the lower limit of the first preset range, it indicates that the current target image is too dark, and if the exposure intensity signal is greater than the upper limit of the first preset range, it indicates that the current target image is too bright, which cannot meet the update requirement.

[0069] Exemplarily, the reference value threshold of the exposure intensity signal of the target image is set in the embodiment, and only when the ratio of the absolute value of the difference between the exposure intensity signal of the target image and the reference value to the reference value threshold is less than a second preset value (0.5), it is determined that the exposure intensity signal of the target image is within the first preset range, i.e.

[0070]

[0071] wherein the reference value threshold and the second preset value can be flexibly adjusted according to actual needs.

[0072] Step S71: Update the target pattern class, and perform weighted summation on each pattern in the target image image and the target pattern class respectively. The weight of the target image image is the update coefficient a, and the weight of each pattern mark1 to mark i in the target pattern class is (1-a), i.e. the updated pattern

[0073]

[0074] wherein, The reciprocal of the light intensity coefficient is selected, and the target image is adjusted to the same exposure intensity signal as the background. The update coefficient a is determined according to the image quality quality and the exposure intensity signal signal, i.e., a = f(quality, signal), and the mapping relationship is adjusted according to the change of the acquisition environment. The upper limit of the update coefficient a is set as a1, and the lower limit is set as a2. The image quality quality and the exposure intensity signal signal are normalized and subtracted, and then multiplied by the upper limit a1 of the update coefficient to obtain an intermediate coefficient a0. If the calculated intermediate coefficient a0 is less than or equal to the lower limit a2, the value of the update coefficient a is a2; if a2 < a0 < a1, the value of the update coefficient is the intermediate coefficient a0; and if the intermediate coefficient a0 is greater than or equal to the upper limit a1, the value of the update coefficient a is a1.

[0075] In a feasible embodiment, the upper limit a1 of the update coefficient a is 0.005, and the lower limit a2 is 0.001. The intermediate coefficient a0 is calculated as follows:

[0076]

[0077] If the intermediate coefficient a0 is less than or equal to 0.001, the update coefficient a = 0.001; if 0.001 < a0 < 0.005, the update coefficient a = a0; and if the intermediate coefficient a0 is greater than or equal to 0.005, the update coefficient a = 0.005.

[0078] In another form, the update coefficient a is calculated as follows:

[0079]

[0080] The smaller one of the intermediate coefficient a0 and 1 is selected and multiplied by The larger one is compared with a1, and the update coefficient a is obtained.

[0081] In another feasible embodiment, the intermediate coefficient a0 can also be calculated by the following formula:

[0082]

[0083] Step S72: The target background is not updated.

[0084] Optionally, each background class can also include a plurality of pre-acquired images including fingerprint information and background information. When the images included in the background class are large enough, the target background mark obtained by calculating the mean value will not include fingerprint information. Moreover, as the background library is continuously updated, the images in each background class will gradually be updated to background images that do not include fingerprint information.

[0085] It should be understood that the bottom update method of the embodiment of the present application can be performed each time the fingerprint recognition or the bottom removal is performed, and there is no strict sequence between the bottom removal method and the bottom update method of the image processing method of the embodiment of the present application. The bottom removal method can be performed first and then the bottom update method, or the bottom update method can be performed first and then the bottom removal method, or the two methods can be performed independently.

[0086] After the experimental analysis of various influencing factors, the image processing method of the embodiment of the present application collects the bottom by using the method of calculating the bottom of three different exposure intensities at equal intervals, and updates one or more bottom classes in the bottom library in real time each time the target image is collected to offset the influence of other influencing factors, so that a relatively clean fingerprint image can be obtained, as shown in Figures 5a to 5c . Figures 5a to 5c The fingerprint image obtained by the image processing method of the embodiment of the present application is shown, wherein, Figure 5a The fingerprint image obtained by the image processing method of the embodiment of the present application before the bottom library is established is shown, Figure 5b and Figure 5c The fingerprint images obtained by the image processing method of the embodiment of the present application after the bottom library is updated for a certain number of times are shown. As can be seen from the figures, the image processing method of the embodiment of the present application can reduce the residual bottom information, thereby effectively improving the accuracy of the final fingerprint recognition.

