CN107578001B - Method and device for testing resolution of fingerprint acquisition equipment - Google Patents
Method and device for testing resolution of fingerprint acquisition equipment Download PDFInfo
- Publication number
- CN107578001B CN107578001B CN201710748038.0A CN201710748038A CN107578001B CN 107578001 B CN107578001 B CN 107578001B CN 201710748038 A CN201710748038 A CN 201710748038A CN 107578001 B CN107578001 B CN 107578001B
- Authority
- CN
- China
- Prior art keywords
- quadrant
- image
- resolution
- testing
- stripe
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Landscapes
- Image Input (AREA)
Abstract
The embodiment of the invention provides a method and a device for testing the resolution of fingerprint acquisition equipment, wherein the method comprises the following steps: acquiring an image of an optical test card acquired by a fingerprint acquisition device to be tested, wherein stripes of the image are divided into four quadrants, the stripes of the I quadrant and the II quadrant are used for testing a first resolution, and the stripes of the III quadrant and the IV quadrant are used for testing a second resolution; respectively acquiring a preset number of first image characteristics in an I-th quadrant and an II-th quadrant in an image, inputting the acquired first image characteristics into a first classifier, and indicating whether the resolution of the to-be-tested fingerprint acquisition device meets the first resolution or not by the result output by the first classifier; and respectively acquiring a preset number of second image characteristics in the III-th quadrant and the IV-th quadrant in the image, inputting the acquired second image characteristics into a second classifier, and indicating whether the resolution of the fingerprint acquisition device to be tested meets the second resolution or not by the result output by the second classifier.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a device for testing the resolution of fingerprint acquisition equipment.
Background
The resolution of common optical fingerprint devices is 500DPI, 1000DPI and the like, and in reality, in some occasions (such as a production factory and a quality inspection institution) it is necessary to check whether the fingerprint acquisition device meets the requirement of a specific resolution, and currently, the judgment is generally performed in a manual observation mode, and whether the fingerprint acquisition device meets a specific resolution is determined by manually observing the imaging condition (shown in fig. 1,2 and 3) of a specific standard test card on the fingerprint acquisition device.
At present, the manual judgment is to observe the definition of black stripes and white stripes in each quadrant of an image, or cannot clearly see the horizontal or vertical stripes, and takes fig. 1 (in fig. 1, four areas, an upper right area (a square of the vertical stripes) is called a quadrant i area, an upper left area (a square of the horizontal stripes) is called a quadrant ii area, a lower left area (a square of the vertical stripes) is called a quadrant iii area, and a lower right area (a square of the horizontal stripes) is called a quadrant iv area) as an example:
if the stripes of the quadrant I and the quadrant II can be seen clearly (the former is 49 vertical black stripes, the latter is 49 horizontal black stripes, and the black stripe intervals are equal), the resolution of the fingerprint acquisition equipment is more than or equal to 1000 DPI;
if the stripes in quadrant III and quadrant IV can be seen clearly (the former is 19 vertical black stripes, the latter is 19 horizontal black stripes, and the black stripe intervals are equal), the resolution of the fingerprint acquisition device is more than or equal to 500 DPI.
In general, if the stripes of quadrant I and quadrant II are visible, the stripes of quadrant III and quadrant IV are also visible.
Taking fig. 2 as an example, observing fig. 2, the striping of quadrant i and quadrant ii is not obvious, but the striping of quadrant iii and quadrant iv is still possible, i.e. the resolution of the fingerprint acquisition device is greater than or equal to 500DPI, but not greater than or equal to 1000 DPI.
Taking fig. 3 as an example, when observing fig. 3, the stripes in the four quadrants are not distinct, which indicates that the resolution of the fingerprint acquisition device does not meet the 500DPI standard.
However, the method for determining the resolution of the fingerprint acquisition device by manually observing the imaging condition of a special standard test card on the fingerprint acquisition device is laborious, and the visual quantification has the defect of low accuracy.
Disclosure of Invention
The embodiment of the invention provides a method for testing the resolution of fingerprint acquisition equipment, which aims to solve the technical problems of labor waste and low accuracy in manual judgment in the prior art. The method comprises the following steps: acquiring an image of an optical test card acquired by a fingerprint acquisition device to be tested, wherein stripes of the image are divided into four quadrants, the stripes of the I quadrant and the II quadrant are used for testing a first resolution, and the stripes of the III quadrant and the IV quadrant are used for testing a second resolution; respectively acquiring a preset number of first image features in an I-quadrant and an II-quadrant in the image, inputting the acquired first image features into a first classifier, wherein the result output by the first classifier represents whether the resolution of the fingerprint acquisition device to be tested meets a first resolution, and the first classifier is obtained by image training of an optical test card conforming to the first resolution; and respectively acquiring a preset number of second image features in a third quadrant and a fourth quadrant in the image, inputting the acquired second image features into a second classifier, wherein the result output by the second classifier represents whether the resolution of the fingerprint acquisition device to be tested meets a second resolution, and the second classifier is obtained by image training of an optical test card conforming to the second resolution.
