CN110020591B - Fingerprint template registration method and fingerprint identification device based on sliding sampling - Google Patents
Fingerprint template registration method and fingerprint identification device based on sliding sampling Download PDFInfo
- Publication number
- CN110020591B CN110020591B CN201910105883.5A CN201910105883A CN110020591B CN 110020591 B CN110020591 B CN 110020591B CN 201910105883 A CN201910105883 A CN 201910105883A CN 110020591 B CN110020591 B CN 110020591B
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- image
- images
- sliding
- sampling
- 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
- 238000000034 method Methods 0.000 title claims abstract description 182
- 238000005070 sampling Methods 0.000 title claims abstract description 62
- 238000012216 screening Methods 0.000 claims abstract description 59
- 238000012545 processing Methods 0.000 claims abstract description 31
- 210000001015 abdomen Anatomy 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 6
- 230000007547 defect Effects 0.000 abstract description 4
- 230000001965 increasing effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06V40/13—Sensors therefor
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
- Image Input (AREA)
Abstract
The application provides a fingerprint template registration method and a fingerprint identification device based on sliding sampling. According to the fingerprint image registration method, through the screening process of the collected fingerprint images, coincident fingerprint images in the registration fingerprint image data processing process are reduced, incomplete pressing fingerprint images are removed, the fingerprint images are screened, the data processing amount in the fingerprint image registration process is reduced, the data processing efficiency is improved, the quick entry of the fingerprint template is facilitated, and the fingerprint entry experience of a user is improved; the application adopts a sliding type and pressing type combined sampling mode to draw the advantages of the sliding type and the pressing type, overcomes the defects of the sliding type and the pressing type by means of the screening process, and is more beneficial to improving user experience and fingerprint identification rate.
Description
Technical Field
The present application relates to a data processing method and apparatus, and in particular, to a fingerprint data acquisition processing method and fingerprint identification apparatus.
Background
In a small area sensor based fingerprint identification implementation, fingerprint entry means for fingerprint template registration include push type entry and slide type entry.
In the prior art, fingerprint data to be registered are collected through multiple pressing in a pressing type mode, and a collected fingerprint template is easy to form a template island due to the position difference of each pressing; and fingerprint images with high coincidence degree are easy to collect after multiple pressing entries; in addition, the push type fingerprint input process requires the user to perform ten times, even tens of times of push operations, and the user experience is poor.
In the prior art, a plurality of continuous fingerprint image data are collected in the process that the finger slides over the fingerprint sensor in a sliding mode, so that the fingerprint information collection amount is large, and the user experience is improved. However, sliding type input still can produce a large amount of fingerprint images with high overlap ratio, increases fingerprint image concatenation processing difficulty in the fingerprint registration process, causes data processing time to increase, and the image area is big after fingerprint image concatenation, causes fingerprint image recognition time to increase as well.
Disclosure of Invention
The application aims to solve the technical problem of avoiding the defects of the prior art and provides a fingerprint template registration method capable of screening out high-coincidence fingerprint images and incomplete pressing fingerprint images, improving fingerprint input registration efficiency, further being beneficial to improving fingerprint recognition rate, enhancing sliding unlocking experience and improving user experience effect, and a fingerprint recognition device for realizing the method.
The application solves the technical problems by adopting the following technical scheme:
a fingerprint template registration method capable of rapidly screening images based on sliding sampling is provided, and the fingerprint template registration method is based on a fingerprint identification device comprising a fingerprint acquisition sensor, a data processor and a memory. The method comprises the following steps:
a fingerprint template entry process based on sliding sampling,
prompting a user to input a fingerprint template in a mode that a finger slides through a fingerprint acquisition window;
the fingerprint acquisition sensor acquires n fingerprint images;
the n fingerprint images are subjected to a screening process as follows,
a starting image process is selected and a starting image process is selected,
detecting the coincidence degree of two adjacent fingerprint images according to the image coincidence judging standard and the sequence from front to back of the fingerprint collecting time, and selecting an earlier fingerprint image in a first pair of adjacent fingerprint images which do not accord with the image coincidence judging standard as a starting image;
the process of terminating the image is selected,
selecting a first fingerprint image which accords with the full-press image standard as a termination image according to the full-press image standard and the sequence of the fingerprint acquisition time from back to front;
the course of the selection of the fingerprint image,
selecting a group of fingerprint images to be registered from a group of fingerprint images from the initial image to the final image according to the screening standard;
the process of inputting the fingerprint template,
processing each fingerprint image group to be registered and storing the fingerprint image group into a memory;
detecting whether a sliding number threshold value of sliding fingerprint input is reached or not; if the sliding frequency threshold is not reached, returning to prompt the user to record the fingerprint template in a mode that the finger slides through the fingerprint acquisition window; and if the sliding times threshold is reached, terminating the fingerprint template recording process based on sliding sampling.
The process of selecting the initial image is specifically as follows:
setting a correlation coefficient threshold of a local area of the image; the correlation coefficient of the local area of the image reflects the superposition degree of the two images;
sequentially selecting adjacent fingerprint images according to the sequence of the fingerprint acquisition time from front to back, carrying out the following image coincidence judging process,
selecting the same local area from the two adjacent fingerprint images, comparing the two local areas, judging the coincidence degree of the two local areas, and calculating the local area correlation coefficient of the two fingerprint images;
if the local area correlation coefficient is larger than the image local area correlation coefficient threshold, judging that fingerprint images where the two local areas are respectively located coincide, and conforming to an image coincidence judging standard; otherwise, judging that the fingerprint images of the two local areas are not overlapped and do not accord with the image overlapping judgment standard;
when a first pair of adjacent fingerprint images which do not meet the image coincidence judging standard are found, an earlier fingerprint image in the two adjacent fingerprint images is selected as a starting image.
