Palm print identification method, device, equipment and medium

Abstract

The invention discloses a palmprint recognition method and device, equipment and a medium. The method comprises the following steps: acquiring a to-be-recognized hand region of a to-be-detected palm and at least one light compensation mode; acquiring ambient light intensity; determining natural light compensation intensity and infrared light compensation intensity according to the ambient light intensity and each light compensation mode; adjusting the intensity of a light supplementing lamp according to the natural light compensation intensity and the infrared light compensation intensity, performing light supplementing on the palm to be detected by adopting the adjusted intensity of the light supplementing lamp, and collecting a natural light image after light supplementing; and recognizing the palmprint according to the natural light image. According to the embodiment of the invention, the accuracy of palmprint recognition can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data detection technology, and in particular to a palmprint recognition method, device, equipment and medium. Background Art

[0002] With the rapid development of science and technology, the types of devices that use biometric information for identity recognition are gradually increasing.

[0003] Currently, users can be identified through devices with palm print recognition function.

[0004] However, the installation environment of palmprint recognition equipment is complex and diverse, and it is difficult for palmprint recognition equipment to ensure the accuracy of user identity recognition. Summary of the invention

[0005] The invention provides a palmprint recognition method, device, equipment and medium to improve the accuracy of palmprint recognition.

[0006] In a first aspect, an embodiment of the present invention provides a palmprint recognition method, the method comprising:

[0007] Acquire a hand area to be identified of a palm to be detected and at least one light compensation method;

[0008] Get the ambient light intensity;

[0009] Determine the natural light compensation intensity and infrared light compensation intensity according to the ambient light intensity and various light compensation methods;

[0010] Adjust the fill light intensity according to the natural light compensation intensity and the infrared light compensation intensity, use the adjusted fill light intensity to fill light the palm to be detected, and collect the natural light image after the fill light;

[0011] Palmprint recognition is performed based on natural light images.

[0012] In a second aspect, an embodiment of the present invention further provides a palmprint recognition device, the device comprising:

[0013] A data acquisition module, used to acquire a hand area to be identified of a palm to be detected, and at least one light compensation method;

[0014] An ambient light acquisition module is used to obtain the ambient light intensity;

[0015] An intensity determination module, used to determine the natural light compensation intensity and the infrared light compensation intensity according to the ambient light intensity and various light compensation modes;

[0016] An image acquisition module is used to adjust the fill light intensity according to the natural light compensation intensity and the infrared light compensation intensity, use the adjusted fill light intensity to fill light the palm to be detected, and collect the natural light image after the fill light;

[0017] The palmprint recognition module is used to recognize the palmprint based on the natural light image.

[0018] In a third aspect, an embodiment of the present invention further provides a palmprint recognition device, the palmprint recognition device comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by at least one processor so that the at least one processor can execute the palmprint recognition method of any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the palmprint recognition method of any embodiment of the present invention when executed.

[0023] The technical solution of the embodiment of the present invention obtains the hand area to be identified of the palm to be detected, and at least one light compensation method; obtains the ambient light intensity; determines the natural light compensation intensity and the infrared light compensation intensity according to the ambient light intensity and the various light compensation methods; adjusts the fill light intensity according to the natural light compensation intensity and the infrared light compensation intensity, uses the adjusted fill light intensity to fill light the palm to be detected, and collects the natural light image after the fill light; recognizes the palmprint according to the natural light image, and can automatically perform natural light compensation and infrared light compensation according to the ambient light intensity, and can execute different light compensation methods for different ambient light intensities, refines the palmprint recognition operation, and improves the accuracy of palmprint recognition.

[0024] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 is a flow chart of a palmprint recognition method provided according to Embodiment 1 of the present invention;

[0027] Figure 2 is a flow chart of a palmprint recognition method provided according to Embodiment 2 of the present invention;

[0028] Figure 3 It is a schematic diagram of the layout of a palmprint recognition module provided by an embodiment of the present invention;

[0029] Figure 4 is a structural diagram of a palmprint recognition device provided according to an embodiment of the present invention;

[0030] Figure 5 It is a schematic diagram of the structure of a palmprint recognition device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] In the technical solution of the embodiment of the present invention, the acquisition, storage and application of palmprint features etc. are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0034] Embodiment 1

[0035] Figure 1This is a flow chart of a palmprint recognition method provided in Embodiment 1 of the present invention. The embodiment of the present invention is applicable to palmprint recognition, and the method can be executed by a palmprint recognition device, which can be implemented in the form of hardware and / or software.

[0036] See also Figure 1 The palmprint recognition method shown includes:

[0037] S101, obtaining a hand area to be identified of a palm to be detected and at least one light compensation method.

[0038] The palm to be detected may be the palm of the user whose palm print is to be detected. The hand area to be identified may be the area to be detected. The light compensation method may be a method of compensating the light of the hand area to be identified so that the palm print of the hand area to be identified is clearly visible.

[0039] Specifically, the palmprint detection module can be configured on the palmprint detection device. The palmprint detection module can be used to perform palmprint detection on the hand area to be identified of the palm to be detected. The area where palmprint detection can be performed can be preset according to the distance between the palm to be detected and the palmprint detection device. When the palm to be detected is in the designated area where palmprint detection can be performed, the hand area to be identified of the palm to be detected is obtained, and palmprint detection is performed on the palm to be detected; when the palm to be detected is not in the designated area for palmprint detection, palmprint detection is not performed on the palm to be detected. At least one light compensation method for performing light compensation on the hand area to be identified of the palm to be detected is obtained, and the acquisition method includes but is not limited to: a sequential search algorithm, a binary search algorithm, or a neural network algorithm, etc., which is not limited in the embodiment of the present invention.

