WO2020001400A1 - 纹路识别设备分辨率的测试方法及装置、***及存储介质 - Google Patents

纹路识别设备分辨率的测试方法及装置、***及存储介质 Download PDF

Info

Publication number
WO2020001400A1
WO2020001400A1 PCT/CN2019/092548 CN2019092548W WO2020001400A1 WO 2020001400 A1 WO2020001400 A1 WO 2020001400A1 CN 2019092548 W CN2019092548 W CN 2019092548W WO 2020001400 A1 WO2020001400 A1 WO 2020001400A1
Authority
WO
WIPO (PCT)
Prior art keywords
resolution
recognition device
test
image
standard test
Prior art date
Application number
PCT/CN2019/092548
Other languages
English (en)
French (fr)
Inventor
来航曼
Original Assignee
京东方科技集团股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 京东方科技集团股份有限公司 filed Critical 京东方科技集团股份有限公司
Publication of WO2020001400A1 publication Critical patent/WO2020001400A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1365—Matching; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching

Definitions

  • Embodiments of the present disclosure relate to a method for testing the resolution of a texture recognition device, a device for testing the resolution of a texture recognition device, a system for testing the resolution of a texture recognition device, and a storage medium.
  • biometric technology has become a hotspot of identity authentication technology due to its irrefutable security, convenience and ease of operation.
  • the biological characteristics of the human body include fingerprints, voiceprints, faces, irises, and palm prints.
  • fingerprint recognition technology has attracted much attention due to its uniqueness and stability, as well as high recognition efficiency, convenient collection, and low cost. It has become one of the most widely used recognition technologies in biometrics. One.
  • At least one embodiment of the present disclosure provides a method for testing the resolution of a texture recognition device, including: obtaining multiple test images of multiple standard test cards collected by the texture recognition device to be tested; and acquiring a first direction of the plurality of test images. Resolution and second direction resolution; obtaining the first direction resolution and the second direction resolution of the texture recognition device to be tested based on the first direction resolution and the second direction resolution of the plurality of test images, Wherein, the first direction intersects the second direction.
  • the plurality of standard test cards are independent of each other and constitute a test card group, or the plurality of standard test cards are located on the same test mother card, respectively. Among many different areas.
  • acquiring multiple test images of multiple standard test cards collected by the texture recognition device to be tested includes: moving multiple standards of the test mother card
  • the test card is such that a plurality of standard test cards in the plurality of different regions are respectively located in a recognition area of the texture recognition device to collect the plurality of test images.
  • the first-direction resolution and the second-direction resolution are horizontal resolution and vertical resolution, respectively, and are based on the multi-resolution
  • the first direction resolution and the second direction resolution of each test image to obtain the first direction resolution and the second direction resolution of the texture recognition device to be tested are expressed as:
  • Rx represents the first direction resolution of the texture recognition device to be tested
  • Ry represents the second direction resolution of the texture recognition device to be tested
  • Rx n represents the nth of the test card group or the test mother card.
  • Ry n represents the second direction resolution of the test image of the nth standard test card in the test card group or the test mother card
  • N is the test card group or The number of standard test cards included in the test mother card, 1 ⁇ n ⁇ N.
  • a first-direction resolution of a test image of an n-th standard test card in the test card group or the test mother card is expressed as:
  • Px n / L represents the number of pixels of the n-th standard test card in the first direction.
  • the second-direction resolution of the test image of the n-th standard test card in the test card group or the test mother card is expressed as:
  • Qy n / L represents the number of pixels of the n-th standard test card in the second direction.
  • the stripe spacing between the first standard test card and the second standard test card is equal, and the third standard test card and the The stripe pitch of the fourth standard test card is equal, and the stripe pitch of the first and second standard test cards is greater than the stripe pitch of the third and fourth standard test cards.
  • the method for testing the resolution of a texture recognition device further includes: performing an image preprocessing operation on the plurality of test images to obtain a plurality of processed images; and performing an image ratio on the plurality of processed images.
  • the pair operation is performed to output a texture recognition result.
  • the image preprocessing operation includes: performing an image segmentation operation, an image enhancement operation, an image binarization operation, or an image thinning operation on the image. Operate to obtain the processed image.
  • the image comparison operation includes: extracting feature values of the plurality of processed images; and a template in the feature value and texture library When the similarity of the feature values is greater than or equal to a preset threshold, the texture is matched; when the similarity of the feature value and the template feature value in the texture database is less than the preset threshold, the texture is not matched.
  • the texture recognition device is a fingerprint recognition device or a palm print recognition device.
  • At least one implementation of the present disclosure further provides a texture recognition device resolution test device, including: an image acquisition unit configured to acquire multiple test images of multiple standard test cards collected by the texture recognition device to be tested; an image resolution acquisition unit, Configured to acquire a first-direction resolution and a second-direction resolution of the plurality of test images; and a device resolution acquisition unit configured to be based on the first-direction resolution and the second-direction resolution of the plurality of test images, respectively A first direction resolution and a second direction resolution of the texture recognition device to be tested are obtained, and the first direction and the second direction intersect.
  • a texture recognition device resolution test device including: an image acquisition unit configured to acquire multiple test images of multiple standard test cards collected by the texture recognition device to be tested; an image resolution acquisition unit, Configured to acquire a first-direction resolution and a second-direction resolution of the plurality of test images; and a device resolution acquisition unit configured to be based on the first-direction resolution and the second-direction resolution of the plurality of test images, respectively A first direction resolution
  • At least one implementation of the present disclosure also provides a texture recognition device resolution test device, including: a processor; a memory; one or more computer program modules, the one or more computer program modules being stored in the memory and It is configured to be executed by the processor, and the one or more computer program modules include instructions for executing a test method for implementing a resolution of a texture recognition device provided by any embodiment of the present disclosure.
  • At least one implementation of the present disclosure also provides a texture recognition device resolution test system, including a texture recognition device resolution test device and a plurality of standard test cards provided by any of the embodiments of the present disclosure.
  • At least one implementation of the present disclosure also provides a storage medium for storing non-transitory computer-readable instructions, and when the non-transitory computer-readable instructions are executed by a computer, the texture recognition provided according to any embodiment of the present disclosure may be performed. Instructions for testing methods for device resolution.
  • FIG. 1 is a flowchart of an example of a method for testing resolution of a fingerprint recognition device according to some embodiments of the present disclosure
  • FIG. 2 is a schematic diagram of a standard test card provided by some embodiments of the present disclosure.
  • 3A is a flowchart of another example of a method for testing resolution of a fingerprint recognition device provided by some embodiments of the present disclosure
  • 3B is a schematic diagram of a fingerprint recognition system provided by some embodiments of the present disclosure.
  • FIG. 6 is a schematic block diagram of a device for testing resolution of a fingerprint recognition device provided by some embodiments of the present disclosure
  • FIG. 7 is a schematic block diagram of another device for testing resolution of a fingerprint recognition device provided by some embodiments of the present disclosure.
  • FIG. 8 is a schematic diagram of a fingerprint recognition device resolution test system provided by some embodiments of the present disclosure.
  • the image acquisition part of the texture recognition device is a front-end device for texture recognition.
  • the quality of the image obtained will directly affect the difficulty of the back-end software algorithm and the level of the texture recognition rate. Therefore, in some cases (such as a production plant or Quality inspection agencies, etc.) need to check whether the texture recognition device meets the requirements of a specific resolution.
  • the minimum resolution required by a fingerprint recognition system based on detail points is 500 dpi (dpi represents the number of pixels per inch), and the minimum resolution required by a fingerprint recognition system based on sweat holes The rate is 1000dpi.
  • this method requires a lot of manpower, material resources and time, and the test cost is high; on the other hand, due to the subjective factors such as pollution, damage or deformation of fingers or other objects to be tested, the texture recognition device may be unable A clear texture image is collected, so the device resolution of the texture recognition device cannot be objectively evaluated.
  • At least one embodiment of the present disclosure provides a method for testing the resolution of a texture recognition device, including: obtaining multiple test images of multiple standard test cards collected by the texture recognition device to be tested; and acquiring a first-direction resolution of the multiple test images. And second direction resolution; the first direction resolution and the second direction resolution of the texture recognition device to be tested are respectively obtained based on the first direction resolution and the second direction resolution of the plurality of test images, and the first direction and the second direction resolution Directions intersect.
  • At least one embodiment of the present disclosure further provides a texture recognition device resolution test device, a texture recognition device resolution test system, and a storage medium corresponding to the above-mentioned method for testing the texture recognition device resolution.
  • a method for testing the resolution of a texture recognition device provided by at least one embodiment of the present disclosure.
  • the method can avoid the impact of subjective factors such as contamination and breakage of the test finger or other test objects on the test result, and thus can recognize the texture
  • the device resolution of the device is objectively evaluated.
  • the test method has higher accuracy and reliability, and the required test cost is lower.
  • the texture recognition device may be used for fingerprint recognition, and accordingly, the texture recognition device may be a fingerprint identification device and thus used for fingerprint recognition. It should be noted that the texture recognition device may also be another texture recognition device such as a palm print recognition device for identifying other textures such as a palm print, which is not limited in the embodiments of the present disclosure.
  • the following describes a method, a test device, a test system, and a storage medium for measuring the resolution of a texture recognition device by taking the texture recognition device for fingerprint identification (that is, the texture recognition device is a fingerprint recognition device) as an example, and the embodiments of the present disclosure address this. No restrictions.
  • the other test methods, test devices, test systems, and storage media for the resolution of the texture recognition device are similar to the fingerprint identification device, and will not be described again.
  • FIG. 1 is a flowchart of an example of a method for testing resolution of a fingerprint recognition device provided by some embodiments of the present disclosure.
  • the fingerprint recognition device can collect a fingerprint image and perform feature matching on the fingerprint image.
  • the fingerprint recognition device can be a fingerprint sensor, a fingerprint recognition module, and a fingerprint recognition device.
  • the method for testing the resolution of a fingerprint recognition device can be implemented in software, loaded and executed by a processor in the fingerprint recognition device, or implemented in hardware, etc., to solve the problem generated during the test of the resolution of the fingerprint recognition device. High test cost and low accuracy.
  • the method for testing the resolution of the fingerprint recognition device includes steps S110 to S130.
  • the following description uses the first direction resolution as the horizontal resolution and the second direction resolution as the vertical resolution.
  • the device resolution of a fingerprint recognition device includes horizontal resolution and vertical resolution.
  • the first direction and the second direction are not limited to be perpendicular to each other, and may also have other appropriate angles, such as 45 °, 60 °, 75 °, and the like.
  • Step S110 Acquire multiple test images of multiple standard test cards collected by the fingerprint recognition device to be tested.
  • Step S120 Acquire the horizontal resolution and the vertical resolution of the plurality of test images.
  • Step S130 Obtain the horizontal and vertical resolutions of the fingerprint recognition device to be tested respectively based on the horizontal and vertical resolutions of the plurality of test images.
  • the standard test card is placed above the fingerprint identification device to be tested (that is, the texture recognition device to be tested), and a plurality of standard test cards of the test mother card are moved to make multiple Standard test cards (for example, the first standard test card 1, the second standard test card 2, the third standard test card 3, and the fourth standard test card 4 shown in FIG. 2) are respectively located in the recognition area of the fingerprint recognition device.
  • the test image is image information of a standard test card collected by a fingerprint recognition device.
  • the materials of the plurality of standard test cards may be silicone or plastic and other materials that can simulate and replace a finger or a palm to perform a resolution test of a texture recognition device.