The process of selecting the termination image is specifically as follows:
setting a non-pressing area duty ratio threshold;
the non-pressing area judging process is carried out on each fingerprint image according to the sequence of the fingerprint acquisition time from the back to the front,
calculating a pressing area and a non-pressing area of the fingerprint image according to the gray value of the fingerprint image, and calculating the ratio of the area of the non-pressing area to the area of the fingerprint image;
comparing the non-pressing area occupation ratio of the fingerprint image with a non-pressing area occupation ratio threshold, and judging that the fingerprint image meets the full-pressing image standard if the non-pressing area occupation ratio is not larger than the non-pressing area occupation ratio threshold; if the non-pressing area occupation ratio is larger than the non-pressing area occupation ratio threshold, judging that the full-pressing image standard is not met;
when the first fingerprint image meeting the full-press image standard is found, the fingerprint image is selected as the termination image.
The fingerprint image selection process specifically comprises the following steps:
in an alternative image group comprising sn fingerprint images acquired from a starting image to a terminating image, sequentially numbering each fingerprint image according to the sequence from front to back of the fingerprint acquisition time;
determining the effective image quantity valid_n according to the operation parameters of the fingerprint identification device;
if sn is less than or equal to valid_n, all sn fingerprint images are selected as fingerprint image groups to be registered;
if sn > valid_n, filtering and sampling, selecting the fingerprint image with serial number of sid from the candidate image group as the ith fingerprint image in the fingerprint image group to be registered,
sid=round（i 0 +（i-1）×sf），
wherein i is 0 Is the serial number of the starting image;
i is the serial number of each fingerprint image in the fingerprint image group to be registered, i is an independent variable, i is a natural number, and i is more than or equal to 1 and less than or equal to valid_n;
sil is the serial number of the finger print image in the alternative image group, sil is the natural number, and sil is more than or equal to 1 and less than or equal to sn;
sf is the screening sampling frequency, sf = sn/valid_n, sf is the floating point number;
round (x) is a function of rounding the variable x to an integer.
Specifically, the valid_n of the number of valid images is determined according to the operation parameters of the fingerprint identification device:
calculating the effective image quantity valid_n= (tl/ll-1)/r+1, wherein tl is the maximum total length empirical value of human finger abdomen, ll is the side length of a single square image acquired by the fingerprint acquisition sensor, and r is the image coincidence proportion coefficient, and r is more than or equal to 0.2 and less than or equal to 0.5.
Specifically, the screening process further includes the following steps:
the process of establishing the image buffer area is carried out,
the number of valid _ n of valid pictures is calculated,
valid_n=(tl/ll-1)/r+1，
wherein tl is the empirical value of the maximum total length of human finger abdomen,
ll is the side length of a single square image acquired by the fingerprint acquisition sensor,
r is an image coincidence proportion coefficient, and r is more than or equal to 0.2 and less than or equal to 0.5;
the number of stored images save _ n is calculated,
save_n=q×valid_n，
wherein q is a distribution proportionality coefficient, and q is more than or equal to 1.2 and less than or equal to 1.5;
memory space for storing save_n fingerprint images is allocated in memory for the screening process.
In addition, the fingerprint template registration method capable of rapidly screening images based on sliding sampling further comprises the following fingerprint template entry process based on pressing sampling:
prompting a user to press the fingerprint acquisition window with a finger;
acquiring a fingerprint image to be registered;
detecting whether the pressing frequency threshold value of the pressing type fingerprint input is reached, if the pressing frequency threshold value is not reached, returning to prompting the user to press the fingerprint acquisition window by the finger; if the pressing frequency threshold is reached, performing a fingerprint template input process;
the process of inputting the fingerprint template,
and processing the fingerprint image group to be registered obtained by the push type input and storing the fingerprint image group to be registered in a memory.
The application can solve the technical problems by adopting the following technical proposal:
a fingerprint identification device based on a sliding type sampling registration fingerprint template and capable of rapidly screening images is designed and manufactured and comprises a data processor, and a fingerprint acquisition sensor and a memory which are electrically connected with the data processor. The data processor comprises more than two electronic components, and the composition and the connection structure of each electronic component enable the fingerprint identification device to complete the following fingerprint template registration process:
a fingerprint template entry process based on sliding sampling,
prompting a user to input a fingerprint template in a mode that a finger slides through a fingerprint acquisition window;
the fingerprint acquisition sensor acquires n fingerprint images;
the n fingerprint images are subjected to a screening process as follows,
a starting image process is selected and a starting image process is selected,
detecting the coincidence degree of two adjacent fingerprint images according to the image coincidence judging standard and the sequence from front to back of the fingerprint collecting time, and selecting an earlier fingerprint image in a first pair of adjacent fingerprint images which do not accord with the image coincidence judging standard as a starting image;
the process of terminating the image is selected,
selecting a first fingerprint image which accords with the full-press image standard as a termination image according to the full-press image standard and the sequence of the fingerprint acquisition time from back to front;
the course of the selection of the fingerprint image,
selecting a group of fingerprint images to be registered from a group of fingerprint images from the initial image to the final image according to the screening standard;
the process of inputting the fingerprint template,
processing each fingerprint image group to be registered and storing the fingerprint image group into a memory;
detecting whether a sliding number threshold value of sliding fingerprint input is reached or not; if the sliding frequency threshold is not reached, returning to prompt the user to record the fingerprint template in a mode that the finger slides through the fingerprint acquisition window; and if the sliding times threshold is reached, terminating the fingerprint template recording process based on sliding sampling.
In addition, the composition and the connection structure of each electronic component of the data processor enable the fingerprint identification device to enable the fingerprint template registration process to further comprise the following fingerprint template registration process based on push type sampling:
prompting a user to press the fingerprint acquisition window with a finger;
acquiring a fingerprint image to be registered;
detecting whether the pressing frequency threshold value of the pressing type fingerprint input is reached, if the pressing frequency threshold value is not reached, returning to prompting the user to press the fingerprint acquisition window by the finger; if the pressing frequency threshold is reached, performing a fingerprint template input process;
the process of inputting the fingerprint template,
and processing the fingerprint image group to be registered obtained by the push type input and storing the fingerprint image group to be registered in a memory.