[0040] In one example, the hand region to be identified of the palm to be detected is the region where the palm to be detected is located 10 centimeters away from the palm print detection device. 10 light compensation methods are found through a sequential search algorithm.

[0041] S102: Obtain ambient light intensity.

[0042] The ambient light intensity may be the intensity of light in the hand area to be identified of the palm to be detected, and the unit of the light intensity is lumen.

[0043] Specifically, when the palmprint detection device is installed in different environments, the palmprint detection device will be affected by different light intensities when performing palmprint detection; when the palmprint detection device performs palmprint detection in different time periods, it will also be affected by different light intensities. The intensity of light in the hand area to be identified of the detected palm can be detected in real time by the ambient light sensor, so as to compensate for the intensity of light in the hand area to be identified of the detected palm in real time, so that the palmprint of the hand area to be identified of the detected palm can be clearly seen.

[0044] In one example, the ambient light intensity obtained by the ambient light sensor is 100 lumens.

[0045] S103: Determine the natural light compensation intensity and the infrared light compensation intensity according to the ambient light intensity and various light compensation modes.

[0046] The natural light compensation intensity may be the intensity of natural light used to compensate the hand region to be identified of the detected palm, and the infrared light compensation intensity may be the intensity of infrared light used to compensate the hand region to be identified of the detected palm.

[0047] Specifically, natural light, also known as "natural light", does not directly show polarization. It includes all possible vibration directions perpendicular to the propagation direction of the light wave, so it does not show polarization. Natural light emitted directly from an ordinary light source is an irregular collection of countless polarized lights, so when directly observed, it is not possible to find which direction the light intensity is biased towards. This kind of light with the same intensity of light waves vibrating in all directions is called natural light. Infrared light, also known as infrared rays, is an electromagnetic wave (light) with a wavelength longer than visible light, with a wavelength between 770 nanometers and 1 millimeter, and is on the outside of red light on the spectrum. Infrared light can be used to compensate for ambient light intensity because: infrared light has high penetrating power and can penetrate the surface of the skin to illuminate the blood vessels and lines under the palm. It can capture the details of the palm lines without interfering with the surface image of the palm, effectively reducing interference from the surrounding environment and improving the accuracy of palmprint recognition. The target ambient light intensity can be preset according to experimental data. When the ambient light intensity reaches the target ambient light intensity, the accuracy of palmprint recognition of the palm to be detected is the highest, and the recognized palmprint features are the most comprehensive. By calculating the difference in the intensity of natural light between the ambient light intensity and the target ambient light intensity, and calculating the difference in the intensity of infrared light between the ambient light intensity and the target ambient light intensity, the natural light compensation intensity and the infrared light compensation intensity are determined, and the ambient light intensity is compensated until the ambient light intensity is the same as the target ambient light intensity, thereby improving the accuracy of palmprint recognition.

[0048] In one example, the ambient light intensity is 100 lumens. According to the ambient light intensity and various light compensation modes, when the ambient light intensity is 100 lumens, the natural light compensation intensity is 500 lumens and the infrared light compensation intensity is 400 lumens.

[0049] S104, adjusting the fill light intensity according to the natural light compensation intensity and the infrared light compensation intensity, using the adjusted fill light intensity to fill light the palm to be detected, and collecting the natural light image after the fill light.

[0050] The fill light intensity may be the intensity of the light of the light used to fill light for the hand area to be identified of the detected palm. The natural light image may be an image collected under natural light after natural light compensation and infrared light compensation are performed on the hand area to be identified of the detected palm.

[0051] Specifically, after obtaining the natural light compensation intensity and the infrared light compensation intensity, the fill light intensity is adjusted according to the natural light compensation intensity and the infrared light compensation intensity. There may be at least one fill light corresponding to the infrared light and at least one fill light corresponding to the natural light. By adjusting the fill light, the ambient light intensity reaches the target ambient light intensity. The adjusted fill light intensity is used to fill light the palm to be detected, and the natural light image after the fill light is collected.

[0052] In an example, the natural light compensation intensity is 500 lumens, and the infrared light compensation intensity is 600 lumens. The intensity of a fill light corresponding to the natural light is adjusted to 500 lumens according to the natural light compensation intensity, and the intensity of a fill light corresponding to the infrared light is adjusted to 600 lumens according to the infrared light compensation intensity. The adjusted fill light intensity is used to fill light the palm to be detected, and the natural light image after fill light is collected.

[0053] S105: Recognize the palm print according to the natural light image.

[0054] Specifically, the natural light image can be recognized based on the natural light image after light filling, and the palm print recognition method corresponding to the recognition result is obtained based on the recognition result, so as to recognize the palm print corresponding to the palm to be detected.

[0055] In one example, based on the natural light image after fill-in, the gesture is recognized as a clenched fist, and the palm print cannot be seen, so the subsequent palm print recognition process is not entered.