  • the fingerprint recognition device may acquire a test image through optical recognition technology, semiconductor recognition technology (such as capacitive recognition technology), or ultrasonic recognition technology.
  • the multiple standard test cards are independent of each other and form a test card group, or the multiple standard test cards are respectively located in multiple different areas of the same test mother card (as shown in FIG. 2).
  • the test mother card includes a first standard test card 1, a second standard test card 2, a third standard test card 3, and a fourth standard test card 4, and a first area 1, a The second area 2, the third area 3, and the fourth area 4, the four standard test cards are respectively located in the four different areas.
  • the first standard test card 1 and the third standard test card 3 include stripes arranged side by side along the first arrangement direction
  • the second standard test card 2 and the fourth standard test card 4 include along the second
  • the stripes are arranged side by side in the arrangement direction.
  • the first arrangement direction and the second arrangement direction are vertically arranged.
  • the first arrangement direction is horizontal and the second arrangement direction is vertical, or vice versa.
  • the stripe is a black and white grid uniformly arranged on the surface of each standard test card.
  • the stripes included in the four standard test cards can also be arranged side by side in four different arrangement directions, such as the second standard test card 2, the third standard test card 3, and the fourth standard test card 4 and The angles at which the stripes intersect in the first standard test card 1 are 45 °, 90 °, and 135 °, respectively. It should be noted that the arrangement direction and angle of the plurality of standard test cards can also be any combination of other angles, as long as it meets the extension direction of the finger fingerprint, which is not limited in the embodiments of the present disclosure.
  • test card group or the test mother card may further include more or less standard test cards, for example, includes 8 standard test cards, and the stripe direction of the 8 standard test cards may also be along Eight different arrangement directions are arranged side by side, which is not limited in the embodiments of the present disclosure.
  • the stripe may be a vertical stripe or an S-shaped stripe, and a specific shape thereof may be set according to a shape of a finger fingerprint, which is not limited in the embodiment of the present disclosure.
  • the stripe pitch of the first standard test card 1 and the second standard test card 2 is equal, for example, the stripe pitch is referred to as a; the stripe of the third standard test card 3 and the fourth standard test card 4
  • the pitches are equal, and this stripe pitch is referred to as b, for example.
  • the stripe pitch of the first standard test card 1 and the second standard test card 2 is greater than the stripe pitch of the third standard test card 3 and the fourth standard test card 4, that is, a> b. It should be noted that it can also be set to b> a, and the specific setting method depends on the specific situation, which is not limited in the embodiments of the present disclosure.
  • the values of a and b are similar to the distance between the fingerprints of the fingers, for example, 0.04 centimeter (cm) ⁇ a ⁇ 0.15 cm, 0.04 cm ⁇ b ⁇ 0.15 cm. It should be noted that the values of a and b may depend on specific situations, and the embodiments of the present disclosure do not limit this.
  • each of the plurality of standard test cards may include 49, 74 stripes, and the like, and embodiments of the present disclosure are not limited thereto.
  • each standard test card can be set to a square whose length and width are L. It should be noted that it is not limited to this, and can also be set to other shapes such as a circle or an oval. For example, in the embodiments of the present disclosure, L is equal to 5 centimeters (cm). It should be noted that the values of the length and width of the standard test card may be determined according to specific circumstances, which are not limited in the embodiments of the present disclosure.
  • This standard test card simulates and replaces fingers or other test objects for testing, which can avoid the impact of subjective factors such as contamination, damage or deformation of fingers or other test objects on the test results, so that the device resolution of the texture recognition device can be tested Objective evaluation, at the same time, also reduces the test cost and improves the accuracy and reliability of the device resolution test method.
  • an image acquisition unit for acquiring multiple test images may be provided, and multiple test images of multiple standard test cards collected by the fingerprint recognition device to be tested may be acquired through the image acquisition unit; for example, a central processing unit (CPU ), An image processor (GPU), a tensor processor (TPU), a field programmable logic gate array (FPGA), or other forms of processing units with data processing capabilities and / or instruction execution capabilities to implement the image acquisition unit.
  • the processing unit may be a general-purpose processor or a special-purpose processor, and may be a processor based on the X86 or ARM architecture.
  • the plurality of test images may be obtained through step S110.
  • image processing methods such as Gaussian filtering, binarization, and corrosion expansion can be used to process the acquired test images accordingly to facilitate multiple test images. Collection.
  • the first direction resolution (that is, the horizontal resolution) of the test image of the n-th standard test card in the test card group or the test mother card is expressed as:
  • Px n / L represents the number of pixels of the n-th standard test card in the first direction (that is, the horizontal direction).
  • the second-direction resolution (that is, vertical resolution) of the test image of the n-th standard test card in the test card group or the test mother card is expressed as:
  • Qy n / L represents the number of pixels of the n-th standard test card in the second direction (that is, the vertical direction).
  • an image resolution acquisition unit for acquiring horizontal and vertical resolutions of multiple test images may be provided, and the horizontal resolution and vertical resolution of multiple test images may be acquired by the image resolution acquisition unit; for example, It can also be processed by central processing unit (CPU), image processor (GPU), tensor processor (TPU), field programmable logic gate array (FPGA), or other forms of processing with data processing capabilities and / or instruction execution capabilities Unit to implement the image resolution acquisition unit.
  • CPU central processing unit
  • GPU image processor
  • TPU tensor processor
  • FPGA field programmable logic gate array
  • step S130 for example, the horizontal and vertical resolutions of the fingerprint recognition device to be tested obtained based on the horizontal and vertical resolutions of the plurality of test images obtained in step S120 are expressed as:
  • Rx represents the horizontal resolution of the fingerprint recognition device to be tested
  • Ry represents the vertical resolution of the fingerprint recognition device to be tested
  • Rx n represents the horizontal resolution of the test image of the nth standard test card in the test card group or the test mother card
  • Ry n represents the vertical resolution of the test image of the nth standard test card in the test card group or test mother card
  • N is the number of standard test cards included in the test card group or test mother card, 1 ⁇ n ⁇ N. For example, in the example shown in FIG. 2, N is equal to 4.
  • a device resolution acquisition unit that acquires the horizontal and vertical resolutions of the fingerprint recognition device to be tested may be provided, and the horizontal resolution and vertical resolution of the fingerprint recognition device to be tested are acquired by the device resolution acquisition unit; for example, It can also be processed by central processing unit (CPU), image processor (GPU), tensor processor (TPU), field programmable logic gate array (FPGA), or other forms of processing with data processing capabilities and / or instruction execution capabilities Unit to implement the device resolution acquisition unit.
  • CPU central processing unit
  • GPU image processor
  • TPU tensor processor
  • FPGA field programmable logic gate array
  • the method can avoid the influence of subjective factors such as contamination and breakage of the test finger or other test objects on the test result, and thus can The device resolution of the texture recognition device is objectively evaluated.
  • the test method has higher accuracy and reliability, and the required test cost is lower.
  • FIG. 3A is a flowchart of another example of a method for testing resolution of a fingerprint recognition device provided by some embodiments of the present disclosure.
  • the method for testing the resolution of a fingerprint recognition device further includes steps S140 to S150.
  • the steps S140 to S150 are fingerprint recognition methods of the fingerprint recognition device, that is, tests obtained on the fingerprint recognition device.
  • An image eg, a fingerprint image
  • Steps S140 to S150 of the fingerprint recognition method and their respective exemplary implementations are described below.
  • Step S140 Perform image preprocessing operations on the multiple test images to obtain multiple processed images.
  • Step S150 Perform an image comparison operation on a plurality of processed images to output a fingerprint recognition result.
  • a fingerprint image (ie, a test image) may be collected by the fingerprint recognition device to be tested in steps S110 to S130, and fingerprint recognition may be performed on the fingerprint image in steps S140 to 150.
  • the fingerprint recognition device under test includes a fingerprint collection device.
  • the fingerprint collection device includes an optical sensor, an ultrasonic sensor, or a semiconductor sensor.
  • the fingerprint acquisition device may adopt a fingerprint image acquisition method in the art to acquire a fingerprint image, and details are not described herein again.
  • the fingerprint recognition device when a point light source or a line light source emits light, when the light emitted from the point light source to the touch side is irradiated onto the touch side surface, due to the effect of total reflection of the touch side surface, The part where the incident angle is greater than or equal to the critical angle ⁇ of total reflection will cause a total reflection effect, resulting in that part of the light cannot be emitted from the touch-side surface, thereby generating a circular total reflection area. Accordingly, a portion of these lights having an incident angle smaller than the critical angle ⁇ of total reflection is emitted from the touch-side surface.
  • the texture image can be collected by the light reflected in the total reflection area.
  • the total reflection condition of the corresponding position is destroyed, and when the valley of the fingerprint touches the total reflection area, the corresponding position does not destroy the total reflection condition.
  • the light incident on the fingerprint acquisition device is different at different positions, forming a light and dark line image.
  • FIG. 3B is a schematic diagram of a fingerprint recognition system provided by some embodiments of the present disclosure.
  • the fingerprint recognition system includes a training unit 10 and an authentication unit 20.
  • the training unit 10 is implemented in a server, for example, and can be used to input fingerprints to form a fingerprint database, or to train fingerprint classification algorithms and matching programs (such as pattern recognition programs such as neural networks) based on existing fingerprint databases. , Upgrade, etc .;
  • the authentication unit 20 is installed in the fingerprint identification terminal, and is connected and communicated with a database or a server or the like through a wireless or wired network or the like.
  • the training unit 10 and the authentication unit 20 may both be located at the fingerprint recognition terminal, and the specific settings may depend on the actual situation, which is not limited in the embodiments of the present disclosure.
  • the training unit 10 is configured to obtain a fingerprint database containing a large number of fingerprint features, so that the fingerprint image collected by the fingerprint recognition device is compared with the fingerprint features in the fingerprint database in the authentication unit 20 to determine whether a fingerprint is Match to output the fingerprint recognition result.
  • the training unit 10 includes an image acquisition unit 11, an image pre-processing unit 12, a fingerprint image feature extraction unit 13, and a fingerprint library 14, and they can be implemented in hardware, software, firmware, and any combination thereof.
  • the image acquisition unit 11 may acquire a fingerprint image through a fingerprint acquisition device in the above-mentioned fingerprint identification device.
  • the image pre-processing unit 12 and the fingerprint image feature extraction unit 13 may be implemented by corresponding computer programs.
  • the fingerprint database 14 may be implemented using various appropriate types of data, for example, it may be a relational or non-relational database.
  • the image pre-processing unit 12 may implement the image pre-processing operation in step S140.
  • the acquired fingerprint image is an image with varying degrees of noise interference.
  • the fingerprint The ridgeline may be disconnected, bridged, or blurred, etc. This noisy fingerprint ridgeline structure seriously affects the recognition performance of the fingerprint recognition device.
  • This image pre-processing operation uses signal processing technology to remove various noise interferences in the image, turn it into a clear fingerprint image, and restore the ridge structure of the fingerprint in order to reliably extract the correct fingerprint features and facilitate subsequent processes. Fingerprint recognition.
  • FIG. 4 is a flowchart of an image preprocessing operation provided by some embodiments of the present disclosure. That is, FIG. 4 is a flowchart of an example of step S140 shown in FIG. 3A. As shown in FIG. 4, the image pre-processing operation includes steps S141 to S144.
  • Step S141 Perform image segmentation operations on a plurality of test images.
  • the image segmentation operation can segment the foreground area that contains fingerprints and the background area that does not contain fingerprints, so that the preprocessing process only processes the foreground area, which can not only greatly reduce the preprocessing time, but also reduce background false features. Interference to subsequent image processing, thereby improving the performance of the entire fingerprint recognition system.
  • This image segmentation operation can be implemented by, for example, an adaptive local threshold image segmentation method, a variance method for segmentation based on image grayscale characteristics, or a pattern method for segmentation using image orientation information.
  • Step S142 Perform an image enhancement operation.
  • image enhancement operations can be used to improve the fingerprint image characteristics to improve the fingerprint image's analyzeability.