[0087] Optionally, in the image processing method of the embodiment of the present application, the bottom library includes a fixed number of bottom classes, and each bottom class includes a fixed number of bottom images. The number of bottom classes or the number of bottom images in each bottom class does not need to be dynamically adjusted, and it is easier to store and call.

[0088] Optionally, after the target image is collected, it is judged whether the image quality and the exposure intensity meet the preset conditions. Only when the image quality and the exposure intensity meet the requirements, one or more bottom classes are updated in a floating ratio, that is, an update coefficient is obtained according to the image quality and the exposure intensity, and one or more target bottom classes are updated in a ratio according to the update coefficient, so that the bottom library can better reflect the real state of the current bottom.

[0089] As Figure 6As shown, this embodiment of the invention also provides an image processing apparatus 10. The image processing apparatus 10 is coupled to a display panel 30, which further includes a photosensing array 31 for receiving light reflected from a finger area. The display panel 30 is, for example, selected from an OLED (Organic Light-Emitting Diode) display panel or an AMOLED (Active-matrix organic light-emitting diode) display panel. The photosensing array 31 can be a CMOS sensor array, a CCD sensor array, a photodiode array, or other photosensing arrays.

[0090] The image processing device 10 includes an acquisition unit 11, a control unit 12, and a storage unit 13. The acquisition unit 11 acquires a target image or texture information based on a photosensitive array 31. The storage unit 13 is configured to store a texture library including multiple texture classes. The texture library includes multiple target texture classes divided according to exposure intensity, and each target texture class includes multiple pre-acquired texture images. The control unit 12 is configured to select a target texture class from the texture library based on the exposure intensity of the target image acquired by the acquisition unit 11, calculate the average value of the selected texture images in the target texture class to obtain a target texture image, and subtract the target texture image from the target image to obtain a texture-free image. For example, the acquisition unit 11 includes an optical fingerprint module.

[0091] In one feasible embodiment, the acquisition unit 11 further includes a sensor or other unit for acquiring environmental parameters such as exposure intensity and temperature.

[0092] Furthermore, such as Figure 7 As shown, this embodiment of the invention also provides an electronic device 20. The electronic device 20 includes a processor 21, a storage medium, and an interface 24 connected via a bus 23. The storage medium includes a non-volatile storage medium 22 and internal memory 25, and the interface 24, for example, connects to... Figure 6 The display panel 30 is coupled to receive signals or data from the light sensing array 31.

[0093] The non-volatile storage medium 22 stores an operating system 221, a computer program 222, and a database 223, the database 223 being used to store a texture library. The processor 221 is capable of executing instructions in the computer program 222, enabling the electronic device 20 to execute all or part of the processes in the image processing method of this embodiment of the invention. The internal memory 25 provides a running environment for the operating system 221 and the computer program 222.

[0094] Exemplarily, the electronic device 20 can be selected from a mobile phone, a tablet computer and the like supporting an under-screen optical fingerprint identification technology. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage, a flash memory, a magnetic disk or an optical disk.

[0095] In a feasible embodiment, the electronic device 20 is selected from a server for example, and the interface 24 is selected from a network interface so as to communicate with an external terminal in a manner of being connected through a network.

[0096] The present application also provides a computer-readable storage medium, which stores a computer program executable by the processor 21 to complete the image processing method provided by the present application.

[0097] Optionally, the computer-readable storage medium can include an internal storage unit of the electronic device, and can also include an external storage device. The storage medium can be used to store the computer program and other programs and data required by the electronic device, and can also be used to temporarily store data that has been output or will be output.