[0056] The technical solution of the embodiment of the present invention obtains the hand area to be identified of the palm to be detected, and at least one light compensation method; obtains the ambient light intensity; determines the natural light compensation intensity and the infrared light compensation intensity according to the ambient light intensity and the various light compensation methods; adjusts the fill light intensity according to the natural light compensation intensity and the infrared light compensation intensity, uses the adjusted fill light intensity to fill light the palm to be detected, and collects the natural light image after the fill light; recognizes the palmprint according to the natural light image, and can automatically perform natural light compensation and infrared light compensation according to the ambient light intensity, and can execute different light compensation methods for different ambient light intensities, refines the palmprint recognition operation, and improves the accuracy of palmprint recognition.

[0057] Optionally, obtaining the hand area to be identified of the palm to be detected includes: obtaining the first detection range, the second detection range and the distance of the object to be detected between the palm to be detected and the shooting device corresponding to the shooting device; comparing the distance of the object to be detected with the first detection range and the second detection range respectively to obtain a distance comparison result; if the distance comparison result is that it is in the first detection range, performing a card matching detection through a card swiping detection module, and the card swiping detection module is integrated with the shooting device; if the distance comparison result is that it is in the second detection range, determining the area where the palm to be detected is located as the hand area to be identified.

[0058] Among them, the shooting device can be a device for shooting the palm to be detected. The first detection range can be the range of the distance between the palm to be detected and the shooting device. The second detection range can be the range of the distance between the palm to be detected and the shooting device. The first detection range includes endpoint A and endpoint B, and the second detection range includes endpoint C and endpoint D, endpoint A is smaller than endpoint B, endpoint C is smaller than endpoint D, and endpoint B is smaller than endpoint C. The distance of the object to be detected can be the distance between the palm to be detected and the shooting device. The distance comparison result can be the result of comparing the distance of the object to be detected with the first detection range and the second detection range respectively. The card swiping detection module can be a module for detecting an inductive card. Near Field Communication (NFC) is an emerging technology. Devices (such as mobile phones) using NFC technology can exchange data when they are close to each other. It is evolved from the integration of contactless radio frequency identification (RFID) and interconnection technology. By integrating the functions of inductive card reader, inductive card and point-to-point communication on a single chip, mobile terminals are used to realize applications such as mobile identity recognition. Card matching detection can be a way of matching inductive cards through NFC technology.

[0059] Specifically, the first detection range and the second detection range corresponding to the photographing device are obtained, and the acquisition method may be mouse selection or keyboard input, etc. The distance between the palm to be detected and the object to be detected can be obtained by the distance sensor. The distance of the object to be detected is compared with the first detection range and the second detection range respectively to obtain a distance comparison result. If the distance comparison result is in the first detection range, it means that the distance between the palm to be detected and the photographing device is very close, and it is difficult to fully capture the palm print. In this case, the card matching detection is performed through the card swiping detection module, and the card swiping detection module is integrated with the photographing device; if the distance comparison result is in the second detection range, it means that the distance between the palm to be detected and the photographing device is appropriate and is in the range where the palm print can be fully captured. In this case, the area where the palm to be detected is located is determined as the hand area to be identified. The layout of the photographing device can be as follows Figure 2As shown, when the palm to be detected is in the first detection range, inductive card detection is performed through the NFC induction coil, and when the palm to be detected is in the second detection range, the palm print of the palm to be detected is photographed through the infrared camera and the camera for palm print recognition.

[0060] In one example, the first detection range corresponding to the shooting device is obtained as [4 cm, 7 cm] and the second detection range is (7 cm, 15 cm]. The distance between the palm to be detected by the distance sensor and the object to be detected by the shooting device is 10 cm. The distance of the object to be detected is compared with the first detection range and the second detection range respectively, and the distance comparison result is obtained that it is in the second detection range, then the area where the palm to be detected is located is determined as the hand area to be identified.

[0061] By obtaining the first detection range, the second detection range and the distance of the object to be detected between the palm to be detected and the shooting device corresponding to the shooting device; comparing the distance of the object to be detected with the first detection range and the second detection range respectively, to obtain a distance comparison result; if the distance comparison result is in the first detection range, a card matching detection is performed through a card swiping detection module, and the card swiping detection module is integrated with the shooting device; if the distance comparison result is in the second detection range, the area where the palm to be detected is located is determined as the hand area to be identified, and different operations are performed for different distances of the object to be detected, thereby refining the palmprint recognition method and improving the palmprint recognition accuracy.

[0062] Embodiment 2

[0063] Figure 3 This is a flow chart of a palmprint recognition method provided in the second embodiment of the present invention. Based on the above embodiments, the palmprint recognition operation is optimized and improved in the embodiment of the present invention.

[0064] Furthermore, "determine the natural light compensation intensity and the infrared light compensation intensity according to the ambient light intensity and each light compensation method" is refined into "screening among the light compensation methods according to the ambient light intensity to obtain the light compensation method corresponding to the ambient light intensity; identifying the light compensation method corresponding to the ambient light intensity to obtain the natural light compensation formula and the infrared light compensation formula corresponding to the ambient light intensity; calculating the natural light compensation intensity and the infrared light compensation intensity according to the natural light compensation formula and the infrared light compensation formula" to improve the palmprint recognition operation.

[0065] It should be noted that for the parts not described in detail in the embodiments of the present invention, reference may be made to the descriptions of other embodiments.

[0066] See also Figure 3 The palmprint recognition method shown includes:

[0067] S301, obtaining a hand region to be identified of a palm to be detected and at least one light compensation method.

[0068] S302: Obtain ambient light intensity.