  • the image enhancement operation may be implemented by methods such as median filtering, sharpening filtering, or contrast enhancement, and the specific implementation manner thereof may adopt a conventional method in the art, and details are not described herein again. This image enhancement operation can enhance the edges and lines of the fingerprint image, making the image clearer and easier to process.
  • Step S143 Perform image binarization.
  • the image binarization operation can convert the grayscale image of the collected fingerprint image into a binarized image including only 0 and 1, thereby further reducing the amount of data processing.
  • the specific operation method can be used in the field. The method is not repeated here.
  • Step S144 Perform image thinning operation.
  • the image thinning operation can strip the collected fingerprint image layer by layer and remove some unnecessary points (for example, false feature points, etc.) from the original fingerprint image, but still maintain the original shape until it is included. Processed image of the skeleton of a fingerprint image. For example, in order to further reduce the amount of information, only the ridges of the fingerprint can be refined to make the image features more obvious.
  • the image thinning operation may also use a conventional method in the art, and details are not described herein again.
  • the fingerprint image feature extraction unit 13 is configured to extract feature values of a fingerprint image (that is, a processed image) after the image thinning operation for fingerprint matching.
  • the feature value may include a directional feature of a feature point of a fingerprint image, a ridge feature, and the like.
  • the characteristic points of the fingerprint image include the abrupt positions of the ridges of the fingerprint, and may include, for example, endpoints, bifurcation points, ring points, isolated points, short lines, and the like.
  • the end points, bifurcation points, or composite features (trifurcations or intersections) of the ridge line can be selected as the feature points for fingerprint recognition.
  • a 3 ⁇ 3 template can be used to examine the value of each pixel and its 8 neighborhoods to determine whether the pixel can be a feature point, its type, and location.
  • the feature values of the extracted feature points are stored in a register of a controller (such as an FPGA) for implementing the fingerprint recognition method of the embodiment of the present disclosure and further stored to form a fingerprint library 14 (ie, a texture library).
  • a controller such as an FPGA
  • the controller can be read from the fingerprint library 14 to be called when performing feature matching.
  • the identification unit 20 includes an image acquisition unit 21, an image pre-processing unit 22, a fingerprint image feature extraction unit 23, a fingerprint classification and matching unit 24, and an output unit 25.
  • the work of the image acquisition unit 21, the image pre-processing unit 22, the fingerprint image feature extraction unit 23 included in the identification unit 20, and the image acquisition unit 11, the image pre-processing unit 12, and the fingerprint image feature extraction unit 13 included in the training unit 10 The principle is similar, and can be implemented in software, hardware, firmware, and any combination thereof, which is not repeated here.
  • the fingerprint classification and matching unit 24 may compare the collected fingerprint feature values with the template feature values stored in the fingerprint database to implement fingerprint verification / recognition.
  • the fingerprint classification is used as the primary stage of fingerprint matching.
  • the input fingerprint image can be assigned to each fingerprint sub-bank, so that the input fingerprint image can be matched only with the fingerprint image in the sub-bank, thereby reducing fingerprint matching.
  • the search time in the process reduces the computational complexity.
  • a classification method based on a neural network a classification method based on a singular point, or a classification method based on a ridge line geometry can be used to implement fingerprint classification.
  • the fingerprint classification and matching unit 24 may implement the image comparison operation in step S150.
  • FIG. 5 is a flowchart of an image comparison operation provided by some embodiments of the present disclosure. That is, FIG. 5 is a flowchart of an example of step S150 shown in FIG. 3A. As shown in FIG. 5, the image comparison operation includes steps S151 to S154, and fingerprint matching can be performed on the fingerprint image.
  • Step S151 Feature values of a plurality of processed images are extracted.
  • the feature value extraction may be implemented in the fingerprint image feature extraction unit 23/13, which is not repeated here.
  • Step S152 judging whether the number of matching between the feature value and the template feature value in the fingerprint database (that is, the texture database) is greater than or equal to a preset threshold; if yes, execute step S153 to output the result of fingerprint matching; if not, execute In step S154, the result of the fingerprint mismatch is output.
  • the feature value of the processed image may be obtained by the image feature extraction unit 23, and the template feature value in the fingerprint database may be obtained by the training unit 10 described above.
  • the fingerprint database may refer to a fingerprint sub-database corresponding to a currently processed image after fingerprint classification. For example, when the number of matching between the feature value and the template feature value in the fingerprint database is greater than or equal to a preset threshold, the fingerprint is matched; the number of matching between the feature value and the template feature value in the fingerprint database is less than the preset threshold , The fingerprints do not match.
  • the preset threshold value can be set to 12, etc. It should be noted that the size of the preset threshold value depends on specific situations, which is not limited in the embodiments of the present disclosure.
  • the feature value of any feature point in the template image in the fingerprint database if there is a corresponding feature point in the range of the corresponding radius R in the image to be identified, and the feature value of the feature point is the same as the template feature in the fingerprint database If the value similarity is greater than 85%, the feature value of the feature point is considered to be successfully matched, and the number of pairs of successfully matched feature points in the image to be identified is counted. If the number of successfully matched feature points is greater than or equal to a preset threshold, It is considered that the two fingerprints are successfully matched; otherwise, the fingerprints are unsuccessful.
  • the specific implementation method of the fingerprint matching may also adopt a method in the art, which is not described in detail here.
  • the preset threshold may be stored in a register of a controller (for example, an FPGA) for implementing the fingerprint recognition method of the embodiment of the present disclosure or a predetermined position in a fingerprint library.
  • the controller may use the register or fingerprint when needed. Read from library.
  • the output unit 25 may output a result of fingerprint recognition.
  • the data recognized by the system can be directly displayed through a display device (such as a liquid crystal display device LCD), or the user can be notified of the detection result through a voice output device (speaker).
  • the process of the method for testing the resolution of a fingerprint recognition device may include more or fewer operations, and these operations may be performed sequentially or in parallel.
  • the flow of the method for testing the resolution of the fingerprint identification device described above includes multiple operations occurring in a specific order, it should be clearly understood that the order of the multiple operations is not limited.
  • the method for testing the resolution of the fingerprint recognition device described above may be executed once or multiple times according to a predetermined condition. It should be noted that the following embodiments are the same and will not be described again.
  • the method for testing the resolution of a texture recognition device provided by the embodiments of the present disclosure.
  • the method can avoid the impact of test results due to the subjective factors such as breakage and pollution of the test finger or other test objects, and thus can affect the equipment of the texture recognition device Resolution is objectively evaluated; on the other hand, this test method can improve the accuracy and reliability of test results, and the required test cost is lower.
  • FIG. 6 is a schematic block diagram of a resolution testing apparatus for a fingerprint recognition device provided by some embodiments of the present disclosure.
  • the fingerprint recognition device resolution test apparatus 100 includes an image acquisition unit 110, an image resolution acquisition unit 120, and a device resolution acquisition unit 130.
  • the image acquisition unit 110 is configured to acquire a plurality of test images of a plurality of standard test cards collected by the fingerprint recognition device to be tested.
  • the image acquisition unit 110 may implement step S110.
  • the image acquisition unit 110 may be implemented by means of hardware, software, firmware, and any combination thereof, for example, by an FPGA device, a circuit, or a computer program.
  • the image resolution acquiring unit 120 is configured to acquire a horizontal resolution and a vertical resolution of a plurality of test images.
  • the image resolution obtaining unit 120 may implement step S120.
  • the image resolution obtaining unit 120 may be implemented in a manner of hardware, software, firmware, and any combination thereof, for example, an FPGA device, a circuit, or a computer program.
  • the device resolution obtaining unit 130 is configured to obtain the horizontal resolution and the vertical resolution of the fingerprint recognition device to be tested based on the horizontal resolution and the vertical resolution of a plurality of test images, respectively.
  • the device resolution obtaining unit 130 may implement step S130.
  • the device resolution obtaining unit 130 may be implemented by hardware, software, or firmware, such as an FPGA device, a circuit, or a computer program.
  • each unit / module may be included, and the connection relationship between the units / modules is not limited, and may be determined according to actual needs.
  • the specific structure of each unit / module is not limited, and may be composed of an analog device according to the principle of the unit / module, a digital chip, or other applicable methods.
  • FIG. 7 is a schematic block diagram of another device for testing resolution of a fingerprint recognition device provided by some embodiments of the present disclosure.
  • the fingerprint recognition device resolution test apparatus 200 includes a processor 210, a memory 220, and one or more computer program modules 221.
  • the processor 210 and the memory 220 are connected through a bus system 230.
  • one or more computer program modules 221 may be stored in the memory 220.
  • one or more computer program modules 221 may include instructions for executing a method for testing a resolution of a fingerprint recognition device provided by any embodiment of the present disclosure.
  • the instructions in one or more of the computer program modules 221 may be executed by the processor 210.
  • the bus system 230 may be a commonly used serial or parallel communication bus, and the embodiments of the present disclosure are not limited thereto.
  • the processor 210 may be a central processing unit (CPU) or other form of processing unit having data processing capabilities and / or instruction execution capabilities, may be a general-purpose processor or a special-purpose processor, and may control the resolution of a fingerprint recognition device Other components in the apparatus 200 are tested to perform desired functions.
  • the memory 220 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory.
  • the volatile memory may include, for example, a random access memory (RAM) and / or a cache memory.
  • the non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, and the like.
  • One or more computer program instructions may be stored on a computer-readable storage medium, and the processor 210 may run the program instructions to implement the functions (implemented by the processor 210) in the embodiments of the present disclosure and / or other desired functions, For example, fingerprint recognition device resolution test method.
  • the computer-readable storage medium may also store various applications and various data, such as a fingerprint database and various data used and / or generated by the applications.
  • the embodiments of the present disclosure do not provide all the constituent units of the fingerprint recognition device resolution test apparatus 200.
  • those skilled in the art may provide and set other unillustrated component units according to specific needs, which is not limited in the embodiments of the present disclosure.
  • FIG. 8 is a schematic diagram of a fingerprint recognition device resolution test system provided by some embodiments of the present disclosure.
  • the fingerprint recognition device resolution test system 1 includes a fingerprint recognition device resolution test device 300.
  • the fingerprint recognition device resolution test apparatus 300 may be the fingerprint recognition device resolution test apparatus 100 shown in FIG. 6 or the fingerprint recognition device resolution test apparatus 200 shown in FIG. 7.
  • the fingerprint identification device resolution test system 1 further includes a plurality of standard test cards 400 and a fingerprint identification device 500.
  • a standard test card 400 and the fingerprint recognition device 500 reference may be made to related descriptions in the method for testing the resolution of a fingerprint recognition device provided in the embodiments of the present disclosure, and details are not described herein again.
  • An embodiment of the present disclosure also provides a storage medium.
  • the storage medium is used for non-transitory storage of computer-readable instructions.
  • a test for resolution of a fingerprint recognition device provided by any embodiment of the present disclosure may be performed. method.
  • the storage medium may be any combination of one or more computer-readable storage media.
  • one computer-readable storage medium contains a computer-readable program code for obtaining an image resolution
  • another computer-readable storage medium contains Computer-readable program code to obtain device resolution.
  • the computer may execute the program code stored in the computer storage medium to perform, for example, a method for testing the resolution of a fingerprint recognition device provided by any embodiment of the present disclosure.
  • the storage medium may include a memory card of a smart phone, a storage part of a tablet computer, a hard disk of a personal computer, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM),
  • RAM random access memory
  • ROM read-only memory
  • EPROM erasable programmable read-only memory
  • CD-ROM compact disc read-only memory
  • flash memory or any combination of the foregoing storage media may also be other applicable storage media.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Multimedia (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Human Computer Interaction (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Collating Specific Patterns (AREA)
  • Image Input (AREA)