[0098] In summary, the image processing method of the embodiment of the present application judges whether the image quality and the exposure intensity of the collected target image meet the preset conditions, and only when the image quality and the exposure intensity both meet the requirements, the floating proportional update is performed on one or more underlines, that is, the update coefficient is obtained according to the image quality and the exposure intensity, and one or more target underlines are updated in proportion according to the update coefficient, so that the underline library can better reflect the real state of the current underline.

[0099] Optionally, the image processing method of the embodiment of the present application adopts the method of calculating underlines at different exposure intensities at equal intervals to collect underlines, and through the real-time update of one or more underlines in the underline library at each time of collecting the target image to offset the influence of other factors, a relatively clean fingerprint image can be obtained. The image processing method of the embodiment of the present application can reduce the residual underline information, thereby effectively improving the accuracy of the final fingerprint identification.

[0100] Optionally, in the image processing method of the embodiments of the present application, one or more base patterns in the base pattern library are updated in real time during the process of collecting the target image, so as to offset the influence of other factors, and the base pattern library includes a fixed number of base pattern classes, and each base pattern class includes a fixed number of base pattern images, so that the number of base pattern classes or the number of base pattern images in each base pattern class does not need to be dynamically adjusted, and the base pattern library is easier to store and call.

[0101] It should be noted that those skilled in the art can understand that the words "during", "when" and "when" related to the operation of the circuit used in this paper are not strict terms of action that occurs immediately at the start of the starting action, but there can be some small but reasonable delay or delays between the reaction initiated by the starting action, such as various transmission delays, etc. The use of the word "about" or "essentially" in this paper means that the value of the element has a parameter close to the declared value or position. However, as is well known in the art, there is always a slight deviation so that the value or position is difficult to be strictly the declared value. It has been properly determined in the art that a deviation of at least ten percent (10%) (at least twenty percent (20%) for semiconductor doping concentration) is a reasonable deviation from the described accurate ideal target. When used in conjunction with signal states, the actual voltage value or logic state of the signal (for example, "1" or "0") depends on whether positive logic or negative logic is used.

[0102] In accordance with the embodiments of the present application as described above, these embodiments do not describe all the details and are not limited to the specific embodiments. Obviously, many modifications and changes can be made according to the above description. The description selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can well utilize the present application and make modifications and uses based on the present application. The scope of protection of the present application should be defined by the scope of the claims of the present application and their equivalents.

Claims

1. An image processing method, wherein, The method comprises the following steps: collecting a target image to be processed; selecting a target base pattern class corresponding to the target image from a base pattern library, wherein the base pattern library comprises a plurality of base pattern classes, and each base pattern class comprises a plurality of base pattern images; judging whether the image quality and exposure intensity of the target image meet preset conditions; if the image quality and exposure intensity of the target image meet the preset conditions, obtaining an update coefficient according to the image quality and exposure intensity, and updating each base pattern image in the target base pattern class in proportion according to the update coefficient, wherein the update coefficient according to the image quality and exposure intensity comprises: subtracting the image quality and exposure intensity after normalization processing, and then multiplying the intermediate coefficient by the upper limit of the update coefficient to obtain the intermediate coefficient, wherein the update coefficient comprises an upper limit and a lower limit; when the intermediate coefficient is less than or equal to the lower limit of the update coefficient, the value of the update coefficient is the lower limit of the update coefficient, when the value of the intermediate coefficient is between the upper and lower limits of the update coefficient, the value of the update coefficient is the intermediate coefficient, and when the value of the intermediate coefficient is greater than or equal to the upper limit of the update coefficient, the value of the update coefficient is the upper limit of the update coefficient.

2. The image processing method of claim 1, wherein, The method further comprises the following steps before the step of judging whether the image quality and exposure intensity of the target image meet the preset conditions: obtaining a target base pattern from the target base pattern class, and obtaining a base pattern removed image from the target image and the target base pattern.