Compared with the prior art, the fingerprint template registration method and the fingerprint identification device based on sliding sampling have the technical effects that:
through the screening process of the collected fingerprint images, coincident fingerprint images in the registration fingerprint image data processing process are reduced, incompletely pressed fingerprint images are removed, the fingerprint images are screened, the data processing amount in the fingerprint image registration process is reduced, the data processing efficiency is improved, the quick entry of the fingerprint template is facilitated, and the user fingerprint entry experience is improved; the effective fingerprint template registration information is increased by removing repeated useless data in the screening process, so that the fingerprint identification rate is improved;
the fingerprint identification sliding unlocking method is beneficial to improving fingerprint identification sliding unlocking experience based on a sliding type sampling mode;
the application adopts a sliding type and pressing type combined sampling mode to draw the advantages of the sliding type and the pressing type, overcomes the defects of the sliding type and the pressing type by means of the screening process, and is more beneficial to improving user experience and fingerprint identification rate.
Drawings
FIG. 1 is an electrical schematic block diagram of a first embodiment of the present application, a fingerprint template registration method and a fingerprint recognition device based on sliding sampling;
FIG. 2 is a flow chart of the first embodiment fingerprint template registration method;
FIG. 3 is a schematic diagram of a typical full fingerprint;
FIG. 4 is an enlarged partial schematic view of the indicated portion A of FIG. 3;
FIG. 5 is a schematic diagram of a principle of partial region coincidence determination of adjacent fingerprint images;
FIG. 6 is a schematic view of the first embodiment selecting a start image and a stop image;
fig. 7 is a flowchart of a fingerprint template registration method according to a second embodiment of the present application.
Detailed Description
The embodiments are described in further detail below in conjunction with the drawings.
The application provides a fingerprint identification device based on a sliding type sampling registration fingerprint template and capable of rapidly screening images, which is shown in fig. 1 and comprises a data processor 1, and a fingerprint acquisition sensor 2 and a memory 3 which are electrically connected with the data processor 1. The fingerprint identification device can be used as a biological characteristic identification device for realizing unlocking functions of electronic equipment such as a computer, a mobile communication terminal, a tablet personal computer, an electronic watch, a video and audio player and the like, and can also be used for independent unlocking equipment, independent identity verification equipment and the like. When the fingerprint template is collected, fingerprint information is collected by the fingerprint collecting sensor 2 and converted into original fingerprint data to be sent to the data processor 1. The data processor 1 processes the original fingerprint data to form fingerprint template registration data and stores the fingerprint template registration data in the memory 3. When the biological characteristic identity is identified, the data processor 1 compares the fingerprint data acquired by the fingerprint acquisition sensor 2 with the fingerprint template registration data stored in the memory 3 to judge, and then carries out the subsequent related processing process according to the judgment result. The application focuses on the data processing process of registering the fingerprint template in the fingerprint template collecting process. The data processor 1 comprises more than two electronic components, and the composition and the connection structure of each electronic component enable the fingerprint identification device to realize the fingerprint template registration method capable of rapidly screening images based on sliding sampling.
In a first embodiment of the present application, as shown in fig. 2, the fingerprint template registration method capable of rapidly screening images based on slide sampling according to the present application includes a fingerprint template entry process 6 based on slide sampling, in addition to a fingerprint template registration start process 5 and a fingerprint template registration end process 8, which mark the start of the method.
The fingerprint template entry process 6 based on sliding sampling includes the following processes:
as shown in the flow 61 of fig. 2, the user is prompted to enter a fingerprint template in such a way that the finger slides over the fingerprint acquisition window of the fingerprint acquisition sensor 2;
as shown in flow 62 of fig. 2, the fingerprint acquisition sensor 2 acquires n fingerprint images during the finger sliding over the fingerprint acquisition window, as shown in fig. 6;
as shown in the flow 63 of fig. 2, a screening process is performed on the n fingerprint images; the screening process includes selecting a start image process 632, selecting a stop image process 633 and a fingerprint image selection process 634; the method comprises the following steps:
as shown in flow 632 of fig. 2, a start image process is selected,
detecting the coincidence degree of two adjacent fingerprint images according to the image coincidence judging standard and the sequence from front to back of the fingerprint collecting time, and selecting an earlier fingerprint image in a first pair of adjacent fingerprint images which do not accord with the image coincidence judging standard as a starting image;
as shown in fig. 2, flow 633, a termination image process is selected,
selecting a first fingerprint image which accords with the full-press image standard as a termination image according to the full-press image standard and the sequence of the fingerprint acquisition time from back to front;
as shown in flow 634 of fig. 2, the fingerprint image selection process:
selecting a group of fingerprint images to be registered from a group of fingerprint images from the initial image to the final image according to the screening standard; selecting a fingerprint image group to be registered by eliminating fingerprint images which do not need to be subjected to subsequent processing as far as possible by means of a screening standard, thereby reducing the data processing amount of subsequent flow and increasing fingerprint template registration information beneficial to fingerprint identification;
after the screening process is completed, a fingerprint template input process is carried out:
as shown in fig. 2, in a process 64, each fingerprint image group to be registered is processed and stored in the memory 3;
as shown in flow 65 of fig. 2, it is detected whether a sliding number threshold of sliding fingerprint entry is reached; if the sliding frequency threshold is not reached, returning to prompt the user to enter the fingerprint template in a mode that the finger slides through the fingerprint acquisition window, namely returning to the flow 61 shown in fig. 2; and if the sliding times threshold is reached, terminating the fingerprint template recording process 6 based on sliding sampling, namely finishing fingerprint template recording based on sliding sampling.
Based on a sliding sampling mode, the fingerprint template stored in the fingerprint identification device can be correspondingly used for sliding fingerprint identification and unlocking, and the fingerprint identification sliding unlocking experience is improved. According to the application, through the screening process 63 of the collected fingerprint images, the coincident fingerprint images in the registered fingerprint image data processing process are reduced, the incompletely pressed fingerprint images are removed, the fingerprint images are screened, the data processing amount in the fingerprint image registration process is reduced, the data processing efficiency is improved, the quick entry of the fingerprint template is realized, and the fingerprint entry experience of a user is improved; and the effective fingerprint template registration information is increased by removing repeated useless data through the screening process 63, so that the fingerprint identification rate is improved.
The order of execution of the select starting image process 632 and the select ending image process 633 of the screening process 63 may be interchanged.