In one embodiment, the I-th quadrant is a vertical stripe, the first image feature acquired in the image within the I-th quadrant comprises a 102-dimensional image feature, the 102-dimensional image feature comprises a gray mean, a gray standard deviation, a global contrast, a sharpness of the I-th quadrant, and the first 98 values in order from large to small in an absolute gradient accumulated along the y-axis; the second quadrant is a horizontal stripe, and the first image feature acquired in the second quadrant in the image includes a 102-dimensional image feature including: the mean grayscale, the standard deviation grayscale, the global contrast in quadrant II, the sharpness, and the first 98 values in the absolute gradient accumulated along the x-axis in descending order.
In one embodiment, the global contrast of quadrant I is calculated by the following formula: c1＝W1C11+W2C12Wherein, C1Is the global contrast of quadrant I; w1Is 0.4578; w2Is 0.5422; c11Is the contrast of the quadrant I image;
m is the number of pixels of the quadrant I image that are included high; n is the number of pixels included in the width of the I-th quadrant image; lc(x, y) is the local contrast at coordinate (x, y);
in one embodiment, the sharpness of quadrant I is calculated by the following equation:
wherein S is1Is the sharpness of quadrant I; m is the number of pixels of the quadrant I image that are included high; n is the number of pixels included in the width of the I-th quadrant image; g (x, y) is the absolute gradient along the y-axis and the x-axisThe sum of (1); g (x, y) ═ f (x, y) -f (x, y +1) | + | f (x, y) -f (x +1, y) |.
In one embodiment, the absolute gradient accumulated along the y-axis is calculated by the following equation:
wherein, grad _ diffyIs the absolute gradient accumulated along the y-axis; n is the number of pixels included in the width of the I-th quadrant image.
In one embodiment, the quadrant III is a vertical stripe, the second image feature acquired in the image in the quadrant III comprises a 42-dimensional image feature comprising a grayscale mean, a grayscale standard deviation, a global contrast, a sharpness of the quadrant III, and the first 38 values in order from large to small in an absolute gradient accumulated along the y-axis; the IV quadrant is a transverse stripe, and the second image feature acquired in the image in the IV quadrant comprises a 42-dimensional image feature, the 42-dimensional image feature comprising: the mean gray scale, the standard deviation of gray scale, the global contrast in quadrant IV, the sharpness, and the first 98 values in order from large to small in the absolute gradient accumulated along the x-axis.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the method for testing the resolution of the fingerprint acquisition equipment.
An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program for executing any of the above methods for testing the resolution of a fingerprint acquisition device.
The embodiment of the invention also provides a device for testing the resolution of the fingerprint acquisition equipment, which is used for solving the technical problems of labor waste and low accuracy existing in manual judgment in the prior art. The device includes: the device comprises an image acquisition module, a data acquisition module and a data processing module, wherein the image acquisition module is used for acquiring an image of an optical test card acquired by fingerprint acquisition equipment to be tested, the stripes of the image are divided into four quadrants, the stripes of the quadrant I and the quadrant II are used for testing a first resolution, and the stripes of the quadrant III and the quadrant IV are used for testing a second resolution; the first testing module is used for respectively acquiring a preset number of first image features in an I-th quadrant and an II-th quadrant in the image, inputting the acquired first image features into a first classifier, and the result output by the first classifier indicates whether the resolution of the to-be-tested fingerprint acquisition device meets a first resolution or not, wherein the first classifier is obtained by adopting an optical test card image training conforming to the first resolution; and the second testing module is used for respectively acquiring a preset number of second image characteristics in a third quadrant and a fourth quadrant in the image, inputting the acquired second image characteristics into a second classifier, and the result output by the second classifier indicates whether the resolution of the fingerprint acquisition device to be tested meets a second resolution, wherein the second classifier is obtained by adopting an optical test card image training conforming to the second resolution.
In one embodiment, the first test module includes: the first feature acquisition unit is used for acquiring a first image feature in the image, wherein the first image feature acquired in the first quadrant in the image comprises 102-dimensional image features, and the 102-dimensional image features comprise a gray mean value, a gray standard deviation, the global contrast and the sharpness of the first quadrant and the first 98 values in the absolute gradient accumulated along the y axis from large to small; the second quadrant is a horizontal stripe, and the first image feature acquired in the second quadrant in the image includes a 102-dimensional image feature including: the mean grayscale, the standard deviation grayscale, the global contrast in quadrant II, the sharpness, and the first 98 values in the absolute gradient accumulated along the x-axis in descending order.