Abstract

一种纹路识别设备分辨率的测试方法、纹路识别设备分辨率测试装置、纹路识别设备分辨率测试***及非易失性存储介质。该纹路识别设备分辨率的测试方法，包括：获取待测试纹路识别设备采集的多个标准测试卡的多个测试图像；获取多个测试图像的第一方向分辨率和第二方向分辨率；基于多个测试图像的第一方向分辨率和第二方向分辨率分别获取待测试纹路识别设备的第一方向分辨率和第二方向分辨率，第一方向与第二方向相交。该纹路识别设备分辨率的测试方法可以避免因为测试手指或测试对象的破损、污染等主观因素对测试结果造成的影响，保证了测试结果的准确性和可靠性。

Description

纹路识别设备分辨率的测试方法及装置、***及存储介质
本申请要求于2018年6月28日递交的中国专利申请第201810689590.1号的优先权，在此全文引用上述中国专利申请公开的内容以作为本申请的一部分。
技术领域
本公开的实施例涉及一种纹路识别设备分辨率的测试方法、纹路识别设备分辨率测试装置、纹路识别设备分辨率测试***及存储介质。
背景技术
随着模式识别技术的发展，生物识别技术以其无可辩驳的安全性、便利性和易操作性等优势成为身份鉴别技术的热点。人体的生物特征包括指纹、声纹、人脸、虹膜以及掌纹等。相比其他生物特征识别技术，指纹识别技术由于具有唯一性和稳定性，以及具有识别效率高、采集方便、成本低廉等优点，备受人们重视，成为生物识别技术中应用最为广泛的识别技术之一。
发明内容
本公开至少一实施例提供一种纹路识别设备分辨率的测试方法，包括：获取待测试纹路识别设备采集的多个标准测试卡的多个测试图像；获取所述多个测试图像的第一方向分辨率和第二方向分辨率；基于所述多个测试图像的第一方向分辨率和第二方向分辨率分别获取所述待测试纹路识别设备的第一方向分辨率和第二方向分辨率，其中，所述第一方向与所述第二方向相交。
例如，在本公开一些实施例提供的纹路识别设备分辨率的测试方法中，所述多个标准测试卡彼此独立且构成测试卡组，或者所述多个标准测试卡分别位于同一测试母卡的多个不同区域之中。
例如，在本公开一些实施例提供的纹路识别设备分辨率的测试方法中，获取待测试纹路识别设备采集的多个标准测试卡的多个测试图像包括：移动所述测试母卡的多个标准测试卡，使得所述多个不同区域中的多个标准测试 卡分别位于所述纹路识别设备的识别区域内以采集所述多个测试图像。
例如，在本公开一些实施例提供的纹路识别设备分辨率的测试方法中，所述第一方向分辨率与所述第二方向分辨率分别为水平分辨率和垂直分辨率，并且基于所述多个测试图像的第一方向分辨率和第二方向分辨率分别获取所述待测试纹路识别设备的第一方向分辨率和第二方向分辨率表示为：
Figure PCTCN2019092548-appb-000001
Figure PCTCN2019092548-appb-000002
其中，Rx表示所述待测试纹路识别设备的第一方向分辨率，Ry表示所述待测试纹路识别设备的第二方向分辨率，Rx n表示所述测试卡组或测试母卡中第n个标准测试卡的测试图像的第一方向分辨率，Ry n表示所述测试卡组或测试母卡中第n个标准测试卡的测试图像的第二方向分辨率，N为所述测试卡组或测试母卡包括的标准测试卡的数量，1≤n≤N。
例如，在本公开一些实施例提供的纹路识别设备分辨率的测试方法中，所述测试卡组或测试母卡中第n个标准测试卡的测试图像的第一方向分辨率表示为：
Rx n＝2.54*Px n/L
其中，Px n/L表示所述第n个标准测试卡在所述第一方向上的像素个数。
例如，在本公开一些实施例提供的纹路识别设备分辨率的测试方法中，所述测试卡组或测试母卡中第n个标准测试卡的测试图像的第二方向分辨率表示为：
Ry n＝2.54*Qy n/L
其中，Qy n/L表示所述第n个标准测试卡在所述第二方向上的像素个数。
例如，在本公开一些实施例提供的纹路识别设备分辨率的测试方法中，在N＝4的情况下，所述测试卡包括第一标准测试卡、第二标准测试卡、第三标准测试卡和第四标准测试卡；所述第一标准测试卡和所述第三标准测试卡包括沿第一排布方向并列排布的条纹，所述第二标准测试卡和所述第四标准测试卡包括沿第二排布方向并列排布的条纹，所述第一排布方向和所述第二排布方向交叉。
例如，在本公开一些实施例提供的纹路识别设备分辨率的测试方法中，所述第一标准测试卡和所述第二标准测试卡的条纹间距相等，所述第三标准测试卡和所述第四标准测试卡的条纹间距相等，并且所述第一标准测试卡和所述第二标准测试卡的条纹间距大于所述第三标准测试卡和所述第四标准测试卡的条纹间距。
例如，本公开一些实施例提供的纹路识别设备分辨率的测试方法，还包括：对所述多个测试图像进行图像预处理操作以得到多个处理图像；对所述多个处理图像进行图像比对操作以输出纹路识别结果。
例如，在本公开一些实施例提供的纹路识别设备分辨率的测试方法中，所述图像预处理操作包括：对所述图像进行图像分割操作、图像增强操作、图像二值化操作或图像细化操作以得到所述处理图像。
例如，在本公开一些实施例提供的纹路识别设备分辨率的测试方法中，所述图像比对操作包括：提取所述多个处理图像的特征值；在所述特征值与纹路库中的模板特征值的相似度大于或等于预设阈值时，则纹路匹配；在所述特征值与所述纹路库中的模板特征值的相似度小于所述预设阈值时，则纹路不匹配。
例如，在本公开一些实施例提供的纹路识别设备分辨率的测试方法中，所述纹路识别设备为指纹识别设备或掌纹识别设备。
本公开至少一实施还提供一种纹路识别设备分辨率测试装置，包括：图像获取单元，配置为获取待测试纹路识别设备采集的多个标准测试卡的多个测试图像；图像分辨率获取单元，配置为获取所述多个测试图像的第一方向分辨率和第二方向分辨率；设备分辨率获取单元，配置为基于所述多个测试图像的第一方向分辨率和第二方向分辨率分别获取所述待测试纹路识别设备的第一方向分辨率和第二方向分辨率，所述第一方向和所述第二方向相交。
本公开至少一实施还提供一种纹路识别设备分辨率测试装置，包括：处理器；存储器；一个或多个计算机程序模块，所述一个或多个计算机程序模块被存储在所述存储器中并被配置为由所述处理器执行，所述一个或多个计算机程序模块包括用于执行实现本公开任一实施例提供的纹路识别设备分辨率的测试方法的指令。
本公开至少一实施还提供一种纹路识别设备分辨率测试***，包括本公 开任一实施例提供的纹路识别设备分辨率测试装置以及多个标准测试卡。
本公开至少一实施还提供一种存储介质，用于存储非暂时性计算机可读指令，当所述非暂时性计算机可读指令由计算机执行时可以执行根据本公开任一实施例提供的纹路识别设备分辨率的测试方法的指令。
附图说明
为了更清楚地说明本公开实施例的技术方案，下面将对实施例的附图作简单地介绍，显而易见地，下面描述中的附图仅仅涉及本公开的一些实施例，而非对本公开的限制。
图1为本公开一些实施例提供的一种指纹识别设备分辨率的测试方法一个示例的流程图；
图2为本公开一些实施例提供的一种标准测试卡的示意图；
图3A为本公开一些实施例提供的一种指纹识别设备分辨率的测试方法的另一个示例的流程图；
图3B为本公开一些实施例提供的一种指纹识别***的示意图；
图4为本公开一些实施例提供的一种图像预处理操作的流程图；
图5为本公开一些实施例提供的一种图像比对操作的流程图；
图6为本公开一些实施例提供的一种指纹识别设备分辨率测试装置的示意框图；
图7为本公开一些实施例提供的另一种指纹识别设备分辨率测试装置的示意框图；以及
图8为本公开一些实施例提供的一种指纹识别设备分辨率测试***的示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚，下面将结合本公开实施例的附图，对本公开实施例的技术方案进行清楚、完整地描述。显然，所描述的实施例是本公开的一部分实施例，而不是全部的实施例。基于所描述的本公开的实施例，本领域普通技术人员在无需创造性劳动的前提下所获得的所有其他实施例，都属于本公开保护的范围。
除非另外定义，本公开使用的技术术语或者科学术语应当为本公开所属领域内具有一般技能的人士所理解的通常意义。本公开中使用的“第一”、“第二”以及类似的词语并不表示任何顺序、数量或者重要性，而只是用来区分不同的组成部分。同样，“一个”、“一”或者“该”等类似词语也不表示数量限制，而是表示存在至少一个。“包括”或者“包含”等类似的词语意指出现该词前面的元件或者物件涵盖出现在该词后面列举的元件或者物件及其等同，而不排除其他元件或者物件。“连接”或者“相连”等类似的词语并非限定于物理的或者机械的连接，而是可以包括电性的连接，不管是直接的还是间接的。“上”、“下”、“左”、“右”等仅用于表示相对位置关系，当被描述对象的绝对位置改变后，则该相对位置关系也可能相应地改变。