[0069] S303 , screening various light compensation methods according to the ambient light intensity to obtain a light compensation method corresponding to the ambient light intensity.

[0070] Specifically, different ambient light intensities correspond to different light compensation methods. There is a one-to-one correspondence between ambient light intensity and light compensation methods. The lower the ambient light intensity, the stronger the intensity of the light to be compensated corresponding to the ambient light intensity, and the higher the ambient light intensity, the lower the intensity of the light to be compensated corresponding to the ambient light intensity. Different ambient light intensities correspond to different intensity identifiers, and the light compensation methods are screened according to the intensity identifier to obtain the light compensation method corresponding to the intensity identifier of the ambient light intensity. The screening method can be a neural network or natural language processing, etc., which is not limited in the embodiments of the present invention.

[0071] In one example, the ambient light intensity 1 is 100 lumens, the intensity identifier of the ambient light intensity 1 is HJ100, the identifier corresponding to the light compensation mode 1 is FS100, and the identifier corresponding to the light compensation mode 2 is FS200. According to the intensity identifier HJ100 of the ambient light intensity, the light compensation mode 1 corresponding to the ambient light intensity HJ100 is screened.

[0072] S304: Identify the light compensation method corresponding to the ambient light intensity to obtain a natural light compensation formula and an infrared light compensation formula corresponding to the ambient light intensity.

[0073] The natural light compensation formula may be a method for calculating the natural light compensation intensity, and the infrared light compensation formula may be a method for calculating the infrared light compensation intensity.

[0074] Specifically, the content of the light compensation method corresponding to the ambient light intensity includes the natural light compensation formula and the infrared light compensation formula corresponding to the ambient light intensity. The content of the light compensation method can be identified to obtain the natural light compensation formula and the infrared light compensation formula corresponding to the ambient light intensity. The identification method includes but is not limited to: feedforward neural network, feedback neural network or graph neural network, etc., which is not limited in the embodiment of the present invention.

[0075] In an example, the light compensation method 1 corresponding to the ambient light intensity HJ100 is identified through a feedforward neural network, and the natural light compensation formula corresponding to the ambient light intensity HJ100 is: natural light compensation intensity = natural light intensity in target ambient light intensity - natural light intensity in ambient light intensity; the infrared light compensation formula is: infrared light compensation intensity = infrared light intensity in target ambient light intensity - infrared light intensity in ambient light intensity.

[0076] S305 , calculating the natural light compensation intensity and the infrared light compensation intensity according to the natural light compensation formula and the infrared light compensation formula.

[0077] Specifically, by identifying the natural light compensation formula and the infrared light compensation formula, at least one parameter item can be obtained, the calculation method of each parameter item is obtained, the parameter value corresponding to each parameter item is calculated, and the natural light compensation intensity and the infrared light compensation intensity are calculated according to the parameter values, the natural light compensation formula and the infrared light compensation formula.

[0078] In one example, the natural light compensation formula is: natural light compensation intensity = natural light intensity in target ambient light intensity - natural light intensity in ambient light intensity; the infrared light compensation formula is: infrared light compensation intensity = infrared light intensity in target ambient light intensity - infrared light intensity in ambient light intensity. By identifying the natural light compensation formula and the infrared light compensation formula, the parameter items natural light intensity in target ambient light intensity, natural light intensity in ambient light intensity, infrared light intensity in target ambient light intensity and infrared light intensity in ambient light intensity can be obtained, the calculation method of each parameter item can be obtained, the parameter value corresponding to each parameter item can be calculated, and according to the parameter values, the natural light compensation formula and the infrared light compensation formula, the natural light compensation intensity is calculated to be 500 lumens and the infrared light compensation intensity is 300 lumens.

[0079] S306, adjusting the fill light intensity according to the natural light compensation intensity and the infrared light compensation intensity, using the adjusted fill light intensity to fill light the palm to be detected, and collecting the natural light image after the fill light.

[0080] S307: Recognize the palm print according to the natural light image.

[0081] The embodiment of the present invention obtains a light compensation method corresponding to the ambient light intensity by screening various light compensation methods according to the ambient light intensity; identifies the light compensation method corresponding to the ambient light intensity to obtain a natural light compensation formula and an infrared light compensation formula corresponding to the ambient light intensity; calculates the natural light compensation intensity and the infrared light compensation intensity according to the natural light compensation formula and the infrared light compensation formula, executes different light compensation methods for different ambient light intensities, obtains the natural light compensation formula and the infrared light compensation formula according to the light compensation method corresponding to the ambient light, further refines the light compensation operation, improves the clarity of the palmprint, and improves the accuracy of palmprint recognition.

[0082] Optionally, the light compensation method includes: obtaining standard palm print features of the experimental palm, at least one ambient light intensity, at least one natural light compensation intensity and at least one infrared light compensation intensity; generating at least one light compensation group according to the arrangement and combination of each natural light compensation intensity and each infrared light compensation intensity; adjusting the fill light intensity according to each light compensation group for each ambient light intensity, using the adjusted fill light intensity to fill light the experimental palm, and collecting at least one group of experimental image groups after the fill light, each group of experimental image groups including at least one experimental image; for each ambient light intensity, performing Perform feature recognition to obtain the palmprint features of each experimental image; for each ambient light intensity, perform similarity comparison between the standard palmprint features of the experimental palm and the palmprint features of the experimental images in each experimental image group corresponding to the ambient light intensity to obtain the recognition accuracy rate corresponding to each experimental image group corresponding to the ambient light intensity; for each ambient light intensity, determine the natural light compensation formula and the infrared light compensation formula corresponding to the ambient light intensity according to the light compensation group corresponding to the highest recognition rate corresponding to the ambient light intensity; for each ambient light intensity, determine the natural light compensation formula and the infrared light compensation formula corresponding to the ambient light intensity as the light compensation method corresponding to the ambient light intensity.