In one embodiment, the second test module includes: the second feature acquisition unit is used for acquiring a second image feature, wherein the third quadrant is a vertical stripe, the second image feature acquired in the third quadrant in the image comprises a 42-dimensional image feature, and the 42-dimensional image feature comprises a gray mean value, a gray standard deviation, global contrast and sharpness of the third quadrant and the first 38 values in the absolute gradient accumulated along the y axis from large to small; the IV quadrant is a transverse stripe, and the second image feature acquired in the image in the IV quadrant comprises a 42-dimensional image feature, the 42-dimensional image feature comprising: the mean gray scale, the standard deviation of gray scale, the global contrast in quadrant IV, the sharpness, and the first 98 values in order from large to small in the absolute gradient accumulated along the x-axis.
In the embodiment of the invention, the image of the optical test card collected by the fingerprint collecting device to be tested is obtained, the first image characteristics with the preset number are collected in the I-th quadrant and the II-th quadrant respectively, the collected first image characteristics of the I-th quadrant and the II-th quadrant are input into a first classifier, and the classifier is adopted to judge whether the resolution of the fingerprint collecting device to be tested meets the first resolution; meanwhile, a preset number of second image features are collected in the III-th quadrant and the IV-th quadrant respectively, the collected second image features of the III-th quadrant and the IV-th quadrant are input into a second classifier, and the classifier is adopted to judge whether the resolution of the fingerprint collection device to be tested meets the second resolution. Compared with the prior art, the method and the device have the advantages that manual judgment is avoided, the judgment accuracy is improved, the algorithm operation speed of the classifier is high, and the work efficiency is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a first schematic diagram of an optical test card image according to an embodiment of the present invention;
FIG. 2 is a second schematic diagram of an optical test card image according to an embodiment of the present invention;
FIG. 3 is a third schematic diagram of an optical test card image according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method for testing the resolution of a fingerprint acquisition device according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a coordinate system of an image of an optical test card according to an embodiment of the present invention;
FIG. 6 is a flowchart of a method for testing the resolution of a fingerprint acquisition device according to an embodiment of the present invention;
fig. 7 is a block diagram of an apparatus for testing resolution of a fingerprint acquisition device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the following embodiments and accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
In an embodiment of the present invention, a method for testing a resolution of a fingerprint acquisition device is provided, as shown in fig. 4, the method includes:
step 401: acquiring an image of an optical test card acquired by a fingerprint acquisition device to be tested, wherein stripes of the image are divided into four quadrants, the stripes of the I quadrant and the II quadrant are used for testing a first resolution, and the stripes of the III quadrant and the IV quadrant are used for testing a second resolution;
step 402: respectively acquiring a preset number of first image features in an I-quadrant and an II-quadrant in the image, inputting the acquired first image features into a first classifier, wherein the result output by the first classifier represents whether the resolution of the fingerprint acquisition device to be tested meets a first resolution, and the first classifier is obtained by image training of an optical test card conforming to the first resolution;
step 403: and respectively acquiring a preset number of second image features in a third quadrant and a fourth quadrant in the image, inputting the acquired second image features into a second classifier, wherein the result output by the second classifier represents whether the resolution of the fingerprint acquisition device to be tested meets a second resolution, and the second classifier is obtained by image training of an optical test card conforming to the second resolution.
As can be seen from the process shown in fig. 4, in the embodiment of the present invention, the image of the optical test card collected by the to-be-tested fingerprint collection device is obtained, and the first image features of the preset number are collected in the first quadrant I and the second quadrant II, so that the collected first image features of the first quadrant I and the second quadrant II are input into the first classifier, and the classifier is adopted to determine whether the resolution of the to-be-tested fingerprint collection device meets the first resolution; meanwhile, a preset number of second image features are collected in the III-th quadrant and the IV-th quadrant respectively, the collected second image features of the III-th quadrant and the IV-th quadrant are input into a second classifier, and the classifier is adopted to judge whether the resolution of the fingerprint collection device to be tested meets the second resolution. Compared with the prior art, the method and the device have the advantages that manual judgment is avoided, the judgment accuracy is improved, the algorithm operation speed of the classifier is high, and the work efficiency is improved.
In specific implementation, the image of the optical test card may be illustrated in fig. 1, where the first quadrant I is a vertical stripe, the second quadrant II is a horizontal stripe, the number of black lines in the first quadrant I and the second quadrant II is the same, and the intervals between the black lines are the same, and the first and second quadrants I and II are used for testing a first resolution, for example, the first resolution may be 1000 DPI. Quadrant III is the vertical stripe, quadrant IV is the horizontal stripe, the number of black lines in quadrant III and quadrant IV, and the spacing between black lines, are the same, and quadrant III and quadrant IV are used to test a second resolution, which may be 500DPI, for example. It can be seen that the upper quadrants I and II are generally different from the lower quadrants III and IV in that: the number of black lines is different and the pitch between the black lines is different.