纹路识别设备的图像采集部分是纹路识别的前端装置，其获取图像质量的好坏将直接影响到后端软件算法的难易程度和纹路识别率的高低，因此在有些场合中(例如生产工厂或质量检验机构等)需要检验纹路识别设备是否满足特定分辨率的要求。例如，对于纹路识别设备中的指纹识别设备，基于细节点的指纹识别***所要求的最小分辨率为500dpi(dpi表示每英寸的像素点数)，而基于汗孔的指纹识别***所要求的最小分辨率为1000dpi。在对纹路识别设备的设备分辨率进行测试时，通常是通过直接从手指采集图像以获得带有纹路纹理信息的数字化灰度图像。一方面，该方法需要消耗大量的人力、物力和时间，且测试成本较高；另一方面，由于手指或其他待测试对象可能存在污染、破损或变形等主观因素，可能使得该纹路识别设备无法采集到清晰的纹路图像，从而不能客观地评价该纹路识别设备的设备分辨率。
本公开至少一实施例提供一种纹路识别设备分辨率的测试方法，包括：获取待测试纹路识别设备采集的多个标准测试卡的多个测试图像；获取多个测试图像的第一方向分辨率和第二方向分辨率；基于多个测试图像的第一方向分辨率和第二方向分辨率分别获取待测试纹路识别设备的第一方向分辨率和第二方向分辨率，第一方向与第二方向相交。
本公开至少一实施例还提供了一种对应于上述纹路识别设备分辨率的测试方法的纹路识别设备分辨率测试装置、纹路识别设备分辨率测试***以及存储介质。
本公开至少一实施例提供的纹路识别设备分辨率的测试方法，一方面， 该方法可以避免因为测试手指或其他测试对象的污染、破损等主观因素对测试结果造成的影响，从而可以对纹路识别设备的设备分辨率进行客观评价，另一方面，该测试方法具有较高的准确性和可靠性，并且需要的测试成本较低。
下面结合附图对本公开的实施例进行详细说明。应当注意的是，不同的附图中相同的附图标记将用于指代已描述的相同的元件。
本公开至少一实施例提供一种纹路识别设备分辨率的测试方法。例如，在一些示例中，该纹路识别设备可以用于指纹识别，相应地，该纹路识别设备可以是指纹设别设备，从而用于指纹识别。需要注意的是，该纹路识别设备还可以是掌纹识别设备等其他纹路识别设备，以用于掌纹等其他纹路的识别，本公开的实施例对此不作限制。下面以纹路识别设备用于指纹识别(即纹路识别设备为指纹识别设备)为例对纹路识别设备分辨率的测试方法、测试装置、测试***以及存储介质进行说明，且本公开的实施例对此不作限制。其他纹路识别设备分辨率的测试方法、测试装置、测试***以及存储介质等与该指纹设别设备类似，不再赘述。
图1为本公开一些实施例提供的一种指纹识别设备分辨率的测试方法一个示例的流程图。该指纹识别设备可以采集指纹图像以及对该指纹图像进行特征匹配等，例如可以是指纹传感器、指纹识别模组以及指纹识别整机等。例如，该指纹识别设备分辨率的测试方法可以以软件的方式实现，由指纹识别设备中的处理器加载并执行，或以硬件等方式实现，以解决指纹识别设备分辨率的测试过程中产生的测试成本高、准确性低等问题。
下面，参考图1对本公开实施例提供的指纹识别设备分辨率的测试方法进行说明。如图1所示，该指纹识别设备分辨率的测试方法包括步骤S110至步骤S130，下面以第一方向分辨率为水平分辨率而第二方向分辨率为垂直分辨率为例进行说明，由此指纹识别设备的设备分辨率包括水平分辨率和垂直分辨率。然而，第一方向和第二方向之间不限于彼此垂直，还可以具有其他适当的夹角，例如45°、60°、75°等。
步骤S110：获取待测试指纹识别设备采集的多个标准测试卡的多个测试图像。
步骤S120：获取多个测试图像的水平分辨率和垂直分辨率。
步骤S130：基于多个测试图像的水平分辨率和垂直分辨率分别获取待测试指纹识别设备的水平分辨率和垂直分辨率。
对于步骤S110，例如，将该标准测试卡放在待测试指纹识别设备(即待测纹路识别设备)的上方，通过移动该测试母卡的多个标准测试卡，使得多个不同区域中的多个标准测试卡(例如，如图2所示的第一标准测试卡1、第二标准测试卡2、第三标准测试卡3和第四标准测试卡4)分别位于指纹识别设备的识别区域内以采集多个测试图像。例如，该测试图像为指纹识别设备采集的标准测试卡的图像信息。例如，该多个标准测试卡的材料可以为硅胶或塑料以及其他可以模拟并代替手指或手掌等进行纹路识别设备分辨率测试的材料。例如，该指纹识别设备可以通过光学识别技术、半导体识别技术(例如电容式识别技术)或超声波识别技术等获取测试图像。
例如，该多个标准测试卡彼此独立且构成测试卡组，或者多个标准测试卡分别位于同一测试母卡(如图2所示)的多个不同区域之中。例如，在图2所示的示例中，该测试母卡包括第一标准测试卡1、第二标准测试卡2、第三标准测试卡3和第四标准测试卡4以及第一区域1、第二区域2、第三区域3和第四区域4，该4个标准测试卡分别位于该4个不同的区域中。
例如，在图2中，第一标准测试卡1和第三标准测试卡3包括沿第一排布方向并列排布的条纹，第二标准测试卡2和第四标准测试卡4包括沿第二排布方向并列排布的条纹，这里第一排布方向和第二排布方向垂直设置，例如图中第一排布方向为水平方向，第二排布方向为垂直方向，或者相反，本公开的实施例对此不作限制。例如，如图2所示，该条纹为在各个标准测试卡表面均匀设置的黑白栅格。
需要注意的是，该四个标准测试卡包括的条纹还可以沿四个不同的排布方向并列排布，例如第二标准测试卡2、第三标准测试卡3和第四标准测试卡4与第一标准测试卡1中的条纹交叉的角度分别为45°、90°和135°。需要注意的是，该多个标准测试卡交叉的排布方向和角度还可以是其他角度的任意组合，只要满足符合手指指纹的延伸方向即可，本公开的实施例对此不作限制。例如，在另一个示例中，该测试卡组或测试母卡还可以包括更多或更少的标准测试卡，例如，包括8个标准测试卡，该8个标准测试卡的条纹方向还可以沿八个不同的排布方向并列排布，本公开的实施例对此不作限制。
例如，该条纹可以是竖直条纹，也可以是S型条纹，其具体形状可以根据手指指纹的形状设置，本公开的实施例对此不作限制。
例如，如图2所示，第一标准测试卡1和第二标准测试卡2的条纹间距相等，例如将该条纹间距记作a；第三标准测试卡3和第四标准测试卡4的条纹间距相等，例如将该条纹间距记作b。例如，第一标准测试卡1和第二标准测试卡2的条纹间距大于第三标准测试卡3和第四标准测试卡4的条纹间距，即a>b。需要注意的是，还可以设置为b>a，具体设置方式视具体情况而定，本公开的实施例对此不作限制。例如a和b的取值与手指指纹的间距类似，例如，0.04厘米(cm)≤a≤0.15cm，0.04cm≤b≤0.15cm。需要注意的是，a和b的取值可以视具体情况而定，本公开的实施例对此不作限制。例如，多个标准测试卡的每个可包括49、74条条纹等，本公开的实施例不限于此。
例如，各个标准测试卡可以设置为长度和宽度都是L的正方形，需要注意的是，不限于此，还可以设置为圆形或椭圆形等其他形状。例如，在本公开实施例中，L等于5厘米(cm)。需要注意的是，标准测试卡的长度和宽度的取值可以视具体情况而定，本公开的实施例对此不作限制。
通过该标准测试卡模拟并代替手指或其他测试对象进行测试，可以避免因为手指或其他测试对象污染、破损或变形等主观因素对测试结果造成的影响，从而可以对纹路识别设备的设备分辨率进行客观评价，同时，还降低了测试成本，提高了设备分辨率测试方法的准确性和可靠性。
例如，可以提供用于获取多个测试图像图像获取单元，并通过该图像获取单元获取待测试指纹识别设备采集的多个标准测试卡的多个测试图像；例如，也可以通过中央处理单元(CPU)、图像处理器(GPU)、张量处理器(TPU)、现场可编程逻辑门阵列(FPGA)或者具有数据处理能力和/或指令执行能力的其它形式的处理单元来实现该图像获取单元。该处理单元可以为通用处理器或专用处理器，可以是基于X86或ARM架构的处理器等。
对于步骤S120，例如，该多个测试图像可以通过步骤S110获得。例如，在获取多个测试图像的水平分辨率和垂直分辨率之前，可以采用高斯滤波、二值化、腐蚀膨胀等图像处理方法对采集的测试图像进行相应的处理，以有利于多个测试图像的采集。
例如，测试卡组或测试母卡中第n个标准测试卡的测试图像的第一方向 分辨率(即水平分辨率)表示为：
Rx n＝2.54*Px n/L
其中，Px n/L表示第n个标准测试卡在第一方向(即水平方向)上的像素个数。
例如，测试卡组或测试母卡中第n个标准测试卡的测试图像的第二方向分辨率(即垂直分辨率)表示为：
Ry n＝2.54*Qy n/L
其中，Qy n/L表示第n个标准测试卡在第二方向(即垂直方向)上的像素个数。
例如，可以提供用于获取多个测试图像的水平分辨率和垂直分辨率的图像分辨率获取单元，并通过该图像分辨率获取单元获取多个测试图像的水平分辨率和垂直分辨率；例如，也可以通过中央处理单元(CPU)、图像处理器(GPU)、张量处理器(TPU)、现场可编程逻辑门阵列(FPGA)或者具有数据处理能力和/或指令执行能力的其它形式的处理单元来实现该图像分辨率获取单元。
对于步骤S130，例如，基于步骤S120中获取的多个测试图像的水平分辨率和垂直分辨率获取的待测试指纹识别设备的水平分辨率和垂直分辨率分别表示为：