[0083] Among them, the standard palmprint feature can be the feature data of the palmprint of the experimental subject photographed under the illumination of the target ambient light intensity. The light compensation group can be a collection of data of a natural light compensation intensity and an infrared light compensation intensity. The experimental palm can be the palm of the experimental subject. The experimental image can be a palmprint image of the experimental palm after the fill light is adjusted according to the natural light compensation intensity and the infrared light compensation intensity in a light compensation group. The experimental image group can be a collection of experimental images corresponding to each light compensation group corresponding to an ambient light intensity. The palmprint feature of the experimental image can be the palmprint feature data included in the collected experimental image after compensation for the natural light compensation intensity and the infrared light compensation intensity recorded in the light compensation group. The recognition accuracy rate can be the ratio of the number of similar data in the palmprint features of the experimental image and the standard palmprint features to the number of features in the standard palmprint features. The highest recognition rate can be the recognition accuracy rate with the largest median value of each recognition accuracy rate.

[0084] Specifically, obtain the standard palm print features of the experimental palm, at least one ambient light intensity, at least one natural light compensation intensity and at least one infrared light compensation intensity. Generate at least one light compensation group according to the arrangement and combination of each natural light compensation intensity and each infrared light compensation intensity. For each ambient light intensity, adjust the fill light intensity according to each light compensation group, use the adjusted fill light intensity to fill light the experimental palm, and collect at least one group of experimental image groups after fill light, each experimental image group includes at least one experimental image. For each ambient light intensity, perform feature recognition on the experimental images in each experimental image group corresponding to the ambient light intensity to obtain the palm print features of each experimental image. For each ambient light intensity, perform similarity comparison between the standard palm print features of the experimental palm and the palm print features of the experimental images in each experimental image group corresponding to the ambient light intensity, obtain the similarity data amount of the palm print features of the experimental images in each experimental image group corresponding to the ambient light intensity, compare each similarity data amount with the data amount contained in the standard palm print features of the experimental palm, and obtain the recognition accuracy corresponding to each experimental image group corresponding to the ambient light intensity. For each ambient light intensity, according to the light compensation group corresponding to the highest recognition rate corresponding to the ambient light intensity, and according to the correspondence between the natural light compensation intensity and the infrared light compensation intensity in the light compensation group and the ambient light intensity, the natural light compensation formula and the infrared light compensation formula corresponding to the ambient light intensity are determined. For each ambient light intensity, the natural light compensation formula and the infrared light compensation formula corresponding to the ambient light intensity are determined as the light compensation method corresponding to the ambient light intensity.

[0085] By obtaining standard palm print features of the experimental palm, at least one ambient light intensity, at least one natural light compensation intensity and at least one infrared light compensation intensity; generating at least one light compensation group according to the arrangement and combination of each natural light compensation intensity and each infrared light compensation intensity; adjusting the fill light intensity according to each light compensation group for each ambient light intensity, using the adjusted fill light intensity to fill light the experimental palm, and collecting at least one group of experimental image groups after the fill light, each group of experimental image groups including at least one experimental image; for each ambient light intensity, performing feature recognition on the experimental images in each experimental image group corresponding to the ambient light intensity, and obtaining the palm print features of each experimental image; for each ambient light intensity , a similarity comparison is made between the standard palmprint features of the experimental palm and the palmprint features of the experimental images in each experimental image group corresponding to the ambient light intensity, and the recognition accuracy corresponding to each experimental image group corresponding to the ambient light intensity is obtained; for each ambient light intensity, the natural light compensation formula and the infrared light compensation formula corresponding to the ambient light intensity are determined according to the light compensation group corresponding to the highest recognition rate corresponding to the ambient light intensity; for each ambient light intensity, the natural light compensation formula and the infrared light compensation formula corresponding to the ambient light intensity are determined as the light compensation method corresponding to the ambient light intensity, and the light compensation method with the highest recognition accuracy corresponding to each ambient light intensity is obtained through experiments, thereby improving the accuracy of palmprint recognition.

[0086] Optionally, palm prints are recognized based on natural light images, including: recognizing the natural light images to obtain gesture recognition results of the hand area to be recognized; judging whether to take infrared images based on the gesture recognition results to obtain infrared images; and recognizing the infrared images to obtain palm print features.

[0087] The gesture recognition result may be a result of identifying the palm gesture type in the natural light image obtained by identifying the natural light image. The infrared light image may be an image taken at an infrared light frequency. The palm print feature may be feature data of the palm print of the palm to be detected that can be used for identity recognition.

[0088] Specifically, the natural light image is recognized to obtain the gesture recognition result of the hand area to be recognized. Different gesture recognition results correspond to different operation methods. According to the gesture recognition result, it can be determined whether infrared image shooting is required. If infrared image shooting is required, an infrared light image is obtained, and the infrared light image is recognized to obtain palm print features; if infrared image shooting is not required, infrared image shooting is not performed.