In specific implementation, in order to determine the first resolution of the fingerprint acquisition device to be tested by using the classifier, in this embodiment, the I-th quadrant is a vertical stripe, the first image feature acquired in the I-th quadrant in the image includes 102-dimensional image features, where the 102-dimensional image features include a gray average value, a gray standard deviation, a global contrast and a sharpness of the I-th quadrant, and the first 98 values in an absolute gradient accumulated along a y-axis, which are arranged in order from large to small;
the second quadrant is a horizontal stripe, and the first image feature acquired in the second quadrant in the image includes a 102-dimensional image feature including: the mean grayscale, the standard deviation grayscale, the global contrast in quadrant II, the sharpness, and the first 98 values in the absolute gradient accumulated along the x-axis in descending order.
Specifically, as shown in fig. 5, for an image with a size of M pixels in height and N pixels in width, the calculation process of each feature in the first image feature acquired in quadrant I is described according to the following coordinate system (coordinate axes).
The gray level mean value μ is calculated by the following formula (1)1：
The gray-scale standard deviation σ is calculated by the following formula (2)1：
The contrast C of an image of height M and width N in quadrant I is calculated by the following formula (3)11：
Wherein M is the number of pixels highly included in the I-th quadrant image; n is the number of pixels included in the width of the I-th quadrant image; lc(x, y) is the local contrast at coordinate (x, y);
the contrast C of the image in quadrant I is calculated by the following formula (4) after down-sampling, i.e., reducing the image range to half the original size12：
Finally, the global contrast C of quadrant I is calculated by the following formula (5)1：
C1＝W1C11+W2C12 (5)
Wherein, W1Is 0.4578; w2Is 0.5422.
The sharpness S is calculated by the following equation (6)1：
Wherein S is1Is the sharpness of quadrant I; m is the number of pixels of the quadrant I image that are included high; n is the number of pixels included in the width of the I-th quadrant image; g (x, y) is the sum of the absolute gradients along the y-axis and the x-axis; g (x, y) ═ f (x, y) -f (x, y +1) | + | f (x, y) -f (x +1, y) |.
Since quadrant I is a vertical stripe, the gray difference between the edge of the black vertical stripe and the edge-adjacent pixel (left or right) is relatively large, and the absolute gradient accumulated along the y-axis is calculated by the following equation (7):
wherein, grad _ diffyIs the absolute gradient accumulated along the y-axis; n is the number of pixels included in the width of the I-th quadrant image.
Since there are 49 vertical stripes, each with left and right sides, then we want { grad _ d }iffyThe first 98 largest values in y 1, 2.
In specific implementation, the mean value mu of the gray scale in the first image characteristic collected in the II-th quadrant2Standard deviation of gray scale σ2Global contrast C in quadrant II2Sharpness S2With reference to the calculation of the mean value μ of the gray scale in the first image characteristic of quadrant I1Standard deviation of gray scale σ1Global contrast C of quadrant I1Sharpness S1The method of (3).
Since the II-th quadrant is a horizontal stripe, the gray difference between the edge of the horizontal stripe in black and the edge-adjacent pixel (above or below) is relatively large, the present application calculates the absolute gradient accumulated along the x-axis by the following equation (8):
since there are 49 horizontal stripes, each horizontal stripe has upper and lower sides, then we want to take { grad _ diffxThe first 98 largest values of x 1, 2.
In specific implementation, in order to determine the second resolution of the fingerprint acquisition device to be tested by using the classifier, in this embodiment, the third quadrant is a vertical stripe, the second image feature acquired in the third quadrant in the image includes a 42-dimensional image feature, where the 42-dimensional image feature includes a gray average value, a gray standard deviation, a global contrast and a sharpness of the third quadrant, and the first 38 values in an absolute gradient accumulated along the y-axis, which are arranged in order from large to small;
the IV quadrant is a transverse stripe, and the second image feature acquired in the image in the IV quadrant comprises a 42-dimensional image feature, the 42-dimensional image feature comprising: the mean gray scale, the standard deviation of gray scale, the global contrast in quadrant IV, the sharpness, and the first 38 values in order from large to small in the absolute gradient accumulated along the x-axis.
In specific implementation, the method for calculating 42-dimensional image features included in the second image feature of the third quadrant may refer to a method for calculating 102-dimensional image features included in the first image feature of the first quadrant; the method for calculating the 42-dimensional image feature included in the second image feature of the IV quadrant may refer to a method for calculating the 102-dimensional image feature included in the first image feature of the II quadrant.