Figure PCTCN2019092548-appb-000003
Figure PCTCN2019092548-appb-000004
其中，Rx表示待测试指纹识别设备的水平分辨率，Ry表示待测试指纹识别设备的垂直分辨率，Rx n表示测试卡组或测试母卡中第n个标准测试卡的测试图像的水平分辨率，Ry n表示测试卡组或测试母卡中第n个标准测试卡的测试图像的垂直分辨率，N为测试卡组或测试母卡包括的标准测试卡的数量，1≤n≤N。例如，在图2所示的示例中，N等于4。
例如，可以提供获取待测试指纹识别设备的水平分辨率和垂直分辨率的设备分辨率获取单元，并通过该设备分辨率获取单元获取待测试指纹识别设备的水平分辨率和垂直分辨率；例如，也可以通过中央处理单元(CPU)、图像处理器(GPU)、张量处理器(TPU)、现场可编程逻辑门阵列(FPGA)或 者具有数据处理能力和/或指令执行能力的其它形式的处理单元来实现该设备分辨率获取单元。
在本公开至少一实施例提供的纹路识别设备分辨率的测试方法中，一方面，该方法可以避免因为测试手指或其他测试对象的污染、破损等主观因素对测试结果造成的影响，从而可以对纹路识别设备的设备分辨率进行客观评价，另一方面，该测试方法具有较高的准确性和可靠性，并且需要的测试成本较低。
图3A为本公开一些实施例提供的指纹识别设备分辨率的测试方法的另一个示例的流程图。例如，如图3A所示，该指纹识别设备分辨率的测试方法还包括步骤S140至步骤S150，该步骤S140至步骤S150是该指纹识别设备的指纹识别方法，即对该指纹识别设备获得的测试图像(例如，指纹图像)进行指纹匹配的过程。下面对该指纹识别方法的步骤S140至步骤S150以及它们各自的示例性实现方式分别进行介绍。
步骤S140：对多个测试图像进行图像预处理操作以得到多个处理图像。
步骤S150：对多个处理图像进行图像比对操作以输出指纹识别结果。
例如，在上述方法中，可以通过步骤S110至步骤S130的待测指纹识别设备采集指纹图像(即测试图像)，并通过步骤S140至步骤150对该指纹图像进行指纹识别。例如，在一些示例中，待测指纹识别设备包括指纹采集器件。例如，该指纹采集器件包括光学传感器、超声波传感器或半导体传感器等。例如，该指纹采集器件可以采用本领域内的指纹图像采集方法采集指纹图像，在此不再赘述。
例如，在一些示例中，在该指纹识别设备中，在一个点光源或线光源发光时，其向触摸侧发射的光照射到触摸侧表面上时，由于该触摸侧表面的全反射的作用，这些光中入射角大于或等于全反射的临界角θ的部分会发生全反射作用，导致这部分光线不能从触摸侧表面出射，由此产生环形的全反射区域。相应地，这些光中入射角小于全反射的临界角θ的部分从触摸侧表面出射。可以通过全反射区域反射的光进行纹路图像采集。例如，当指纹的脊触摸到全反射区域时，相应位置的全反射条件被破坏，而指纹的谷触摸到全反射区域时，相应位置的没有破坏全反射条件。这样，全反射区域中的光线由于谷、脊的不同影响，使得入射到指纹采集器件上的光在不同位置不同， 形成明暗相间的纹路图像。
图3B为本公开一些实施例提供的一种指纹识别***的示意图。如图3B所示，该指纹识别***包括训练单元10和鉴别单元20。下面以纹路识别***为指纹识别***为例进行说明，但本公开的实施例对此不作限制。在一些示例中，训练单元10例如在服务器中实现，可用于录入指纹以形成指纹库，或者用于基于已有的指纹库对指纹分类算法与匹配程序(例如神经网络等模式识别程序)进行训练、升级等；鉴别单元20安装在指纹识别终端，并且例如通过无线或有线网络等方式与数据库或服务器等连接、通信。需要注意的是，训练单元10和鉴别单元20也可以均位于指纹识别终端，具体设置可视实际情况而定，本公开的实施例对此不作限制。如图3B所示，训练单元10配置为获取包含大量指纹特征的指纹库，从而在鉴别单元20中将指纹识别设备采集的指纹图像与该指纹库中的指纹特征作比对，以判断是否指纹匹配，从而输出指纹识别结果。
如图3B所示，该训练单元10包括图像采集单元11、图像预处理单元12、指纹图像特征提取单元13以及指纹库14，它们分别可以采用硬件、软件、固件及其任意组合的方式实现。
例如，该图像采集单元11可以通过上述指纹识别设备中的指纹采集器件获取指纹图像。图像预处理单元12和指纹图像特征提取单元13可以通过相应的计算机程序实现。指纹库14可以采用各种适当类型的数据实现，例如可以为关系型或非关系型数据库。
例如，该图像预处理单元12可以实现步骤S140中的图像预处理操作。例如，在指纹图像的采集过程，由于表面的皮肤特性、采集条件以及图像采集传感器的特征差异等各种原因的影响，采集的指纹图像是一幅含有不同程度噪声干扰的图像，例如，指纹的脊线可能被断开、桥接或模糊等，这种噪化的指纹脊线结构严重地影响了指纹识别设备的识别性能。
该图像预处理操作即利用信号处理技术去除图像中的各种噪声干扰，把它变成一幅清晰的指纹图像，恢复指纹的脊线结构，以便可靠地提取正确的指纹特征，便于后续过程中的指纹识别。
图4为本公开一些实施例提供的一种图像预处理操作的流程图。也就是说，图4为图3A中所示的步骤S140的示例的流程图。如图4所示，该图像 预处理操作包括步骤S141至步骤S144。
步骤S141：对多个测试图像进行图像分割操作。
例如，图像分割操作可以把含有指纹的前景区域和不含有指纹的背景区域分割出来，使预处理过程只对前景区域进行处理，这样不仅可以大大减少预处理的时间，而且还能减少背景伪特征对后续图像处理的干扰，从而提高整个指纹识别***的性能。该图像分割操作例如可以通过自适应的局部阈值图像分割方法、基于图像灰度特性进行分割的方差法或利用图像方向信息进行分割的方向图法等方法实现。
步骤S142：进行图像增强操作。
例如，通过扫描仪等图像采集传感器直接提取的指纹图像的图像质量可能还不能很好地达到图像分析的要求，因此可以采用图像增强操作提高指纹图像特征以提高该指纹图像的可分析性。例如，该图像增强操作可以通过中值滤波、锐化滤波或对比度增强等方法实现，其具体实现方式可以采用本领域内的常规方法，在此不再赘述。该图像增强操作可以增强指纹图像的边缘和线条，使图像变得更加清晰，便于处理。
步骤S143：进行图像二值化操作。
例如，该图像二值化操作可以将采集到的指纹图像的灰度图像转化为只包括0和1的二值化图像，从而进一步减少了数据的处理量，其具体操作方法可以采用本领域内的方法，在此不再赘述。
步骤S144：进行图像细化操作。
例如，图像细化操作可以将采集的指纹图像经过层层的剥离，从原来的指纹图像中去掉一些不必要的点(例如，伪特征点等)，但仍要保持原来的形状，直到得到包括指纹图像的骨架的处理图像。例如，为了进一步减少信息量，可以仅对指纹脊线进行细化操作，从而使得图像特征更加明显。例如，该图像细化操作也可以采用本领域内的常规方法，在此不再赘述。
例如，该指纹图像特征提取单元13配置为提取图像细化操作后的指纹图像(即处理图像)的特征值以用于指纹匹配。例如，该特征值可以包括指纹图像的特征点的方向特征、纹线特征等。例如，指纹图像的特征点包括指纹脊线的突变位置，例如可以包括端点、分叉点、环点、孤立点以及短纹等。例如，可以选用脊线的端点、分叉点或复合特征(三分叉或交叉点)等作为 指纹识别的特征点。例如，可以采用3×3模板考察每个像素及其8邻域的取值，来确定该像素可否为特征点及其类型、位置。
例如，将提取的特征点的特征值存储在用于实现本公开实施例的指纹识别方法的控制器(例如FPGA)的寄存器中并进一步存储以形成指纹库14(即纹路库)，需要使用时该控制器可以从指纹库14中读取，以在进行特征匹配时进行调用。
如图3B所示，该鉴别单元20包括图像采集单元21、图像预处理单元22、指纹图像特征提取单元23、指纹分类与匹配单元24以及输出单元25。例如，该鉴别单元20包括的图像采集单元21、图像预处理单元22、指纹图像特征提取单元23与训练单元10包括的图像采集单元11、图像预处理单元12、指纹图像特征提取单元13的工作原理类似，且分别可以采用软件、硬件、固件及其任意组合的方式实现，在此不再赘述。
指纹分类与匹配单元24可以将采集到的指纹特征值与指纹数据库中所存储模板特征值进行比对，实现指纹的验证/辨识。例如，该指纹分类作为指纹匹配的初级阶段，可以将输入的指纹图像分配到每一个指纹子库，这样输入的指纹图像可以仅与子库中的指纹图像进行匹配即可，从而减少了指纹匹配过程中的搜索时间，降低了计算的复杂性。例如，可以采用基于神经网络的分类方法、基于奇异点的分类方法或基于脊线几何形状的分类方法等实现指纹分类。
例如，该指纹分类与匹配单元24可以实现步骤S150中的图像比对操作。图5为本公开一些实施例提供的一种图像比对操作的流程图。也就是说，图5为图3A中所示的步骤S150的示例的流程图。如图5所示，该图像比对操作包括步骤S151至步骤S154，可以对指纹图像进行指纹匹配。