The screening process is mainly aimed at three practical problems encountered in sliding fingerprint entry:
1. the fingerprint images collected in the initial stage of finger sliding are easy to cause the problem that adjacent images are completely overlapped;
2. the fingerprint image collected at the tail stage of finger sliding is easy to have the problem of non-full finger image;
3. adjacent fingerprint images acquired at the middle stage of finger sliding still tend to have the problem of large overlapping areas.
The above problems all bring more redundant data to the subsequent fingerprint image splicing processing and fingerprint template forming processing, so that the data processing amount is increased. The screening process 63 is to pertinently pre-process the collected fingerprint image to overcome the above three problems, thereby reducing the data processing amount of subsequent processing, improving the data processing efficiency, and improving the user experience.
In order to solve the problem that the fingerprint images collected in the initial stage of finger sliding are easy to have complete overlapping of adjacent images, the initial image selection process 632 performs overlapping judgment and screening on the fingerprint images collected in the initial stage, and several fingerprint images collected earliest can be discarded according to application scenes, finger sliding speed and experience values, or overlapping images can be judged and discarded through image matching. The first embodiment of the present application selects the starting image process 632 to determine the image coincidence level by using the image-fixed local area correlation coefficient. As shown in fig. 5, local areas Z are selected at fixed positions on adjacent fingerprint images, the degree of correlation between the local areas Z is determined according to the data of the local areas Z, such as the number of feature points, the numerical value of the feature points, the contrast of the fixed local areas, and the like, and the degree of correlation between the local areas is represented by an image local area correlation coefficient Y. The closer the local area correlation coefficient Y is to 1, the more the two adjacent fingerprint images tend to overlap completely. And judging the coincidence ratio of the adjacent fingerprint images through the correlation coefficient of the local areas of the images. In the first embodiment of the present application, as shown in fig. 6, the process 632 of selecting the initial image is specifically as follows:
setting the image local area correlation coefficient threshold, the first embodiment of the present application sets the image local area correlation coefficient threshold to 0.9. The local area correlation coefficient of the image reflects the coincidence degree of the two images.
And sequentially selecting adjacent fingerprint images according to the sequence of the fingerprint acquisition time from front to back, and carrying out the following image coincidence judging process:
selecting the same local area from the two adjacent fingerprint images, comparing the two local areas, judging the coincidence degree of the two local areas, and calculating the local area correlation coefficient of the two fingerprint images;
if the local area correlation coefficient is larger than the image local area correlation coefficient threshold, judging that fingerprint images where the two local areas are respectively located coincide, and conforming to an image coincidence judging standard; otherwise, judging that the fingerprint images of the two local areas are not overlapped and do not accord with the image overlapping judgment standard;
when a first pair of adjacent fingerprint images which do not meet the image coincidence judging standard are found, an earlier fingerprint image in the two adjacent fingerprint images is selected as a starting image.
In the first embodiment of the present application, as shown in fig. 6, among n fingerprint images sequenced according to the acquisition time, comparison is performed from the adjacent image 1 and image 2. The image local area correlation coefficients of the image 1 and the image 2 are calculated for the respective local areas Z of the image 1 and the image 2, and the image local area correlation coefficients of the image 1 and the image 2 are larger than the image local area correlation coefficient threshold value of 0.9, so that the image 1 and the image 2 are judged to belong to the coincident image. And then calculating the image local area correlation coefficients of the image 2 and the image 3 according to the respective local areas Z of the image 2 and the image 3, wherein the image local area correlation coefficients of the image 2 and the image 3 are smaller than an image local area correlation coefficient threshold value of 0.9, the image 3 has obvious displacement relative to the image 2, the image 2 and the image 3 are judged not to belong to the coincident images, and the image 2 with earlier acquisition is selected from the image 2 and the image 3 as a starting image.
The first embodiment of the present application selects the initial image process 632 to complete the comparison data calculation by using the local area, and complete the comparison with less data processing amount, and has high stability and execution efficiency
In order to solve the problem that the fingerprint image collected at the end stage of finger sliding is easy to generate a non-full-finger image, the terminating image process 633 is selected to perform non-full-finger image screening on the fingerprint image collected at the end stage, and a plurality of last collected fingerprint images can be discarded according to application scenes, finger sliding speed and experience values, or the non-full-finger image can be judged and discarded according to the number of image feature points, and the like. In the first embodiment of the present application, the selecting terminating image process 633 discriminates the non-full-finger image that is not fully pressed according to the image gray value. The gray value discrimination can adopt the method of setting a dynamic gray threshold value according to the real-time illumination condition of the application environment to judge and distinguish the pressed areas. In the first embodiment of the present application, a gray level fixed threshold segmentation method is adopted to judge the non-pressing area, and the specific steps are as follows:
setting a non-pressing area ratio threshold, wherein the non-pressing area ratio threshold is 10%;
and carrying out a non-pressing area judging process on each fingerprint image according to the sequence of the fingerprint acquisition time from back to front:
calculating a pressing area and a non-pressing area of the fingerprint image according to the gray value of the fingerprint image, and calculating the ratio of the area of the non-pressing area to the area of the fingerprint image;
comparing the non-pressing area occupation ratio of the fingerprint image with a non-pressing area occupation ratio threshold, and judging that the fingerprint image meets the full-pressing image standard if the non-pressing area occupation ratio is not larger than the non-pressing area occupation ratio threshold; if the non-pressing area occupation ratio is larger than the non-pressing area occupation ratio threshold, judging that the full-pressing image standard is not met;
when the first fingerprint image meeting the full-press image standard is found, the fingerprint image is selected as the termination image.
In the first embodiment of the present application, as shown in fig. 6, in the n fingerprint images sequenced according to the acquisition time, the image selection is terminated in the reverse order, i.e. the selection process is started from the image n. The pressed area and the non-pressed area are calculated for the gray value of the image n, and the non-pressed area occupation ratio of the non-pressed area occupation area of the image n is determined. Comparing this ratio with the non-pressed area ratio threshold of 10%, as shown in fig. 6, it is apparent that the non-pressed area ratio of the image n is greater than 10%, thereby determining that the full-pressed image standard is not met. And then judging the image n-1, and analogizing until an image n-4 with the non-pressing area ratio being more than 10% of the non-pressing area ratio threshold value is found, namely the image n-4 is the first fingerprint image meeting the safety pressing image standard, and then selecting the image n-4 as a termination image.