In specific implementation, the first classifier and the second classifier may collect image data, and train the image data with an svmtrain (linear kernel parameter) of Matlab, where for the first classifier, the image marked to meet 1000DPI is +1, and the image marked to not meet 1000DPI is-1, and perform SVM training. And for the second classifier, marking the image which conforms to 500DPI as +1 and the image which does not conform to 500DPI as-1, and performing SVM training. Specifically, the first classifier and the second classifier may be implemented by a two-cascade classifier.
The process of the above method of testing the resolution of a fingerprint acquisition device is described in detail below, and as shown in fig. 6, the process includes:
1. acquiring an image of a specially-made optical test card on an optical fingerprint acquisition device;
2. extracting 102-dimensional image features of the I quadrant and 102-dimensional image features of the II quadrant of the image, and inputting the 204-dimensional image features into a trained first classifier; if the first classifier is passed, the resolution of the fingerprint acquisition equipment is larger than or equal to 1000DPI, the judgment process is ended, otherwise, the judgment process is continued.
3. Extracting 42-dimensional image features of the III quadrant and 42-dimensional image features of the IV quadrant of the image, and inputting the 84-dimensional image features into a trained second classifier; if the second classifier is passed, the resolution of the fingerprint acquisition device is larger than or equal to 500DPI, otherwise, the resolution is smaller than 500DPI, and the judgment process is ended.
In specific implementation, in this embodiment, a computer device is further provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements any of the above methods for testing the resolution of the fingerprint acquisition device.
In concrete implementation, in this embodiment, a computer-readable storage medium is further provided, where the computer-readable storage medium stores a computer program for executing any of the above methods for testing the resolution of a fingerprint acquisition device.
Based on the same inventive concept, the embodiment of the present invention further provides an apparatus for testing the resolution of a fingerprint acquisition device, as described in the following embodiments. Because the principle of the device for testing the resolution of the fingerprint acquisition equipment for solving the problems is similar to the method for testing the resolution of the fingerprint acquisition equipment, the implementation of the device for testing the resolution of the fingerprint acquisition equipment can refer to the implementation of the method for testing the resolution of the fingerprint acquisition equipment, and repeated parts are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 7 is a block diagram of an apparatus for testing resolution of a fingerprint acquisition device according to an embodiment of the present invention, as shown in fig. 7, the apparatus including:
the image acquisition module 701 is used for acquiring an image of an optical test card acquired by a fingerprint acquisition device to be tested, wherein stripes of the image are divided into four quadrants, the stripes of the I quadrant and the II quadrant are used for testing a first resolution, and the stripes of the III quadrant and the IV quadrant are used for testing a second resolution;
a first testing module 702, configured to collect a preset number of first image features in a quadrant I and a quadrant II in the image, respectively, and input the collected first image features into a first classifier, where a result output by the first classifier indicates whether a resolution of the to-be-tested fingerprint collection device meets a first resolution, where the first classifier is obtained by image training using an optical test card conforming to the first resolution;
the second testing module 703 is configured to collect a preset number of second image features in the third quadrant and the fourth quadrant in the image, respectively, input the collected second image features into a second classifier, and indicate whether the resolution of the fingerprint acquisition device to be tested meets a second resolution according to a result output by the second classifier, where the second classifier is obtained by image training using an optical test card conforming to the second resolution.
In one embodiment, the first test module includes: the first feature acquisition unit is used for acquiring a first image feature in the image, wherein the first image feature acquired in the first quadrant in the image comprises 102-dimensional image features, and the 102-dimensional image features comprise a gray mean value, a gray standard deviation, the global contrast and the sharpness of the first quadrant and the first 98 values in the absolute gradient accumulated along the y axis from large to small;
the second quadrant is a horizontal stripe, and the first image feature acquired in the second quadrant in the image includes a 102-dimensional image feature including: the mean grayscale, the standard deviation grayscale, the global contrast in quadrant II, the sharpness, and the first 98 values in the absolute gradient accumulated along the x-axis in descending order.
In one embodiment, the second test module includes: the second feature acquisition unit is used for acquiring a second image feature, wherein the third quadrant is a vertical stripe, the second image feature acquired in the third quadrant in the image comprises a 42-dimensional image feature, and the 42-dimensional image feature comprises a gray mean value, a gray standard deviation, global contrast and sharpness of the third quadrant and the first 38 values in the absolute gradient accumulated along the y axis from large to small;
the IV quadrant is a transverse stripe, and the second image feature acquired in the image in the IV quadrant comprises a 42-dimensional image feature, the 42-dimensional image feature comprising: the mean gray scale, the standard deviation of gray scale, the global contrast in quadrant IV, the sharpness, and the first 38 values in order from large to small in the absolute gradient accumulated along the x-axis.