步骤S151：提取多个处理图像的特征值。
例如，特征值的提取可以在指纹图像特征提取单元23/13中实现，在此不再赘述。
步骤S152：判断特征值与指纹库(即纹路库)中的模板特征值的匹配个数是否大于或等于预设阈值；如果是，则执行步骤S153，输出指纹匹配的结果；如果否，则执行步骤S154，输出指纹不匹配的结果。
例如，该处理图像的特征值可以通过图像特征提取单元23获得，指纹库 中的模板特征值可以通过上述训练单元10获得。例如，该指纹库可以指经过指纹分类后与当前处理图像对应的指纹子库。例如，在特征值与指纹库中的模板特征值的匹配个数大于或等于预设阈值时，则指纹匹配；在特征值与所述指纹库中的模板特征值的匹配个数小于预设阈值时，则指纹不匹配。例如，该预设阈值可以设置为12等，需要注意的是，预设阈值的大小视具体情况而定，本公开的实施例对此不作限制。
例如，对于指纹库中模板图像的任一特征点的特征值，如果待识别图像中对应半径为R的范围内有对应的特征点存在，且该特征点的特征值与指纹库中的模板特征值相似度例如大于85％，则认为该特征点的特征值匹配成功，并统计待识别图像中匹配成功的特征点的对数，如果匹配成功的特征点的对数大于或等于预设阈值，则认为两指纹匹配成功；否则，则指纹匹配不成功。例如，该指纹匹配的具体实现方法也可以采用本领域内的方法，在此不再详细地介绍。
例如，该预设阈值可以存储在用于实现本公开实施例的指纹识别方法的控制器(例如FPGA)的寄存器中或存储在指纹库中预定位置，需要使用时该控制器可以从寄存器或指纹库中读取。
输出单元25可以输出指纹识别的结果。例如，作为独立的指纹识别***，经过***识别的数据可以通过显示装置(例如液晶显示装置LCD)直接显示出来，或通过语音输出装置(扬声器)告知用户检测结果。
需要说明的是，在本公开的各个实施例中，该指纹识别设备分辨率的测试方法的流程可以包括更多或更少的操作，这些操作可以顺序执行或并行执行。虽然上文描述的指纹识别设备分辨率的测试方法的流程包括特定顺序出现的多个操作，但是应该清楚地了解，多个操作的顺序并不受限制。上文描述的指纹识别设备分辨率的测试方法可以执行一次，也可以按照预定条件执行多次。需要注意的是，以下实施例与此相同，不再赘述。
本公开实施例提供的纹路识别设备分辨率的测试方法，一方面，该方法可以避免因为测试手指或其他测试对象的破损、污染等主观因素对测试结果造成影响，从而可以对纹路识别设备的设备分辨率进行客观评价；另一方面，该测试方法可以提高测试结果的准确性和可靠性，并且需要的测试成本较低。
图6为本公开一些实施例提供的一种指纹识别设备分辨率测试装置的示 意框图。该指纹识别设备分辨率测试装置100包括图像获取单元110、图像分辨率获取单元120和设备分辨率获取单元130。
该图像获取单元110配置为获取待测试指纹识别设备采集的多个标准测试卡的多个测试图像。例如，该图像获取单元110可以实现步骤S110，具体描述可以参考步骤S110的描述，在此不再赘述。例如，该图像获取单元110可以通过硬件、软件、固件及其任意组合的方式实现，例如通过FPGA器件、电路或计算机程序实现。
该图像分辨率获取单元120配置为获取多个测试图像的水平分辨率和垂直分辨率。例如，该图像分辨率获取单元120可以实现步骤S120，具体描述可以参考步骤S120的描述，在此不再赘述。例如，该图像分辨率获取单元120可以通过硬件、软件、固件及其任意组合的方式实现，例如通过FPGA器件、电路或计算机程序实现。
该设备分辨率获取单元130配置为基于多个测试图像的水平分辨率和垂直分辨率分别获取待测试指纹识别设备的水平分辨率和垂直分辨率。例如，该设备分辨率获取单元130可以实现步骤S130，具体描述可以参考步骤S130的描述，在此不再赘述。例如，该设备分辨率获取单元130可以通过硬件、软件、固件实现，例如通过FPGA器件、电路或计算机程序实现。
需要注意的是，在本公开的实施例中，可以包括更多或更少的单元/模块，并且各个单元/模块之间的连接关系不受限制，可以根据实际需求而定。各个单元/模块的具体构成方式不受限制，可以根据单元/模块原理由模拟器件构成，也可以由数字芯片构成，或者以其他适用的方式构成。
图7为本公开一些实施例提供的另一种指纹识别设备分辨率测试装置的示意框图。如图7所示，该指纹识别设备分辨率测试装置200包括处理器210、存储器220以及一个或多个计算机程序模块221。
例如，处理器210与存储器220通过总线***230连接。例如，一个或多个计算机程序模块221可以被存储在存储器220中。例如，一个或多个计算机程序模块221可以包括用于执行本公开任一实施例提供的指纹识别设备分辨率的测试方法的指令。例如，一个或多个计算机程序模块221中的指令可以由处理器210执行。例如，总线***230可以是常用的串行、并行通信总线等，本公开的实施例对此不作限制。
例如，该处理器210可以是中央处理单元(CPU)或者具有数据处理能力和/或指令执行能力的其它形式的处理单元，可以为通用处理器或专用处理器，并且可以控制指纹识别设备分辨率测试装置200中的其它组件以执行期望的功能。存储器220可以包括一个或多个计算机程序产品，该计算机程序产品可以包括各种形式的计算机可读存储介质，例如易失性存储器和/或非易失性存储器。该易失性存储器例如可以包括随机存取存储器(RAM)和/或高速缓冲存储器(cache)等。该非易失性存储器例如可以包括只读存储器(ROM)、硬盘、闪存等。在计算机可读存储介质上可以存储一个或多个计算机程序指令，处理器210可以运行该程序指令，以实现本公开实施例中(由处理器210实现)的功能以及/或者其它期望的功能，例如指纹识别设备分辨率测试方法等。在该计算机可读存储介质中还可以存储各种应用程序和各种数据，例如指纹库以及应用程序使用和/或产生的各种数据等。
需要说明的是，为表示清楚、简洁，本公开实施例并没有给出该指纹识别设备分辨率测试装置200的全部组成单元。为实现指纹识别设备分辨率测试装置200的必要功能，本领域技术人员可以根据具体需要提供、设置其他未示出的组成单元，本公开实施例对此不作限制。
关于不同实施例中的指纹识别设备分辨率测试装置100和指纹识别设备分辨率测试装置200的技术效果可以参考本公开的实施例中提供的指纹识别设备分辨率的测试方法的技术效果，这里不再赘述。
本公开至少一个实施例还提供一种指纹识别设备分辨率测试***，包括本公开任一实施例提供的指纹识别设备分辨率测试装置以及多个标准测试卡。图8为本公开一些实施例提供的一种指纹识别设备分辨率测试***的示意图。如图8所示，指纹识别设备分辨率测试***1包括指纹识别设备分辨率测试装置300。例如，该指纹识别设备分辨率测试装置300可以为图6中所示的指纹识别设备分辨率测试装置100或图7中所示的指纹识别设备分辨率测试装置200。
例如，指纹识别设备分辨率测试***1还包括多个标准测试卡400以及指纹识别设备500。例如，该标准测试卡400以及指纹识别设备500可以参考本公开的实施例中提供的指纹识别设备分辨率的测试方法中的相关描述，在此不再赘述。
需要说明的是，为表示清楚、简洁，并没有给出该指纹识别设备分辨率测试***1的全部组成单元。为实现指纹识别设备分辨率测试***1的必要功能，本领域技术人员可以根据具体需要提供、设置其他未示出的组成单元，本公开的实施例对此不作限制。
关于指纹识别设备分辨率测试***1的技术效果可以参考本公开的实施例提供的指纹识别设备分辨率的测试方法的技术效果，这里不再赘述。
本公开一实施例还提供一种存储介质。例如，该存储介质用于非暂时性存储计算机可读指令，当非暂时性计算机可读指令由计算机(包括处理器)执行时可以执行本公开任一实施例提供的指纹识别设备分辨率的测试方法。
例如，该存储介质可以是一个或多个计算机可读存储介质的任意组合，例如一个计算机可读存储介质包含用于获取图像分辨率的计算机可读的程序代码，另一个计算机可读存储介质包含获取设备分辨率的计算机可读的程序代码。例如，当该程序代码由计算机读取时，计算机可以执行该计算机存储介质中存储的程序代码，执行例如本公开任一实施例提供的指纹识别设备分辨率的测试方法。
例如，存储介质可以包括智能电话的存储卡、平板电脑的存储部件、个人计算机的硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM)、便携式紧致盘只读存储器(CD-ROM)、闪存、或者上述存储介质的任意组合，也可以为其他适用的存储介质。有以下几点需要说明：
(1)本公开实施例附图只涉及到与本公开实施例涉及到的结构，其他结构可参考通常设计。
(2)在不冲突的情况下，本公开的实施例及实施例中的特征可以相互组合以得到新的实施例。
以上所述仅是本发明的示范性实施方式，而非用于限制本发明的保护范围，本发明的保护范围由所附的权利要求确定。