In the first embodiment of the present application, as shown in fig. 6, through the process 632 of selecting the initial image and the process 633 of selecting the final image, the image 2 is selected as the initial image, the image n-4 is selected as the final image, and n-5 candidate image groups are taken in total.
In order to solve the problem that the adjacent fingerprint images acquired in the middle stage of finger sliding still easily have a larger overlapping area, the fingerprint image selecting process 634 should perform image overlapping screening on the images in the alternative image group, and an image matching method of image comparison, a characteristic point discriminating method of characteristic point data comparison and the like can be adopted. The first embodiment of the application adopts a sampling extraction method, and specifically comprises the following steps:
in an alternative image group comprising sn fingerprint images acquired from a starting image to a terminating image, sequentially numbering each fingerprint image according to the sequence from front to back of the fingerprint acquisition time;
determining the effective image quantity valid_n according to the operation parameters of the fingerprint identification device; the operation parameters of the fingerprint identification device comprise sampling frequency, fingerprint acquisition window size, set coincidence ratio, set finger length experience value and the like; the valid_n of the effective image number limits the maximum value of the number of fingerprint images in the fingerprint image group to be registered, and when the maximum value exceeds the maximum value, redundant data can be generated, so that the data processing capacity is increased;
if sn is less than or equal to valid_n, all sn fingerprint images are selected as fingerprint image groups to be registered;
if sn > valid_n, filtering and sampling, selecting the fingerprint image with serial number of sid from the candidate image group as the ith fingerprint image in the fingerprint image group to be registered,
sid=round（i 0 +（i-1）×sf），
wherein i is 0 Is the serial number of the starting image;
i is the serial number of each fingerprint image in the fingerprint image group to be registered, i is an independent variable, i is a natural number, and i is more than or equal to 1 and less than or equal to valid_n;
sil is the serial number of the finger print image in the alternative image group, sil is the natural number, and sil is more than or equal to 1 and less than or equal to sn;
sf is the screening sampling frequency, sf = sn/valid_n, sf is the floating point number;
round (x) is a function of rounding the variable x to an integer.
In the first embodiment of the present application, the effective image number valid_n=7 determined according to the operation parameters of the fingerprint identification device, if n=11, the fingerprint image numbers sn=n-5=6 of the candidate image groups selected by the start image selecting process 632 and the stop image selecting process 633, that is, the images 2 to 7, are as described above. Since sn < valid_n in this assumption, all 6 fingerprint images of the candidate image group are selected as the fingerprint image group to be registered.
If n=20, then the fingerprint image numbers sn=n-5=15, i.e., images 2 through 16, of the candidate image groups selected according to the previously described selection start image process 632 and selection stop image process 633 have been numbered in order of fingerprint acquisition time from front to back, i.e., i 0 =2, then the screening samples are taken at a screening sample frequency of sf=sn/valid_n=15/7≡2.14:
when i=1, sid=round (i 0 ++ (i-1) ×sf) =round (2+ (1-1) ×2.14) =2, i.e., the 1 st fingerprint image in the fingerprint image group to be registered is image 2 of the candidate image group;
when i=2, sid=round (i 0 ++ (i-1) ×sf) =round (2+ (2-1) ×2.14) =4, i.e., the 2 nd fingerprint image in the fingerprint image group to be registered is image 4 of the candidate image group;
when i=3, sid=round (i 0 ++ (i-1) ×sf) =round (2+ (3-1) ×2.14) =6, i.e., the 3 rd fingerprint image in the fingerprint image group to be registered is image 6 of the candidate image group;
when i=4, sid=round (i 0 ++ (i-1) ×sf) =round (2+ (4-1) ×2.14) =8, i.e., the 4 th fingerprint image in the fingerprint image group to be registered is image 8 of the candidate image group;
when i=5, sid=round (i 0 ++ (i-1) ×sf) =round (2+ (5-1) ×2.14) =11, i.e., the 5 th fingerprint image in the fingerprint image group to be registered is image 11 of the candidate image group;
when i=6, sid=round (i 0 ++ (i-1) ×sf) =round (2+ (6-1) ×2.14) =13, i.e. the finger to be registeredThe 6 th fingerprint image in the fingerprint image group is the image 13 of the candidate image group;
when i=7, sid=round (i 0 ++ (i-1) ×sf) =round (2+ (7-1) ×2.14) =15, i.e., the 7 th fingerprint image in the fingerprint image group to be registered is the image 15 of the candidate image group.
The fingerprint image selection process 634 of the present application avoids the problem of having a large overlapping area that may occur with adjacent fingerprint images acquired at an intermediate stage of finger sliding, as much as possible, by screening and sampling.
In the first embodiment of the present application, the specific method for determining the effective image number valid_n according to the operation parameter of the fingerprint identification apparatus is as follows:
as shown in fig. 3, an empirical value of the maximum total length of human finger belly is tl, as shown in fig. 4, the side length of a single square image collected by a fingerprint collection window of the fingerprint collection sensor 2 is ll, a proportionality coefficient r reflecting the coincidence ratio of the fingerprint images is set to be more than or equal to 0.2 and less than or equal to 0.5, and then the effective image quantity valid_n= (tl/ll-1)/r+1 is set.
In order to have enough memory to process the screening process data, the screening process 63 further includes an image buffer creation process 631, the image buffer creation process 631 being generally located before the screening process, i.e., before the start image process 632 is selected, and before the stop image process 633 and the fingerprint image selection process 634 are selected, as shown in fig. 2. The process 631 of creating the image buffer includes:
the number of valid _ n of valid pictures is calculated,
valid_n=(tl/ll-1)/r+1，
wherein tl is the empirical value of the maximum total length of human finger abdomen,
ll is the side length of a single square image acquired by the fingerprint acquisition sensor,
r is an image coincidence proportion coefficient, and r is more than or equal to 0.2 and less than or equal to 0.5;
the number of stored images save _ n is calculated,
save_n=q×valid_n，
wherein q is a distribution proportionality coefficient, and q is more than or equal to 1.2 and less than or equal to 1.5;
memory 3 is allocated for the screening process for storing save_n fingerprint images.