[0089] In one example, a natural light image is recognized, and a gesture recognition result of the hand area to be recognized is that the entire palm is exposed; based on the gesture recognition result, it is determined that an infrared image needs to be taken to obtain an infrared light image, and the infrared light image is recognized to obtain palm print features.

[0090] By recognizing the natural light image, the gesture recognition result of the hand area to be recognized is obtained; according to the gesture recognition result, it is determined whether to take an infrared image to obtain an infrared light image; the infrared light image is recognized to obtain the palm print features, and according to the gesture recognition result, it is possible to remove gestures that do not meet the palm print recognition type, reduce the amount of data to be processed, and improve the efficiency of palm print recognition.

[0091] Optionally, the natural light image is recognized to obtain a gesture recognition result of the hand area to be recognized, including: recognizing the natural light image to obtain a hand contour image; determining the gesture type according to the hand contour image; and determining the gesture type as the gesture recognition result of the hand area to be recognized.

[0092] The hand contour image may be an image of the contour of the palm to be detected. The gesture type may be the type of hand movement of the palm to be detected.

[0093] Specifically, the natural light image is recognized to obtain a hand contour image, and the gesture type is determined based on the hand contour image. Different gesture types correspond to different palm print recognition areas, and the gesture type is determined as the gesture recognition result of the hand area to be recognized.

[0094] In one example, the natural light image is recognized by an edge detection algorithm to obtain a hand contour image. According to the hand contour image, it is determined that the gesture type is fully exposed, and the gesture type is determined as the gesture recognition result of the hand area to be recognized, and the gesture recognition result is fully exposed.

[0095] By recognizing the natural light image, a hand contour image is obtained; the gesture type is determined based on the hand contour image; the gesture type is determined as the gesture recognition result of the hand area to be identified. According to the gesture type, redundant data can be removed, the amount of data to be processed can be reduced, and the efficiency of palmprint recognition can be improved.

[0096] Optionally, after identifying the infrared light image and obtaining the palmprint feature, it also includes: obtaining a preset flashing time; matching the palmprint feature with the existing palmprint features in the palmprint library to obtain a palmprint matching result; if the palmprint matching result is a successful match, the prompt light displays a first color, and the sound prompt device outputs a first matching voice; if the palmprint matching result is a failed match, the prompt light flashes according to the preset flashing time and displays a second color, the sound prompt device outputs a second matching voice, and stores the palmprint feature.

[0097] The preset flashing time may be a preset flashing time of the prompt light. The palmprint matching result may be a result of matching a palmprint feature with an existing palmprint feature in a palmprint library, used to indicate whether the palmprint feature exists in the palmprint library. The first color may be a preset color displayed by the prompt light. The first matching voice may be a preset voice output by a sound prompt device. The second color may be a preset color displayed by the prompt light. The second matching voice may be a preset voice output by a sound prompt device. The first color is different from the second color. The first matching voice is different from the second matching voice.

[0098] Specifically, a preset flashing time is obtained, and the palm print features are matched with the existing palm print features in the palm print library to obtain a palm print matching result. If the palm print matching result is a successful match, indicating that the palm print features of the palm to be detected exist in the palm print library, the prompt light is displayed in a first color, and the sound prompt device outputs a first matching voice to prompt the user that the match is successful; if the palm print matching result is a failed match, indicating that the palm print features of the palm to be detected do not exist in the palm print library, the prompt light is flashed according to the preset flashing time and displayed in a second color, and the sound prompt device outputs a second matching voice to prompt the user that the match fails, and the palm print features are stored.

[0099] In one example, the preset flashing time is 3 seconds. The palm print feature is matched with the existing palm print features in the palm print library. If the palm print matching result is successful, the prompt light is displayed in blue, and the sound prompt device outputs the first matching voice to indicate successful authentication.

[0100] By obtaining a preset flashing time; matching the palmprint features with the existing palmprint features in the palmprint library to obtain a palmprint matching result; if the palmprint matching result is a successful match, the prompt light will display a first color, and the sound prompt device will output a first matching voice; if the palmprint matching result is a failed match, the prompt light will flash according to the preset flashing time and display a second color, and the sound prompt device will output a second matching voice, and the palmprint features will be stored, so that the user's palmprint recognition can be promptly prompted whether it is a successful match. If the match fails, the palmprint features can also be saved, thereby improving the security of the palmprint recognition process.

[0101] Embodiment 3

[0102] Figure 4 This is a schematic diagram of the structure of a palmprint recognition device provided by Embodiment 3 of the present invention. The embodiment of the present invention is applicable to the palmprint recognition situation, the device can execute the palmprint recognition method, and the device can be implemented in the form of hardware and / or software.

[0103] See also Figure 4 The palmprint recognition device shown includes: a data acquisition module 401, an ambient light acquisition module 402, an intensity determination module 403, an image acquisition module 404 and a palmprint recognition module 405, wherein:

[0104] The data acquisition module 401 is used to acquire a hand area to be identified of a palm to be detected and at least one light compensation method;

[0105] An ambient light acquisition module 402 is used to acquire the ambient light intensity;

[0106] The intensity determination module 403 is used to determine the natural light compensation intensity and the infrared light compensation intensity according to the ambient light intensity and various light compensation modes;

[0107] The image acquisition module 404 is used to adjust the fill light intensity according to the natural light compensation intensity and the infrared light compensation intensity, use the adjusted fill light intensity to fill light the palm to be detected, and collect the natural light image after the fill light;

[0108] The palm print recognition module 405 is used to recognize the palm print according to the natural light image.