3. The image processing method of claim 2, wherein, The method of obtaining the target base pattern from the target base pattern class comprises: calculating the mean value of the selected base pattern image in the target base pattern class to obtain the target base pattern.

4. The image processing method of claim 2, wherein, The method of obtaining the base pattern removed image from the target base pattern and the target image comprises: subtracting the target base pattern from the target image to obtain the base pattern removed image.

5. The image processing method of claim 1, wherein, The method further comprises the following steps before the step of collecting the target image to be processed: collecting the base pattern images, and classifying the base pattern images into different base pattern classes according to the exposure intensity of the base pattern images to obtain the base pattern library.

6. The image processing method of claim 5, wherein, The method of collecting the base pattern images comprises: collecting the base pattern images under a plurality of different light intensities at equal intervals, and classifying the base pattern images under the plurality of different light intensities into a plurality of different base pattern classes respectively to generate the base pattern library.

7. The image processing method of claim 6, wherein, The method of collecting the base pattern images comprises: collecting the base pattern images under three different light intensities at equal intervals, and classifying the base pattern images under the three different light intensities into three different base pattern classes respectively to generate the base pattern library.

8. The image processing method of claim 1, wherein, The method of judging whether the image quality and exposure intensity of the target image meet the preset conditions comprises: when the image quality is greater than a first preset value, and the exposure intensity is within a first preset range, it is judged that the image quality and exposure intensity of the target image meet the preset conditions.

9. The image processing method of claim 8, wherein, The image quality is determined according to any one or a combination of several of the signal-to-noise ratio, directionality and bad points of the target image.

10. The image processing method of claim 8, wherein, The method of normalizing the exposure intensity comprises: calculating the absolute value of the difference between the exposure intensity and a signal target value and the quotient of the signal target value; wherein the signal target value is selected from the first preset range.

11. The image processing method of claim 1, wherein, The target base class is proportionally updated according to the update coefficient, including: Adjusting the target image and the target base class to the same light intensity; Respectively, each base in the target image and the target base class is weighted and summed, the weight of the target image is an update coefficient a, and the weight of each base in the target base class is 1-a.

12. An image processing apparatus, comprising: Including: The acquisition unit is configured to acquire a target image and a base image; The storage unit is configured to store a base library including a plurality of base classes, each base class including a plurality of base images; The control unit is configured to select a target base class from the base library, determine whether the image quality and the exposure intensity of the target image meet a preset condition, if the image quality and the exposure intensity of the target image meet the preset condition, obtain an update coefficient according to the image quality and the exposure intensity, and proportionally update each base image in the target base class according to the update coefficient, Wherein, the control unit performs difference after normalizing the image quality and the exposure intensity, and then multiplies the upper limit of the update coefficient to obtain an intermediate coefficient, the update coefficient includes an upper limit and a lower limit, When the intermediate coefficient is less than or equal to the lower limit of the update coefficient, the value of the update coefficient is the lower limit of the update coefficient, when the value of the intermediate coefficient is between the upper and lower limits of the update coefficient, the value of the update coefficient is the intermediate coefficient, and when the value of the intermediate coefficient is greater than or equal to the upper limit of the update coefficient, the value of the update coefficient is the upper limit of the update coefficient.

13. The image processing apparatus according to claim 12, wherein The control unit is also configured to obtain a target base according to the target base class, and obtain a base-removed image according to the target image and the target base.

14. The image processing apparatus according to claim 12, wherein The acquisition unit is also configured to be able to acquire environmental parameters, the environmental parameters including any one or several of exposure intensity, temperature.

15. An electronic device, comprising: Including: Storage medium, storing executable program instructions; The processor can execute the program instructions to execute the image processing method of any one of claims 1 to 11.

16. A computer readable storage medium, wherein, The storage medium stores a computer program, which can be executed by the processor to complete the image processing method of any one of claims 1 to 11.

Images