The fingerprint template registration method capable of rapidly screening images based on sliding sampling is characterized in that a fingerprint template entry process 7 based on pressing sampling is further added on the basis of a fingerprint template entry process 6 based on sliding sampling. In a second embodiment of the present application, as shown in fig. 7, a fingerprint template entry process 7 based on push sampling includes:
as shown in fig. 7, flow 71, prompts the user to press with a finger against the fingerprint acquisition window of fingerprint acquisition sensor 2;
as shown in fig. 7 at flow 72, a fingerprint image to be registered is acquired;
as shown in fig. 7, in a flow 73, whether the pressing number threshold of the pressing type fingerprint input is reached is detected, and if the pressing number threshold is not reached, the flow returns to prompt the user to press the finger on the fingerprint acquisition window, namely, in a flow 71 shown in fig. 7; if the number of presses threshold is reached, a fingerprint template entry process is performed, flow 74 shown in FIG. 7;
as shown in fig. 7, in a flow 74, the fingerprint template inputting process processes the fingerprint image group to be registered obtained by the above-mentioned push type inputting and stores the processed fingerprint image group in the memory 3, thereby completing the fingerprint template inputting process 7 based on push type sampling.
The fingerprint template entering process 6 based on sliding type sampling and the fingerprint template entering process 7 based on pressing type sampling can be executed interchangeably, namely, the execution sequence of the fingerprint template entering process 6 based on sliding type sampling and the fingerprint template entering process 7 based on pressing type sampling can be adjusted according to the use condition without affecting the realization of the fingerprint template registering method capable of rapidly screening images based on sliding type sampling.
The composition and connection structure of each electronic component of the data processor 1 enable the fingerprint identification device to realize the fingerprint template registration method based on sliding sampling and capable of rapidly screening images according to the second embodiment of the application.
The application adopts a sliding type and pressing type combined sampling mode to draw the advantages of the sliding type and the pressing type, overcomes the defects of the sliding type and the pressing type by means of the screening process, and is more beneficial to improving user experience and fingerprint identification rate.
The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application, which are intended to be comprehended within the scope of the present application.
Claims (8)
1. A fingerprint template registration method based on sliding sampling and capable of rapidly screening images is based on a fingerprint identification device comprising a fingerprint acquisition sensor, a data processor and a memory; characterized in that the method comprises the following steps:
a fingerprint template entry process based on sliding sampling,
prompting a user to input a fingerprint template in a mode that a finger slides through a fingerprint acquisition window;
the fingerprint acquisition sensor acquires n fingerprint images;
the n fingerprint images are subjected to a screening process as follows,
a starting image process is selected and a starting image process is selected,
detecting the coincidence degree of two adjacent fingerprint images according to the image coincidence judging standard and the sequence from front to back of the fingerprint collecting time, and selecting an earlier fingerprint image in a first pair of adjacent fingerprint images which do not accord with the image coincidence judging standard as a starting image;
the process of terminating the image is selected,
selecting a first fingerprint image which accords with the full-press image standard as a termination image according to the full-press image standard and the sequence of the fingerprint acquisition time from back to front;
the course of the selection of the fingerprint image,
selecting a group of fingerprint images to be registered from a group of fingerprint images from the initial image to the final image according to the screening standard; in particular as follows,
in an alternative image group comprising sn fingerprint images acquired from a starting image to a terminating image, sequentially numbering each fingerprint image according to the sequence from front to back of the fingerprint acquisition time;
determining the effective image quantity valid_n according to the operation parameters of the fingerprint identification device;
if sn is less than or equal to valid_n, all sn fingerprint images are selected as fingerprint image groups to be registered;
if sn > valid_n, filtering and sampling, selecting the fingerprint image with serial number of sid from the candidate image group as the ith fingerprint image in the fingerprint image group to be registered,
sid＝round(i 0 +(i-1)×sf)，
wherein i is 0 Is the serial number of the starting image;
i is the serial number of each fingerprint image in the fingerprint image group to be registered, i is an independent variable, i is a natural number, and i is more than or equal to 1 and less than or equal to valid_n;
sil is the serial number of the finger print image in the alternative image group, sil is a dependent variable, sil is a natural number, and sil is more than or equal to 1 and less than or equal to sn;
sf is the screening sampling frequency, sf = sn/valid_n, sf is the floating point number;
round (x) is a function of rounding the variable x to obtain an integer;
the process of inputting the fingerprint template,
processing each fingerprint image group to be registered and storing the fingerprint image group into a memory;
detecting whether a sliding number threshold value of sliding fingerprint input is reached or not; if the sliding frequency threshold is not reached, returning to prompt the user to record the fingerprint template in a mode that the finger slides through the fingerprint acquisition window; and if the sliding times threshold is reached, terminating the fingerprint template recording process based on sliding sampling.
2. The fingerprint template registration method capable of rapidly screening images based on sliding sampling as claimed in claim 1, wherein the fingerprint template registration method is characterized by comprising the following steps:
the process of selecting the starting image is specifically as follows,
setting a correlation coefficient threshold of a local area of the image; the correlation coefficient of the local area of the image reflects the superposition degree of the two images;
sequentially selecting adjacent fingerprint images according to the sequence of the fingerprint acquisition time from front to back, carrying out the following image coincidence judging process,
selecting the same local area from the two adjacent fingerprint images, comparing the two local areas, judging the coincidence degree of the two local areas, and calculating the local area correlation coefficient of the two fingerprint images;
if the local area correlation coefficient is larger than the image local area correlation coefficient threshold, judging that fingerprint images where the two local areas are respectively located coincide, and conforming to an image coincidence judging standard; otherwise, judging that the fingerprint images of the two local areas are not overlapped and do not accord with the image overlapping judgment standard;
when a first pair of adjacent fingerprint images which do not meet the image coincidence judging standard are found, an earlier fingerprint image in the two adjacent fingerprint images is selected as a starting image.