Claims (16)

  1. 一种纹路识别设备分辨率的测试方法，包括：
    获取待测试纹路识别设备采集的多个标准测试卡的多个测试图像；
    获取所述多个测试图像的第一方向分辨率和第二方向分辨率；
    基于所述多个测试图像的第一方向分辨率和第二方向分辨率分别获取所述待测试纹路识别设备的第一方向分辨率和第二方向分辨率，其中，所述第一方向与所述第二方向相交。
  2. 根据权利要求1所述的纹路识别设备分辨率的测试方法，其中，所述多个标准测试卡彼此独立且构成测试卡组，或者所述多个标准测试卡分别位于同一测试母卡的多个不同区域之中。
  3. 根据权利要求2所述的纹路识别设备分辨率的测试方法，其中，获取待测试纹路识别设备采集的多个标准测试卡的多个测试图像包括：
    移动所述测试母卡的多个标准测试卡，使得所述多个不同区域中的多个标准测试卡分别位于所述纹路识别设备的识别区域内以采集所述多个测试图像。
  4. 根据权利要求2所述的纹路识别设备分辨率的测试方法，其中，所述第一方向分辨率与所述第二方向分辨率分别为水平分辨率和垂直分辨率，并且基于所述多个测试图像的第一方向分辨率和第二方向分辨率获取所述待测试纹路识别设备的第一方向分辨率和第二方向分辨率表示为：
    Figure PCTCN2019092548-appb-100001
    Figure PCTCN2019092548-appb-100002
    其中，Rx表示所述待测试纹路识别设备的第一方向分辨率，Ry表示所述待测试纹路识别设备的第二方向分辨率，Rx n表示所述测试卡组或测试母卡中第n个标准测试卡的测试图像的第一方向分辨率，Ry n表示所述测试卡组或测试母卡中第n个标准测试卡的测试图像的第二方向分辨率，N为所述测试卡组或测试母卡包括的标准测试卡的数量，1≤n≤N。
  5. 根据权利要求4所述的纹路识别设备分辨率的测试方法，其中，所述 测试卡组或测试母卡中第n个标准测试卡的测试图像的第一方向分辨率表示为：
    Rx n＝2.54*Px n/L
    其中，Px n/L表示所述第n个标准测试卡在所述第一方向上的像素个数。
  6. 根据权利要求4所述的纹路识别设备分辨率的测试方法，其中，所述测试卡组或测试母卡中第n个标准测试卡的测试图像的第二方向分辨率表示为：
    Ry n＝2.54*Qy n/L
    其中，Qy n/L表示所述第n个标准测试卡在所述第二方向上的像素个数。
  7. 根据权利要求4所述的纹路识别设备分辨率的测试方法，其中，在N＝4的情况下，所述测试卡包括第一标准测试卡、第二标准测试卡、第三标准测试卡和第四标准测试卡；
    所述第一标准测试卡和所述第三标准测试卡包括沿第一排布方向并列排布的条纹，所述第二标准测试卡和所述第四标准测试卡包括沿第二排布方向并列排布的条纹，所述第一排布方向和所述第二排布方向交叉。
  8. 根据权利要求7所述的纹路识别设备分辨率的测试方法，其中，所述第一标准测试卡和所述第二标准测试卡的条纹间距相等，所述第三标准测试卡和所述第四标准测试卡的条纹间距相等，并且
    所述第一标准测试卡和所述第二标准测试卡的条纹间距大于所述第三标准测试卡和所述第四标准测试卡的条纹间距。
  9. 根据权利要求1-7任一所述的纹路识别设备分辨率的测试方法，还包括：
    对所述多个测试图像进行图像预处理操作以得到多个处理图像；
    对所述多个处理图像进行图像比对操作以输出纹路识别结果。
  10. 根据权利要求9所述的纹路识别设备分辨率的测试方法，其中，所述图像预处理操作包括：
    对所述图像进行图像分割操作、图像增强操作、图像二值化操作或图像细化操作以得到所述处理图像。
  11. 根据权利要求9所述的纹路识别设备分辨率的测试方法，其中，所述图像比对操作包括：
    提取所述多个处理图像的特征值；
    在所述特征值与纹路库中的模板特征值的匹配个数大于或等于预设阈值时，则纹路匹配；
    在所述特征值与所述纹路库中的模板特征值的匹配个数小于所述预设阈值时，则纹路不匹配。
  12. 根据权利要求1-11任一所述的纹路识别设备分辨率的测试方法，其中，所述纹路识别设备为指纹识别设备或掌纹识别设备。
  13. 一种纹路识别设备分辨率测试装置，包括：
    图像获取单元，配置为获取待测试纹路识别设备采集的多个标准测试卡的多个测试图像；
    图像分辨率获取单元，配置为获取所述多个测试图像的第一方向分辨率和第二方向分辨率；
    设备分辨率获取单元，配置为基于所述多个测试图像的第一方向分辨率和第二方向分辨率分别获取所述待测试纹路识别设备的第一方向分辨率和第二方向分辨率，其中所述第一方向和所述第二方向相交。
  14. 一种纹路识别设备分辨率测试装置，包括：
    处理器；
    存储器；一个或多个计算机程序模块，所述一个或多个计算机程序模块被存储在所述存储器中并被配置为由所述处理器执行，所述一个或多个计算机程序模块包括用于执行实现权利要求1-12任一所述的纹路识别设备分辨率的测试方法的指令。
  15. 一种纹路识别设备分辨率测试***，包括权利要求13或14所述的纹路识别设备分辨率测试装置以及多个标准测试卡。
  16. 一种存储介质，非暂时性地存储计算机可读指令，当所述非暂时性计算机可读指令由计算机执行时可以执行根据权利要求1-12任一所述的纹路识别设备分辨率的测试方法的指令。
PCT/CN2019/092548 2018-06-28 2019-06-24 纹路识别设备分辨率的测试方法及装置、***及存储介质 WO2020001400A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810689590.1 2018-06-28
CN201810689590.1A CN110659536A (zh) 2018-06-28 2018-06-28 指纹识别设备分辨率的测试方法及装置、***及存储介质

Publications (1)

Publication Number Publication Date
WO2020001400A1 true WO2020001400A1 (zh) 2020-01-02

Family

ID=68985309

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/092548 WO2020001400A1 (zh) 2018-06-28 2019-06-24 纹路识别设备分辨率的测试方法及装置、***及存储介质

Country Status (2)

Country Link
CN (1) CN110659536A (zh)
WO (1) WO2020001400A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113642443A (zh) * 2021-08-06 2021-11-12 深圳市宏电技术股份有限公司 模型的测试方法、装置、电子设备及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107560541A (zh) * 2017-08-28 2018-01-09 中国电子技术标准化研究院 图像中心偏差的测量方法及装置
CN107578001A (zh) * 2017-08-28 2018-01-12 中国电子技术标准化研究院 测试指纹采集设备的分辨率的方法及装置
US20180173937A1 (en) * 2015-06-26 2018-06-21 Synaptics Incorporated Multi-resolution fingerprint sensor

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180173937A1 (en) * 2015-06-26 2018-06-21 Synaptics Incorporated Multi-resolution fingerprint sensor
CN107560541A (zh) * 2017-08-28 2018-01-09 中国电子技术标准化研究院 图像中心偏差的测量方法及装置
CN107578001A (zh) * 2017-08-28 2018-01-12 中国电子技术标准化研究院 测试指纹采集设备的分辨率的方法及装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113642443A (zh) * 2021-08-06 2021-11-12 深圳市宏电技术股份有限公司 模型的测试方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN110659536A (zh) 2020-01-07

Similar Documents

Publication Publication Date Title
CN110060237B (zh) 一种故障检测方法、装置、设备及***
US7970186B2 (en) System, method and computer program product for fingerprint verification
EP2833294B1 (en) Device to extract biometric feature vector, method to extract biometric feature vector and program to extract biometric feature vector
US10552661B2 (en) Systems and methods for biometric identification
WO2016149944A1 (zh) 用于识别人脸的方法、***和计算机程序产品
CN108009472B (zh) 一种基于卷积神经网络和贝叶斯分类器的指背关节纹识别方法
KR101244220B1 (ko) 지문인식장치 및 그 지문 인식방법
CN106778586A (zh) 离线手写签名鉴别方法及***
Peralta et al. Minutiae filtering to improve both efficacy and efficiency of fingerprint matching algorithms
Thalji et al. Iris Recognition using robust algorithm for eyelid, eyelash and shadow avoiding
US10679094B2 (en) Automatic ruler detection
CN110738222B (zh) 图像匹配方法、装置、计算机设备和存储介质
KR20160037305A (ko) 지문 인식을 이용한 사용자 인증 방법
WO2017161636A1 (zh) 一种基于指纹的终端支付方法及装置
CN113011426A (zh) 一种识别证件的方法和装置
EP3660731B1 (en) Digitization of industrial inspection sheets by inferring visual relations
Doroz et al. An accurate fingerprint reference point determination method based on curvature estimation of separated ridges
Homayon Iris recognition for personal identification using LAMSTAR neural network
WO2020001400A1 (zh) 纹路识别设备分辨率的测试方法及装置、***及存储介质
Szczepanik et al. Data management for fingerprint recognition algorithm based on characteristic points’ groups
CN111179226B (zh) 视野图的识别方法、装置及计算机存储介质
CN110619273B (zh) 一种高效的虹膜识别方法以及识别装置
Rasool Iris Feature Extraction and Recognition based on Gray Level Co-occurrence Matrix (GLCM) Technique
Alasadi et al. Dorsal hand-vein images recognition system based on grey level co-occurrence matrix and Tamura features
JP2019121187A (ja) 画像処理装置、画像処理方法および画像処理プログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19827143

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS (EPO FORM 1205A DATED 21.04.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19827143

Country of ref document: EP

Kind code of ref document: A1