[0109] The technical solution of the embodiment of the present invention obtains the hand area to be identified of the palm to be detected, and at least one light compensation method; obtains the ambient light intensity; determines the natural light compensation intensity and the infrared light compensation intensity according to the ambient light intensity and the various light compensation methods; adjusts the fill light intensity according to the natural light compensation intensity and the infrared light compensation intensity, uses the adjusted fill light intensity to fill light the palm to be detected, and collects the natural light image after the fill light; recognizes the palmprint according to the natural light image, and can automatically perform natural light compensation and infrared light compensation according to the ambient light intensity, and can execute different light compensation methods for different ambient light intensities, refines the palmprint recognition operation, and improves the accuracy of palmprint recognition.

[0110] Optionally, the strength determination module 403 is specifically configured to:

[0111] Screening among various light compensation methods according to the ambient light intensity to obtain the light compensation method corresponding to the ambient light intensity;

[0112] Identify the light compensation method corresponding to the ambient light intensity to obtain the natural light compensation formula and infrared light compensation formula corresponding to the ambient light intensity;

[0113] The natural light compensation intensity and the infrared light compensation intensity are calculated according to the natural light compensation formula and the infrared light compensation formula.

[0114] Optional light compensation methods include:

[0115] Acquire standard palm print features of the experimental palm, at least one ambient light intensity, at least one natural light compensation intensity, and at least one infrared light compensation intensity;

[0116] Generate at least one light compensation group according to the arrangement and combination of each natural light compensation intensity and each infrared light compensation intensity;

[0117] For each ambient light intensity, the fill light intensity is adjusted according to each light compensation group, the test palm is filled with light using the adjusted fill light intensity, and at least one set of experimental image groups after the fill light is collected, each experimental image group including at least one experimental image;

[0118] For each ambient light intensity, feature recognition is performed on the experimental images in each experimental image group corresponding to the ambient light intensity to obtain the palm print features of each experimental image;

[0119] For each ambient light intensity, a similarity comparison is performed between the standard palm print features of the experimental palm and the palm print features of the experimental images in each experimental image group corresponding to the ambient light intensity, and the recognition accuracy corresponding to each experimental image group corresponding to the ambient light intensity is obtained;

[0120] For each ambient light intensity, determine the natural light compensation formula and infrared light compensation formula corresponding to the ambient light intensity according to the light compensation group corresponding to the highest recognition rate corresponding to the ambient light intensity;

[0121] For each ambient light intensity, a natural light compensation formula and an infrared light compensation formula corresponding to the ambient light intensity are determined as a light compensation method corresponding to the ambient light intensity.

[0122] Optionally, the data acquisition module 401 is specifically used for:

[0123] Obtaining a first detection range, a second detection range, and a distance between a palm to be detected and an object to be detected and the photographing device corresponding to the photographing device;

[0124] Compare the distance of the object to be detected with the first detection range and the second detection range respectively to obtain a distance comparison result;

[0125] If the distance comparison result is within the first detection range, a card matching detection is performed through a card swiping detection module, and the card swiping detection module is integrated with the camera device;

[0126] If the distance comparison result is that it is within the second detection range, the area where the palm to be detected is located is determined as the hand area to be identified.

[0127] Optionally, the palmprint recognition module 405 includes:

[0128] A result acquisition unit, used to recognize the natural light image and obtain a gesture recognition result of the hand area to be recognized;

[0129] An image capturing unit, used to determine whether to perform infrared image capturing according to the gesture recognition result, and obtain an infrared light image;

[0130] The feature extraction unit is used to identify the infrared light image and obtain the palm print features.

[0131] Optionally, the result acquisition unit is used to:

[0132] Recognize the natural light image to obtain the hand contour image;

[0133] Determine the gesture type based on the hand contour image;

[0134] The gesture type is determined as a gesture recognition result of the hand area to be recognized.

[0135] Optionally, the palmprint recognition module 405 is further used for:

[0136] After the infrared light image is recognized and the palm print features are obtained, a preset flashing time is obtained;

[0137] Match the palmprint features with the existing palmprint features in the palmprint database to obtain the palmprint matching result;

[0138] If the palm print matching result is a successful match, the prompt light will display the first color, and the sound prompt device will output the first matching voice;

[0139] If the palm print matching result is a match failure, the prompt light will flash according to the preset flashing time and display the second color, and the sound prompt device will output the second matching voice and store the palm print features.

[0140] The palmprint recognition device provided in the embodiment of the present invention can execute the palmprint recognition method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the palmprint recognition method.

[0141] Embodiment 4

[0142] Figure 5 A schematic diagram of the structure of a palmprint recognition device 500 that can be used to implement an embodiment of the present invention is shown.

[0143] like Figure 5 As shown, the palmprint recognition device 500 includes at least one processor 501, and a memory connected to the at least one processor 501, such as a read-only memory (ROM) 502, a random access memory (RAM) 503, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 501 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 502 or the computer program loaded from the storage unit 508 to the random access memory (RAM) 503. In RAM503, various programs and data required for the operation of the palmprint recognition device 500 can also be stored. The processor 501, ROM502 and RAM503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0144] Multiple components in the palmprint recognition device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the palmprint recognition device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0145] The processor 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 501 executes the various methods and processes described above, such as a palmprint recognition method.