3. The fingerprint template registration method capable of rapidly screening images based on sliding sampling as claimed in claim 1, wherein the fingerprint template registration method is characterized by comprising the following steps:
the process of selecting the termination image is specifically as follows,
setting a non-pressing area duty ratio threshold;
according to the sequence of the fingerprint collection time from the back to the front, carrying out a non-pressing area judging process on each fingerprint image, and calculating a pressing area and a non-pressing area of the fingerprint image and a non-pressing area occupation ratio of the area of the non-pressing area to the area of the fingerprint image according to the gray value of the fingerprint image;
comparing the non-pressing area occupation ratio of the fingerprint image with a non-pressing area occupation ratio threshold, and judging that the fingerprint image meets the full-pressing image standard if the non-pressing area occupation ratio is not larger than the non-pressing area occupation ratio threshold; if the non-pressing area occupation ratio is larger than the non-pressing area occupation ratio threshold, judging that the full-pressing image standard is not met;
when the first fingerprint image meeting the full-press image standard is found, the fingerprint image is selected as the termination image.
4. The fingerprint template registration method capable of rapidly screening images based on sliding sampling as claimed in claim 1, wherein the fingerprint template registration method is characterized by comprising the following steps:
the valid _ n number of valid images is determined according to the operating parameters of the fingerprint recognition device,
calculating the effective image quantity valid_n= (tl/ll-1)/r+1, wherein tl is the maximum total length empirical value of human finger abdomen, ll is the side length of a single square image acquired by the fingerprint acquisition sensor, and r is the image coincidence proportion coefficient, and r is more than or equal to 0.2 and less than or equal to 0.5.
5. The fingerprint template registration method capable of rapidly screening images based on sliding sampling as claimed in claim 1, wherein the fingerprint template registration method is characterized by comprising the following steps:
the screening process also includes a process that,
the process of establishing the image buffer area is carried out,
the number of valid _ n of valid pictures is calculated,
valid_n＝(tl/ll-1)/r+1，
wherein tl is the empirical value of the maximum total length of human finger abdomen,
ll is the side length of a single square image acquired by the fingerprint acquisition sensor,
r is an image coincidence proportion coefficient, and r is more than or equal to 0.2 and less than or equal to 0.5;
the number of stored images save _ n is calculated,
save_n＝q×valid_n，
wherein q is a distribution proportionality coefficient, and q is more than or equal to 1.2 and less than or equal to 1.5;
memory space for storing save_n fingerprint images is allocated in memory for the screening process.
6. The fingerprint template registration method capable of rapidly screening images based on slide sampling according to any one of claims 1 to 5, wherein:
also included is a fingerprint template entry process based on push sampling as follows,
prompting a user to press the fingerprint acquisition window with a finger;
acquiring a fingerprint image to be registered;
detecting whether the pressing frequency threshold value of the pressing type fingerprint input is reached, if the pressing frequency threshold value is not reached, returning to prompting the user to press the fingerprint acquisition window by the finger; if the pressing frequency threshold is reached, performing a fingerprint template input process;
the process of inputting the fingerprint template,
and processing the fingerprint image group to be registered obtained by the push type input and storing the fingerprint image group to be registered in a memory.
7. Fingerprint identification device based on fingerprint template is registered in slidingtype sampling and can filter image fast, its characterized in that:
the fingerprint acquisition device comprises a data processor, a fingerprint acquisition sensor and a memory, wherein the fingerprint acquisition sensor and the memory are electrically connected with the data processor;
the data processor comprises more than two electronic components, the composition and the connection structure of each electronic component enable the fingerprint identification device to complete the following fingerprint template registration process,
a fingerprint template entry process based on sliding sampling,
prompting a user to input a fingerprint template in a mode that a finger slides through a fingerprint acquisition window;
the fingerprint acquisition sensor acquires n fingerprint images;
the n fingerprint images are subjected to a screening process as follows,
a starting image process is selected and a starting image process is selected,
detecting the coincidence degree of two adjacent fingerprint images according to the image coincidence judging standard and the sequence from front to back of the fingerprint collecting time, and selecting an earlier fingerprint image in a first pair of adjacent fingerprint images which do not accord with the image coincidence judging standard as a starting image;
the process of terminating the image is selected,
selecting a first fingerprint image which accords with the full-press image standard as a termination image according to the full-press image standard and the sequence of the fingerprint acquisition time from back to front;
the process of selecting the image of the fingerprint,
selecting a group of fingerprint images to be registered from a group of fingerprint images from the initial image to the final image according to the screening standard; in particular as follows,
in an alternative image group comprising sn fingerprint images acquired from a starting image to a terminating image, sequentially numbering each fingerprint image according to the sequence from front to back of the fingerprint acquisition time;
determining the effective image quantity valid_n according to the operation parameters of the fingerprint identification device;
if sn is less than or equal to valid_n, all sn fingerprint images are selected as fingerprint image groups to be registered;
if sn > valid_n, filtering and sampling, selecting the fingerprint image with serial number of sid from the candidate image group as the ith fingerprint image in the fingerprint image group to be registered,
sid＝round(i 0 +(i-1)×sf)，
wherein i is 0 Is the serial number of the starting image;
i is the serial number of each fingerprint image in the fingerprint image group to be registered, i is an independent variable, i is a natural number, and i is more than or equal to 1 and less than or equal to valid_n;
sil is the serial number of the finger print image in the alternative image group, sil is the natural number, and sil is more than or equal to 1 and less than or equal to sn;
sf is the screening sampling frequency, sf = sn/valid_n, sf is the floating point number;
round (x) is a function of rounding the variable x to obtain an integer;
the process of inputting the fingerprint template,
processing each fingerprint image group to be registered and storing the fingerprint image group into a memory;
detecting whether a sliding number threshold value of sliding fingerprint input is reached or not; if the sliding times threshold is not reached, returning to the sliding type fingerprint input; and if the sliding times threshold is reached, terminating the fingerprint template recording process based on sliding sampling.