In one embodiment, the first test module includes: a first test unit that calculates a global contrast ratio of quadrant I by the following formula: c1＝W1C11+W2C12(ii) a Wherein, C1Is the global contrast of quadrant I; w1Is 0.4578; w2Is 0.5422; c11Is the contrast of the quadrant I image;
m is the number of pixels of the quadrant I image that are included high; n is the number of pixels included in the width of the I-th quadrant image; lc(x, y) is the local contrast at coordinate (x, y);
；C12contrast when the image range of quadrant I is reduced to half of the original size;
in one embodiment, the first test unit in the first test module calculates the sharpness of quadrant I by the following equation:
wherein S is1Is the sharpness of quadrant I; m is the number of pixels of the quadrant I image that are included high; n is the number of pixels included in the width of the I-th quadrant image; g (x, y) is the sum of the absolute gradients along the y-axis and the x-axis; g (x, y) ═ f (x, y) -f (x, y +1) | + | f (x, y) -f (x +1, y) |.
In one embodiment, the first test cell in the first test module calculates the absolute gradient accumulated along the y-axis by the following equation:
wherein, grad _ diffyIs the absolute gradient accumulated along the y-axis; n is the number of pixels included in the width of the I-th quadrant image.
In the embodiment of the invention, the image of the optical test card collected by the fingerprint collecting device to be tested is obtained, the first image characteristics with the preset number are collected in the I-th quadrant and the II-th quadrant respectively, the collected first image characteristics of the I-th quadrant and the II-th quadrant are input into a first classifier, and the classifier is adopted to judge whether the resolution of the fingerprint collecting device to be tested meets the first resolution; meanwhile, a preset number of second image features are collected in the III-th quadrant and the IV-th quadrant respectively, the collected second image features of the III-th quadrant and the IV-th quadrant are input into a second classifier, and the classifier is adopted to judge whether the resolution of the fingerprint collection device to be tested meets the second resolution. Compared with the prior art, the method and the device have the advantages that manual judgment is avoided, the judgment accuracy is improved, the algorithm operation speed of the classifier is high, and the work efficiency is improved.
It will be apparent to those skilled in the art that the modules or steps of the embodiments of the invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, embodiments of the invention are not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes may be made to the embodiment of the present invention by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (11)
1. A method of testing the resolution of a fingerprint acquisition device, comprising:
acquiring an image of an optical test card acquired by fingerprint acquisition equipment to be tested, wherein stripes of the image are divided into four quadrants, the first quadrant is a vertical stripe, the second quadrant is a horizontal stripe, the number of stripe black lines in the first quadrant and the second quadrant is the same, the intervals between the stripe black lines are the same, the third quadrant is a vertical stripe, the fourth quadrant is a horizontal stripe, the number of stripe black lines in the third quadrant and the fourth quadrant is the same, the intervals between the stripe black lines are the same, the integral difference between the first quadrant and the second quadrant and the third quadrant and the fourth quadrant is that the number of stripe black lines is different, the intervals between the stripe black lines are different, the stripes in the first quadrant and the second quadrant are used for testing a first resolution, and the stripes in the third quadrant and the fourth are used for testing a second resolution;
respectively acquiring a preset number of first image features in an I-quadrant and an II-quadrant in the image, inputting the acquired first image features into a first classifier, wherein the result output by the first classifier represents whether the resolution of the fingerprint acquisition device to be tested meets a first resolution, and the first classifier is obtained by image training of an optical test card conforming to the first resolution;
and respectively acquiring a preset number of second image features in a third quadrant and a fourth quadrant in the image, inputting the acquired second image features into a second classifier, wherein the result output by the second classifier represents whether the resolution of the fingerprint acquisition device to be tested meets a second resolution, and the second classifier is obtained by image training of an optical test card conforming to the second resolution.
2. The method of testing the resolution of a fingerprint acquisition device of claim 1 wherein the I-th quadrant is a vertical stripe, the first image feature acquired in the I-th quadrant in the image comprises a 102-dimensional image feature comprising a grayscale mean, a grayscale standard deviation, a global contrast, a sharpness of the I-th quadrant, and the first 98 values in order from large to small in an absolute gradient accumulated along the y-axis;
the second quadrant is a horizontal stripe, and the first image feature acquired in the second quadrant in the image includes a 102-dimensional image feature including: the mean grayscale, the standard deviation grayscale, the global contrast in quadrant II, the sharpness, and the first 98 values in the absolute gradient accumulated along the x-axis in descending order.