[0146] In some embodiments, the palmprint recognition method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the palmprint recognition device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the processor 501, one or more steps of the palmprint recognition method described above may be performed. Alternatively, in other embodiments, the processor 501 may be configured to perform the palmprint recognition method in any other appropriate manner (e.g., by means of firmware).

[0147] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0148] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0149] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0150] To provide interaction with a user, the systems and techniques described herein may be implemented on a palmprint recognition device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the palmprint recognition device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0151] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0152] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS (Virtual Private Server) services.

[0153] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0154] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A palmprint recognition method, characterized in that: The method comprises: Acquire a hand area to be identified of a palm to be detected and at least one light compensation method; Get the ambient light intensity; Determining the natural light compensation intensity and the infrared light compensation intensity according to the ambient light intensity and each of the light compensation modes; Adjusting the fill light intensity according to the natural light compensation intensity and the infrared light compensation intensity, using the adjusted fill light intensity to fill light the palm to be detected, and collecting the natural light image after the fill light; The palm print is recognized according to the natural light image.

2. The method according to claim 1, characterized in that: The determining of the natural light compensation intensity and the infrared light compensation intensity according to the ambient light intensity and each of the light compensation modes includes: Screening the light compensation methods according to the ambient light intensity to obtain a light compensation method corresponding to the ambient light intensity; Identify the light compensation method corresponding to the ambient light intensity to obtain a natural light compensation formula and an infrared light compensation formula corresponding to the ambient light intensity; The natural light compensation intensity and the infrared light compensation intensity are calculated according to the natural light compensation formula and the infrared light compensation formula.

3. The method according to claim 2, characterized in that The light compensation method includes: Acquire standard palm print features of the experimental palm, at least one ambient light intensity, at least one natural light compensation intensity, and at least one infrared light compensation intensity; Generate at least one light compensation group according to the arrangement and combination of each of the natural light compensation intensities and each of the infrared light compensation intensities; For each of the ambient light intensities, the fill light intensity is adjusted according to each of the light compensation groups, the experimental palm is filled with light using the adjusted fill light intensity, and at least one group of experimental image groups after the fill light is collected, each group of experimental image groups including at least one experimental image; For each of the ambient light intensities, feature recognition is performed on the experimental images in each of the experimental image groups corresponding to the ambient light intensities to obtain palm print features of each of the experimental images; For each of the ambient light intensities, a similarity comparison is performed between the standard palmprint features of the experimental palm and the palmprint features of the experimental images in each of the experimental image groups corresponding to the ambient light intensity, to obtain the recognition accuracy corresponding to each of the experimental image groups corresponding to the ambient light intensity; For each of the ambient light intensities, determining a natural light compensation formula and an infrared light compensation formula corresponding to the ambient light intensity according to a light compensation group corresponding to the highest recognition rate corresponding to the ambient light intensity; For each of the ambient light intensities, a natural light compensation formula and an infrared light compensation formula corresponding to the ambient light intensity are determined as a light compensation method corresponding to the ambient light intensity.

4. The method according to claim 1, characterized in that: The step of obtaining a hand region to be identified of a palm to be detected includes: Acquire a first detection range, a second detection range, and a distance between a palm to be detected and an object to be detected corresponding to a photographing device; Comparing the distance of the object to be detected with the first detection range and the second detection range respectively to obtain a distance comparison result; If the distance comparison result is within the first detection range, a card matching detection is performed by a card swiping detection module, wherein the card swiping detection module is integrated with the photographing device; If the distance comparison result is that the hand is in the second detection range, the area where the palm to be detected is located is determined as the hand area to be identified.

5. The method according to claim 1, characterized in that The identifying of the palm print according to the natural light image comprises: Recognize the natural light image to obtain a gesture recognition result of the hand area to be recognized; Determining whether to perform infrared image shooting according to the gesture recognition result to obtain an infrared light image; The infrared light image is recognized to obtain palm print features.

6. The method according to claim 5, characterized in that The step of recognizing the natural light image to obtain a gesture recognition result of the hand area to be recognized includes: Recognize the natural light image to obtain a hand contour image; Determining a gesture type according to the hand contour image; The gesture type is determined as a gesture recognition result of the hand area to be recognized.

7. The method according to claim 5, characterized in that After the infrared light image is recognized to obtain the palm print feature, the method further includes: Get the preset flashing time; Matching the palmprint features with existing palmprint features in a palmprint database to obtain a palmprint matching result; If the palmprint matching result is a successful match, the prompt light displays a first color, and the sound prompt device outputs a first matching voice; If the palm print matching result is a match failure, the prompt light will flash according to a preset flashing time and display a second color, and the sound prompt device will output a second matching voice and store the palm print feature.

8. A palmprint recognition device, characterized in that: The device comprises: A data acquisition module, used to acquire a hand area to be identified of a palm to be detected, and at least one light compensation method; An ambient light acquisition module is used to obtain the ambient light intensity; An intensity determination module, used for determining the natural light compensation intensity and the infrared light compensation intensity according to the ambient light intensity and each of the light compensation modes; An image acquisition module, used to adjust the fill light intensity according to the natural light compensation intensity and the infrared light compensation intensity, use the adjusted fill light intensity to fill light the palm to be detected, and acquire the natural light image after the fill light; The palmprint recognition module is used to recognize the palmprint according to the natural light image.

9. A palmprint recognition device, characterized in that: The palmprint recognition device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the palmprint recognition method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the palmprint recognition method according to any one of claims 1 to 7 when executed.

Images