8. The fingerprint identification device capable of rapidly screening images based on a sliding type sampling registration fingerprint template according to claim 7, wherein:
the composition and connection structure of the electronic components of the data processor enable the fingerprint recognition device to enable the fingerprint template registration process to further comprise a fingerprint template registration process based on push type sampling,
prompting a user to press the fingerprint acquisition window with a finger;
acquiring a fingerprint image to be registered;
detecting whether the pressing frequency threshold value of the pressing type fingerprint input is reached, if the pressing frequency threshold value is not reached, returning to prompting the user to press the fingerprint acquisition window by the finger; if the pressing frequency threshold is reached, performing a fingerprint template input process;
the process of inputting the fingerprint template,
and processing the fingerprint image group to be registered obtained by the push type input and storing the fingerprint image group to be registered in a memory.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910105883.5A CN110020591B (en) | 2019-02-01 | 2019-02-01 | Fingerprint template registration method and fingerprint identification device based on sliding sampling |
| TW108129704A TWI733168B (en) | 2019-02-01 | 2019-08-20 | Fingerprint template registration method based on sliding sampling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910105883.5A CN110020591B (en) | 2019-02-01 | 2019-02-01 | Fingerprint template registration method and fingerprint identification device based on sliding sampling |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110020591A CN110020591A (en) | 2019-07-16 |
| CN110020591B true CN110020591B (en) | 2023-11-14 |
Family
ID=67188923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910105883.5A Active CN110020591B (en) | 2019-02-01 | 2019-02-01 | Fingerprint template registration method and fingerprint identification device based on sliding sampling |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110020591B (en) |
| TW (1) | TWI733168B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580387A (en) * | 2019-09-27 | 2021-03-30 | 北京小米移动软件有限公司 | Fingerprint input method and device and electronic equipment |
| CN110751105B (en) * | 2019-10-22 | 2022-04-08 | 珠海格力电器股份有限公司 | Finger image acquisition method and device and storage medium |
| EP4143740A4 (en) * | 2020-04-30 | 2024-05-22 | Fingerprint Cards Anacatum IP AB | Method and system for enrolling a fingerprint |
| CN114004744B (en) * | 2021-10-15 | 2023-04-28 | 深圳市亚略特科技股份有限公司 | Fingerprint splicing method and device, electronic equipment and medium |
| CN114373196B (en) * | 2021-12-31 | 2023-09-19 | 天津极豪科技有限公司 | Effective acquisition area determination method, program product, storage medium and electronic device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105373786A (en) * | 2015-11-30 | 2016-03-02 | 东莞酷派软件技术有限公司 | Fingerprint acquisition method, fingerprint acquisition device and electronic device |
| CN105814585A (en) * | 2016-03-17 | 2016-07-27 | 深圳信炜科技有限公司 | Fingerprint processing method and device, fingerprint recognition system, and electronic equipment |
| CN106778461A (en) * | 2016-03-17 | 2017-05-31 | 深圳信炜科技有限公司 | Finger prints processing method, finger prints processing device, fingerprint recognition system and electronic equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105447436B (en) * | 2014-12-19 | 2017-08-04 | 比亚迪股份有限公司 | Fingerprint recognition system and fingerprint identification method and electronic equipment |
| CN107808084A (en) * | 2017-10-18 | 2018-03-16 | 维沃移动通信有限公司 | A kind of touch operation method and mobile terminal |
| CN109241957B (en) * | 2018-11-19 | 2020-12-11 | Oppo广东移动通信有限公司 | Electronic device, fingerprint acquisition method and device, storage medium and mobile terminal |
-
2019
- 2019-02-01 CN CN201910105883.5A patent/CN110020591B/en active Active
- 2019-08-20 TW TW108129704A patent/TWI733168B/en active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105373786A (en) * | 2015-11-30 | 2016-03-02 | 东莞酷派软件技术有限公司 | Fingerprint acquisition method, fingerprint acquisition device and electronic device |
| CN105814585A (en) * | 2016-03-17 | 2016-07-27 | 深圳信炜科技有限公司 | Fingerprint processing method and device, fingerprint recognition system, and electronic equipment |
| CN106778461A (en) * | 2016-03-17 | 2017-05-31 | 深圳信炜科技有限公司 | Finger prints processing method, finger prints processing device, fingerprint recognition system and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110020591A (en) | 2019-07-16 |
| TWI733168B (en) | 2021-07-11 |
| TW201945981A (en) | 2019-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110020591B (en) | Fingerprint template registration method and fingerprint identification device based on sliding sampling | |
| CN111626371B (en) | Image classification method, device, equipment and readable storage medium | |
| CN107301389B (en) | Method, device and terminal for identifying user gender based on face features | |
| WO2017008349A1 (en) | Fingerprint recognition method and device | |
| CN109800731B (en) | Fingerprint input method and related device | |
| WO2004079658A1 (en) | Biological image correlation device and correlation method thereof | |
| CN109690563B (en) | Fingerprint registration method, terminal and computer-readable storage medium | |
| WO2020156033A1 (en) | Fingerprint verification method and related apparatus | |
| CN110516672A (en) | Card card information identifying method, device and terminal | |
| JPH0660167A (en) | Individual identification device | |
| RU2234734C1 (en) | Method for multi-stage analysis of information of bitmap image | |
| CN112509586A (en) | Method and device for recognizing voice print of telephone channel | |
| CN112132797A (en) | Short video quality screening method | |
| CN117392404A (en) | Method and system for improving image detection speed | |
| CN108260012A (en) | Electronic device, video playing control method and related product | |
| CN111368715B (en) | Fingerprint anti-counterfeiting method, device and equipment | |
| CN110858294B (en) | Fingerprint identification method for improving fingerprint identification rate and fingerprint identification chip | |
| CN109858348B (en) | Method and system for acquiring ten-finger fingerprints based on thread control | |
| CN112580462A (en) | Feature point selection method, terminal and storage medium | |
| JP5395795B2 (en) | Image collation apparatus and image collation method | |
| JP2003030660A (en) | Fingerprint collation device and fingerprint collation method | |
| CN110895571A (en) | Dust removal platform based on dust concentration detection | |
| KR20190129351A (en) | Apparatus and method for selecting image of face recognition | |
| JP2575676B2 (en) | Automatic Matching Point Tracking Method for Fingerprint Matching | |
| WO2024125312A1 (en) | Picture quality recognition method, apparatus and device, and storage medium and product |
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 |