3. The method of testing the resolution of a fingerprint acquisition device of claim 2 wherein the global contrast for quadrant I is calculated by the following formula:
C1＝W1C11+W2C12
wherein, C1Is the global contrast of quadrant I; w1Is 0.4578; w2Is 0.5422; c11Is the contrast of the quadrant I image;
m is the number of pixels of the quadrant I image that are included high; n is the number of pixels included in the width of the I-th quadrant image; lc(x, y) is the local contrast at coordinate (x, y);
4. the method of testing the resolution of a fingerprint acquisition device of claim 2 wherein the sharpness of quadrant I is calculated by the following equation:
wherein S is1Is the sharpness of quadrant I; m is the number of pixels of the quadrant I image that are included high; n is the number of pixels included in the width of the I-th quadrant image; g (x, y) is the sum of the absolute gradients along the y-axis and the x-axis; g (x, y) ═ f (x, y) -f (x, y +1) | + | f (x, y) -f (x +1, y) |, f (x, y) is the grayscale at the coordinates (x, y), f (x, y +1) is the grayscale at the coordinates (x, y +1), and f (x +1, y) is the grayscale at the coordinates (x +1, y).
5. The method of testing the resolution of a fingerprint acquisition device of claim 2 wherein the absolute gradient accumulated along the y-axis is calculated by the formula:
wherein, grad _ diffyIs the absolute gradient accumulated along the y-axis; n is the number of pixels included in the width of the I-th quadrant image; f (x, y) is the gray scale at coordinate (x, y); f (x, y-1) is the gray scale at coordinate (x, y-1).
6. The method of testing the resolution of a fingerprint acquisition device of any one of claims 1 to 5 wherein the quadrant III is a vertical stripe, the second image feature acquired in the image within the quadrant III comprises a 42-dimensional image feature comprising a gray mean, a gray standard deviation, a global contrast, a sharpness of the quadrant III, and the first 38 values in order from large to small in an absolute gradient accumulated along the y-axis;
the IV quadrant is a transverse stripe, and the second image feature acquired in the image in the IV quadrant comprises a 42-dimensional image feature, the 42-dimensional image feature comprising: the mean gray scale, the standard deviation of gray scale, the global contrast in quadrant IV, the sharpness, and the first 38 values in order from large to small in the absolute gradient accumulated along the x-axis.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements the method of testing the resolution of a fingerprint acquisition device according to any one of claims 1 to 6.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of testing the resolution of a fingerprint acquisition device according to any one of claims 1 to 6.
9. An apparatus for testing the resolution of a fingerprint acquisition device, comprising:
the image acquisition module is used for acquiring an image of an optical test card acquired by fingerprint acquisition equipment to be tested, wherein the stripes of the image are divided into four quadrants, the first quadrant is a vertical stripe, the second quadrant is a horizontal stripe, the number of black stripe lines in the first quadrant and the second quadrant is the same, the intervals between the black stripe lines are the same, the third quadrant is a vertical stripe, the fourth quadrant is a horizontal stripe, the number of black stripe lines in the third quadrant and the fourth quadrant is the same, the intervals between the black stripe lines are the same, the integral differences between the first quadrant and the second quadrant as well as between the third quadrant and the fourth quadrant are that the number of black stripe lines is different, the intervals between the black stripe lines are different, the stripes in the first quadrant and the second quadrant are used for testing a first resolution, and the stripes in the third quadrant and the fourth are used for testing a second resolution;
the first testing module is used for respectively acquiring a preset number of first image features in an I-th quadrant and an II-th quadrant in the image, inputting the acquired first image features into a first classifier, and the result output by the first classifier indicates whether the resolution of the to-be-tested fingerprint acquisition device meets a first resolution or not, wherein the first classifier is obtained by adopting an optical test card image training conforming to the first resolution;
and the second testing module is used for respectively acquiring a preset number of second image characteristics in a third quadrant and a fourth quadrant in the image, inputting the acquired second image characteristics into a second classifier, and the result output by the second classifier indicates whether the resolution of the fingerprint acquisition device to be tested meets a second resolution, wherein the second classifier is obtained by adopting an optical test card image training conforming to the second resolution.
10. The apparatus for testing resolution of a fingerprint acquisition device of claim 9 wherein said first test module comprises:
the first feature acquisition unit is used for acquiring a first image feature in the image, wherein the first image feature acquired in the first quadrant in the image comprises 102-dimensional image features, and the 102-dimensional image features comprise a gray mean value, a gray standard deviation, the global contrast and the sharpness of the first quadrant and the first 98 values in the absolute gradient accumulated along the y axis from large to small;
the second quadrant is a horizontal stripe, and the first image feature acquired in the second quadrant in the image includes a 102-dimensional image feature including: the mean grayscale, the standard deviation grayscale, the global contrast in quadrant II, the sharpness, and the first 98 values in the absolute gradient accumulated along the x-axis in descending order.
11. The apparatus for testing resolution of a fingerprint acquisition device as defined in claim 9 or 10, wherein said second test module comprises:
the second feature acquisition unit is used for acquiring a second image feature, wherein the third quadrant is a vertical stripe, the second image feature acquired in the third quadrant in the image comprises a 42-dimensional image feature, and the 42-dimensional image feature comprises a gray mean value, a gray standard deviation, global contrast and sharpness of the third quadrant and the first 38 values in the absolute gradient accumulated along the y axis from large to small;
the IV quadrant is a transverse stripe, and the second image feature acquired in the image in the IV quadrant comprises a 42-dimensional image feature, the 42-dimensional image feature comprising: the mean gray scale, the standard deviation of gray scale, the global contrast in quadrant IV, the sharpness, and the first 38 values in order from large to small in the absolute gradient accumulated along the x-axis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710748038.0A CN107578001B (en) | 2017-08-28 | 2017-08-28 | Method and device for testing resolution of fingerprint acquisition equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710748038.0A CN107578001B (en) | 2017-08-28 | 2017-08-28 | Method and device for testing resolution of fingerprint acquisition equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107578001A CN107578001A (en) | 2018-01-12 |
| CN107578001B true CN107578001B (en) | 2020-11-13 |
Family
ID=61029708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710748038.0A Active CN107578001B (en) | 2017-08-28 | 2017-08-28 | Method and device for testing resolution of fingerprint acquisition equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107578001B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110659536A (en) * | 2018-06-28 | 2020-01-07 | 京东方科技集团股份有限公司 | Method, device and system for testing resolution of fingerprint identification equipment and storage medium |
| CN112312121A (en) * | 2019-07-30 | 2021-02-02 | 浙江中正智能科技有限公司 | Test card for detecting image resolution of camera equipment and use method thereof |
| CN112560539A (en) * | 2019-09-10 | 2021-03-26 | 中国电子技术标准化研究院 | Resolution testing method, device and system for iris acquisition equipment |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101144842B (en) * | 2007-10-18 | 2010-11-03 | 上海交通大学 | Display device definition test card and its definition measuring method |
| US9307230B2 (en) * | 2012-06-29 | 2016-04-05 | Apple Inc. | Line pair based full field sharpness test |
| CN105260729B (en) * | 2015-11-20 | 2018-10-26 | 武汉大学 | A kind of satellite remote-sensing image cloud amount computational methods based on random forest |
| CN106525393B (en) * | 2017-01-17 | 2019-05-10 | 福建师范大学 | A kind of industrial camera lens optical projection detection resolution plate |
| CN106937109B (en) * | 2017-03-02 | 2018-10-23 | 湖北三赢兴电子科技有限公司 | The method that low cost judges resolution ratio of camera head level |
-
2017
- 2017-08-28 CN CN201710748038.0A patent/CN107578001B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107578001A (en) | 2018-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104331876B (en) | Method for detecting straight line and processing image and related device | |
| EP3396359B1 (en) | Damage information processing device and damage information processing method | |
| CN108537787B (en) | Quality judgment method for face image | |
| CN107578001B (en) | Method and device for testing resolution of fingerprint acquisition equipment | |
| CN110570435B (en) | Method and device for carrying out damage segmentation on vehicle damage image | |
| CN105574527A (en) | Quick object detection method based on local feature learning | |
| CN110490839B (en) | Method and device for detecting damaged area in expressway and computer equipment | |
| CN105718931B (en) | System and method for determining clutter in acquired images | |
| CN110189341B (en) | Image segmentation model training method, image segmentation method and device | |
| CN112233076B (en) | Structural vibration displacement measurement method and device based on red round target image processing | |
| CN112991374B (en) | Canny algorithm-based edge enhancement method, canny algorithm-based edge enhancement device, canny algorithm-based edge enhancement equipment and storage medium | |
| CN116165216B (en) | Liquid crystal display micro scratch flaw 3D detection method, system and computing equipment | |
| CN113592839B (en) | Distribution network line typical defect diagnosis method and system based on improved fast RCNN | |
| CN106485710A (en) | A kind of element mistake part detection method and device | |
| US10375383B2 (en) | Method and apparatus for adjusting installation flatness of lens in real time | |
| CN111724354B (en) | Image processing-based method for measuring wheat ear length and wheat ear number of multiple wheat plants | |
| JP2016220198A (en) | Information processing device, method, and program | |
| CN113252103A (en) | Method for calculating volume and mass of material pile based on MATLAB image recognition technology | |
| CN107403429B (en) | Method for quickly and automatically acquiring parameters of periodic sequence image model | |
| CN111161264B (en) | Method for segmenting TFT circuit image with defects | |
| CN109389644A (en) | Parking stall line detecting method based on direction gradient enhancing | |
| CN109084721B (en) | Method and apparatus for determining a topographical parameter of a target structure in a semiconductor device | |
| Zhang et al. | A combined approach to single-camera-based lane detection in driverless navigation | |
| CN112146834B (en) | Method and device for measuring structural vibration displacement | |
| CN114708230A (en) | Vehicle frame quality detection method, device, equipment and medium based on image analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |