WO2020237481A1 - 反色区域的确定方法、指纹芯片及电子设备 - Google Patents

反色区域的确定方法、指纹芯片及电子设备 Download PDF

Info

Publication number
WO2020237481A1
WO2020237481A1 PCT/CN2019/088650 CN2019088650W WO2020237481A1 WO 2020237481 A1 WO2020237481 A1 WO 2020237481A1 CN 2019088650 W CN2019088650 W CN 2019088650W WO 2020237481 A1 WO2020237481 A1 WO 2020237481A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
fingerprint
image blocks
matched
blocks
Prior art date
Application number
PCT/CN2019/088650
Other languages
English (en)
French (fr)
Inventor
徐波
Original Assignee
深圳市汇顶科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市汇顶科技股份有限公司 filed Critical 深圳市汇顶科技股份有限公司
Priority to PCT/CN2019/088650 priority Critical patent/WO2020237481A1/zh
Priority to CN201980000858.9A priority patent/CN110383287B/zh
Publication of WO2020237481A1 publication Critical patent/WO2020237481A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1347—Preprocessing; Feature extraction
    • 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

Definitions

  • the embodiments of the present application relate to the field of biometric identification technology, and in particular to a method for determining an inverted color area, a fingerprint chip, and an electronic device.
  • fingerprints are unique, they can be used for identity verification to meet the security and confidentiality requirements of different application scenarios.
  • fingerprint recognition technology has been widely used in various fields for identity authentication to realize various functions, such as payment, unlocking, customs clearance inspection, attendance, and security authentication.
  • the fingerprint acquisition module collects the fingerprint image and matches it with the stored fingerprint template to complete the fingerprint identification.
  • the darker lines correspond to the ridges on the fingerprint of the finger
  • the brighter lines correspond to the valleys on the fingerprint of the finger.
  • the valley feature of the finger is often opposite to the ridge feature, that is, it should be a ridge feature, but it does appear as a valley feature on the fingerprint image, or it is originally a valley feature, but it does appear to be a valley feature. Ridge characteristics, this phenomenon is also known as the reverse color in the industry. If the fingerprint image has an inverted color, it will lead to recognition failure, and further lead to a false rejection rate (FRR).
  • FRR false rejection rate
  • one of the technical problems solved by the embodiments of the present invention is to provide a method for determining an inverted color area, a fingerprint chip, and an electronic device to overcome the above-mentioned defects in the prior art.
  • the embodiment of the present application provides a method for determining an inverted color area, which includes:
  • Segmenting the target fingerprint image to obtain a number of image blocks, and performing preliminary matching on each of the image blocks with the fingerprint template to determine the image blocks whose preliminary matching is unsuccessful;
  • segmenting the target fingerprint image to obtain several image blocks includes: segmenting the target fingerprint image based on the segmentation window or the gray value or the consistency of the fingerprint pattern direction Get several image blocks.
  • the target fingerprint image is segmented to obtain a number of image blocks, and each of the image blocks is matched with the fingerprint template to determine the fingerprint template.
  • the image block that does not match includes: segmenting the original target fingerprint image to obtain a number of original image blocks, and preprocessing each of the original image blocks to obtain a corresponding preprocessed image block, the preprocessed image
  • the blocks are respectively preliminarily matched with the fingerprint template to determine the pre-processed image blocks that are unsuccessfully preliminarily matched with the fingerprint template.
  • determining the inverted color area on the target fingerprint image with the opposite valley and ridge feature according to the image block that is successfully matched again includes: The coordinates on the above and the size of the image block determine the inverted color area with the opposite valley and ridge feature on the target fingerprint image.
  • it further includes: preprocessing the original target fingerprint image to obtain the preprocessed target fingerprint image; correspondingly, segmenting the target fingerprint image to obtain several image blocks, and Each of the image blocks is matched with a fingerprint template to determine the image blocks that do not match the fingerprint template, including: segmenting the preprocessing target fingerprint image to obtain several preprocessing image blocks, Each pre-processed image block is matched with a fingerprint template to determine the pre-processed image block that does not match the fingerprint template.
  • performing color inversion processing on the image blocks that do not match the fingerprint template includes: performing color inversion processing on all the image blocks that do not initially match the fingerprint template Overall inversion processing, or individual inversion processing is performed on each image block that does not initially match the fingerprint template.
  • the preprocessed image block is a grayscale image block or a binarized image block.
  • performing color inversion processing on the image blocks that do not match the fingerprint template includes: performing color inversion processing on all the image blocks that do not initially match the fingerprint template Overall inversion processing, and when each of the image blocks after the overall inversion processing fails to match the fingerprint template, individually inverting each image block that does not initially match the fingerprint template deal with.
  • the method further includes: marking the image block that is unsuccessfully matched again as to be processed.
  • the method further includes: determining the image block that is initially matched successfully; judging the image block that is successfully matched again and the image block that is primarily matched Whether the target fingerprint image is matched successfully.
  • determining whether the target fingerprint image is successfully matched based on the image blocks that are successfully matched again and the image blocks that are initially matched successfully includes: determining that the target fingerprint image is successfully matched again The sum of the image blocks and the image blocks that are initially matched successfully, the proportion of the sum to the total number of image blocks obtained by segmentation is counted, and the target fingerprint image is judged whether the target fingerprint image matches according to the proportion and the set proportion threshold success.
  • judging whether the target fingerprint image is successfully matched based on the ratio and a set ratio threshold includes: if the ratio is greater than the set ratio threshold, determining The target fingerprint image is matched successfully; otherwise, the image block identified as the to-be-processed image block is enhanced to obtain an enhanced image block, the enhanced image block is matched with the fingerprint template, and the enhanced image block that is successfully matched is determined, and the initial The sum of the image blocks that are successfully matched and the image blocks that are successfully matched again, and the proportion of the sum to the total number of image blocks obtained by segmentation is counted again, if the counted proportion is greater than the set proportion threshold , It is determined that the target fingerprint image matching is successful, otherwise it is determined that the target fingerprint image matching is unsuccessful.
  • An embodiment of the present application also provides a fingerprint chip, which includes a processor, and the processor is configured with:
  • the segmentation module is used to segment the target fingerprint image to obtain a number of image blocks, and perform preliminary matching of each of the image blocks with the fingerprint template to determine the image blocks whose preliminary matching is unsuccessful;
  • the color inversion module is configured to perform color inversion processing on the image blocks whose preliminary matching is unsuccessful, and re-match each image block with the fingerprint template after the color inversion processing;
  • the detection module is used to determine the inverted color area on the target fingerprint image according to the image block that is successfully matched again.
  • An embodiment of the present application also provides an electronic device, which includes the fingerprint chip described in any of the embodiments of the present application.
  • image blocks are obtained by segmenting the target fingerprint image, and each of the image blocks is initially matched with the fingerprint template to determine the unsuccessful preliminary matching.
  • Image block invert the color of the image block that is unsuccessful in the preliminary matching, and re-match each image block with the fingerprint template after the inverted color process; determine the image block that is successfully matched again
  • the inverted color area on the target fingerprint image with the opposite valley and ridge feature can effectively identify the inverted color area of the fingerprint image.
  • the rejection rate can be effectively reduced.
  • FIG. 1 is a schematic flow chart of a method for determining an inverted color area in Embodiment 1 of this application;
  • FIG. 2 is a schematic flowchart of a method for determining an inverted color area in Embodiment 2 of this application;
  • FIG. 3 is a schematic flowchart of a method for determining an inverted color area in Embodiment 3 of the application;
  • FIG. 5 is a schematic flowchart of a method for determining an inverted color area in Embodiment 5 of this application;
  • FIG. 6 is a schematic diagram of the structure of the fingerprint chip in the sixth embodiment of the application.
  • image blocks are obtained by segmenting the target fingerprint image, and each of the image blocks is initially matched with the fingerprint template to determine the unsuccessful preliminary matching.
  • Image block invert the color of the image block that is unsuccessful in the preliminary matching, and re-match each image block with the fingerprint template after the inverted color process; determine the image block that is successfully matched again
  • the inverted color area on the target fingerprint image with the opposite valley and ridge feature can effectively identify the inverted color area of the fingerprint image.
  • the rejection rate can be effectively reduced.
  • FIG. 1 is a schematic flowchart of the method for determining the inverted color area in Embodiment 1 of the application; as shown in FIG. 1, it includes:
  • S101 Segment a target fingerprint image to obtain a number of image blocks, and perform preliminary matching on each of the image blocks with a fingerprint template to determine the image blocks whose preliminary matching is unsuccessful.
  • the process of matching the image block with the fingerprint template can actually be understood as matching the fingerprint features on the image block with the fingerprint template. If the matching degree exceeds the set matching degree threshold, the matching is considered successful, otherwise it is considered matching unsuccessful. In fact, each image block can be regarded as a fingerprint image to be matched.
  • the target fingerprint image when the target fingerprint image is segmented to obtain several image blocks in step S101, the target fingerprint image can be segmented to obtain several image blocks based on the segmentation window or gray value.
  • the target fingerprint image may specifically refer to a fingerprint image obtained by separating the foreground and background of the original image of the target fingerprint, and segmenting is directly based on the fingerprint image to obtain several image blocks.
  • the fingerprint image obtained by separating the foreground and the background can actually obtain an effective fingerprint area, which can further improve the accuracy of subsequent matching.
  • a split window such as a rectangular split window
  • a split window can be used to partition the fingerprint image that has been separated from the foreground and the background to obtain several rectangular image blocks, each rectangular image
  • the block size can be the same or different.
  • each image block has a corresponding size parameter and a coordinate position on the entire fingerprint image.
  • the segmentation of image blocks can be performed by counting the gray values of fingerprint graphics. Further, on the fingerprint image with the separation of the foreground and the background, a reference pixel is selected for the effective fingerprint area on the fingerprint image, and based on the reference pixel, a number of pixels in the neighborhood are selected.
  • Statistics include The reference pixel and the pixel gray average value of the pixel area surrounded by several pixels in the neighborhood of the reference pixel, determine whether the pixel gray average value is approximately equal to the set gray average threshold, and if so, then Divide the reference pixel and several pixels in the same image block, otherwise, expand the neighborhood of the reference pixel to increase the number of pixels until it includes the reference pixel and several pixels in the neighborhood of the reference pixel The pixel gray average value of the enclosed pixel area is approximately equal to the set gray average threshold value.
  • an edge pixel of the image block determined last time is selected as the new reference pixel, and based on the new reference pixel, a number of pixels in the neighborhood of the new reference pixel are selected (the number of pixels is not (Included in the obtained image block), statistics include the new reference pixel and the pixel gray average value of the pixel area surrounded by several pixels in the neighborhood of the new reference pixel, and determine whether the pixel gray average value Approximately equal to the set gray average threshold.
  • the average pixel gray value of the pixel point area surrounded by a plurality of pixels in the neighborhood of the reference pixel point and the reference pixel point is approximately equal to the set gray average value threshold.
  • the gray mean value represents the degree of lightness and darkness
  • the size of the gray value variance represents the contrast
  • the gray mean value represents the contrast of the current block
  • the gray variance represents the contrast of the current block
  • Black and white are more distinct, otherwise the boundary between black and white is more blurred. Therefore, when the statistical gray value is approximately equal to the gray value threshold, and the gray value variance is approximately equal to the gray value variance threshold, the image block segmentation method that meets the two conditions, the obtained image block is in contrast and black and white clarity.
  • the above is relatively uniform, so that each image block has as much effective fingerprint feature data as possible, thereby ensuring the accuracy of subsequent matching.
  • S102 Perform color inversion processing on the image blocks that are unsuccessful in the preliminary matching, and re-match each image block with the fingerprint template after the color inversion processing;
  • the inverted color area is actually due to the valley ridge feature presenting the opposite in the image performance, that is, as mentioned above, it should belong to the ridge feature, but it does appear as the valley feature on the fingerprint image, or it is originally It belongs to valley characteristics, but it does appear as ridge characteristics. Therefore, theoretically, those image blocks that are unsuccessfully matched in step S101 are likely to have inverted color areas. For this reason, after the inverted color processing is performed on these image blocks, the ridge feature on the image corresponds to the fingerprint The ridge and valley features of the corresponding fingerprints correspond to the valleys in the fingerprint. Then when it is matched with the fingerprint template, it should be matched successfully, or the probability of successful matching is very high.
  • the inverted image blocks are matched with the fingerprint template again, so as to relatively accurately determine that those image blocks are image blocks with inverted colors.
  • performing inverted color processing on the image blocks whose initial matching is unsuccessful will not increase the false acceptance rate (False Accept Rate, FAR for short).
  • the technical process of re-matching is similar to the above-mentioned initial matching process, which is essentially a process of matching the fingerprint data on the image block with the fingerprint template to determine the degree of matching.
  • the directly obtained image block is also based on gray.
  • the inverse color processing is performed based on the gray value. Specifically, the gray value of each pixel in the image block is subtracted from the highest gray level to realize the color inversion process.
  • S103 Determine, according to the image block that is successfully matched again, an inverted color area on the target fingerprint image that has the opposite valley and ridge feature.
  • the valley ridge feature based on the inverted color is processed by the inverse color, and theoretically corresponds to the correct valley ridge feature. For this reason, if other factors other than the inverted color are ignored, the theory should be matched again. It should be able to match successfully. Therefore, in this embodiment, according to the rematching process in step S103, the image blocks that are successfully matched again are determined, which indicates that there is an inversion phenomenon on the image blocks of these image blocks (corresponding to before the inversion process).
  • each image block has a coordinate value and a block size value after the image block is divided, it can be known that there is a reverse color area on the target fingerprint image by combining these coordinate values and the size of the image block That is, according to the coordinates of the successfully matched image block on the target fingerprint image and the size of the image block, the inverted color area on the target fingerprint image with the opposite valley and ridge feature is determined.
  • these anti-color areas are not necessarily connected areas, but may actually be scattered multiple areas.
  • Figure 2 is a schematic flow chart of the method for determining the inverted color area in the second embodiment of the application; as shown in Figure 2, it includes:
  • S201 Segment the original target fingerprint image to obtain a number of original image blocks, and perform preprocessing on each of the original image blocks to obtain a corresponding preprocessed image block;
  • Figure 1 is to segment the fingerprint image after the foreground and background are separated from the original target image.
  • the original target fingerprint image is actually separated before the foreground and background. Perform segmentation on the above, and then preprocess the obtained original image block to obtain the preprocessed image block.
  • the preprocessing includes at least one or any combination of gain, denoising, foreground and background separation, image normalization, image enhancement, and binarization.
  • the purpose of gain and de-noising here is to make the fingerprint feature preliminary optimization in the performance of the image.
  • the separation of foreground and background is to remove the background as mentioned above and to determine the effective fingerprint area in the foreground. Due to the inconsistency of the pressing force, the original fingerprint image collected by the fingerprint acquisition module will be biased.
  • the ridge feature color in the middle part is relatively heavy, and the ridge feature on the two edge sides is thin and unclear. Therefore, the image normalization is used to make The image is as consistent as possible in color brightness and contrast, so that the outline of the image is clearly visible.
  • all image blocks can be preprocessed in batches at the same time, or each image block can be preprocessed separately.
  • the specific technical processing for segmentation can be based on the segmentation window or gray value in the embodiment shown in FIG. 1, of course, it can also be based on the consistency of the fingerprint ridge direction.
  • the principle of consistency in the direction of fingerprint lines is roughly as follows: On a binary fingerprint image, the pixel points are projected along the direction of the line, and the pixel average shows a significant sinusoidal change, and the pixel is projected in the direction perpendicular to the line. The pixel average is a relatively flat straight line.
  • the pre-processed image blocks are respectively preliminarily matched with the fingerprint template to determine the pre-processed image blocks that are not successfully pre-matched with the fingerprint template.
  • S203 Perform color inversion processing on the pre-processed image blocks that are unsuccessful in the preliminary matching, and re-match each pre-processed image block after the color inversion processing with the fingerprint template;
  • step S203 when the image blocks that do not match the fingerprint template are inverted in step S203, all the image blocks that do not match the fingerprint template preliminarily may be inverted as a whole. Alternatively, it is also possible to perform individual inversion processing on each of the image blocks that do not initially match the fingerprint template.
  • the difference from the above-mentioned embodiment is that in this embodiment, there is a binary fingerprint image for segmentation. Therefore, the obtained image block is actually a binary image, that is, the gray value of the pixel is not 1 or 0. , Non-zero or 1, therefore, the inverse color processing is relatively simple, that is, the gray value of 1 becomes 0, and the gray value of 0 becomes 1.
  • each image block has a corresponding size parameter and a coordinate position on the entire fingerprint image, when inverting the color, the corresponding image block can be accurately found through the coordinate position and size.
  • the first matching and the second matching are similar to the first embodiment described above.
  • the method for determining the inverted color area is similar to that of the first embodiment above. Further, after the inverted color area is determined, it can be directly labeled on the binary fingerprint image.
  • Figure 3 is a schematic flow chart of the method for determining the inverted color area in the third embodiment of the application; as shown in Figure 3, it includes:
  • S301 Perform preprocessing on the original target fingerprint image to obtain the preprocessed target fingerprint image
  • pre-processing is performed before segmentation.
  • the pre-processing can include but not limited to gain, denoising, foreground and background separation, image normalization, image enhancement, binarization, etc. At least one or any combination of them, therefore, the final pre-processed target fingerprint image is actually a whole binary fingerprint image.
  • the method of the first or second embodiment above can be specifically adopted to perform segmentation processing on the pre-processed target fingerprint image to obtain multiple pre-processed image blocks. Further, these preprocessed image blocks may or may not overlap.
  • S303 Perform color inversion processing on the pre-processed image blocks that are unsuccessful in the preliminary matching, and re-match each pre-processed image block after the color inversion processing with the fingerprint template;
  • step S303 when the image block that does not match the fingerprint template is inverted in step S303, all the image blocks that do not initially match the fingerprint template may be subjected to overall inverted color processing. Alternatively, separate color inversion processing is performed on each image block that does not initially match the fingerprint template.
  • the specific color reversal processing can refer to the above-mentioned processing method for the binary fingerprint image, that is, the gray value of the pixel on the preprocessed image block is changed from 1 to 0, and the gray value of the pixel is changed from 0 to 1.
  • step S304 please refer to the first or second embodiment above for step S304.
  • FIG. 4 is a schematic flow chart of the method for determining the inverted color area in the fourth embodiment of the application; in this embodiment, the difference from the above-mentioned embodiment 3 is that when performing inverted color processing, it is necessary to perform individual inverted colors and overall inverted colors.
  • the requirements for color processing for this reason, in this embodiment, it includes:
  • S401 Preprocess the original target fingerprint image to obtain the preprocessed target fingerprint image
  • S402. Segment the pre-processed target fingerprint image to obtain several pre-processed image blocks, and match each pre-processed image block with a fingerprint template to determine the pre-processed image block that does not match the fingerprint template. .
  • S403 Perform overall inversion processing on all the image blocks that do not initially match the fingerprint template, and re-match each preprocessed image block with the fingerprint template after the overall inversion processing;
  • steps S401, S402, and S403 please refer to the description of the foregoing embodiment.
  • S405 Mark the pre-processed image block that is unsuccessfully matched again as to be processed.
  • the difference from the above-mentioned embodiment is that the overall inversion processing is performed on all the image blocks that do not match initially, and then the matching is performed again. If the matching is unsuccessful again, the matching will be unsuccessful again.
  • the image block undergoes a separate color inversion process, and then is matched again to improve the accuracy of the color inversion area judgment.
  • step S405 the pre-processed image blocks that are unsuccessfully matched again are marked as to be processed, which is mainly because the ultimate purpose of determining the inverted color area is to identify the target value.
  • the image block that is successfully matched again and the image block that is initially matched successfully can be determined that the target fingerprint image is successfully matched.
  • it can be regarded as a preprocessed image block that is identified as a preprocessing image block that matches the target fingerprint image. The result of the judgment has little or no impact.
  • FIG. 5 is a schematic flow chart of the method for determining the inverted color area in the fifth embodiment of the application; in this embodiment, it can actually be understood how to further determine whether the fingerprint image is matched successfully after the inverted area is determined. As shown in Figure 5, it includes:
  • S501 Preprocess the original target fingerprint image to obtain the preprocessed target fingerprint image
  • S503 Perform overall inversion processing on all the image blocks that do not initially match the fingerprint template, and re-match each pre-processed image block with the fingerprint template after the overall inversion processing;
  • S504A If the matching is successful, determine the inverted color area on the target fingerprint image with the opposite valley and ridge feature based on the pre-processed image block that is successfully matched again.
  • S505 Mark the pre-processed image block that is unsuccessfully matched again as to be processed.
  • S506 Determine the image block that is initially matched successfully; based on the image block that is successfully matched again and the image block that is primarily matched, determine whether the target fingerprint image is matched successfully.
  • step S507A is executed; otherwise, step S507B is executed.
  • S507B Perform enhancement processing on the image block identified as to-be-processed to obtain an enhanced image block, and match the enhanced image block with the fingerprint template;
  • S508 Determine whether the target fingerprint image is successfully matched according to the enhanced image block that is successfully matched, the image block that is initially successfully matched, and the image block that is successfully matched again.
  • step S503 it is determined whether the target fingerprint image is matched successfully. For example, specifically, determining the sum of the image blocks that are successfully matched again and the image blocks that are initially successfully matched, and the proportion of the sum to the total number of image blocks obtained by segmentation is calculated according to the proportion and setting The ratio threshold of is judged whether the target fingerprint image is matched successfully. If the ratio is greater than or equal to the set ratio threshold, it is determined that the target fingerprint image matching is successful; otherwise, it is determined that the target fingerprint image matching is unsuccessful. Therefore, in order to improve the accuracy of judging whether the target fingerprint image is matched successfully, it is further combined with the preprocessed image block identified as to be processed to further determine whether the target fingerprint image is matched successfully.
  • the sum of the enhanced image blocks that are successfully matched, the image blocks that are successfully matched initially, and the image blocks that are successfully matched again is determined, and the total is counted again.
  • FIG. 6 is a schematic structural diagram of a fingerprint chip in Embodiment 6 of this application; as shown in FIG. 6, it includes a processor, and the processor is configured with:
  • the segmentation module 601 is configured to segment the target fingerprint image to obtain several image blocks, and perform preliminary matching of each of the image blocks with the fingerprint template to determine the image blocks whose preliminary matching is unsuccessful;
  • the color inversion module 602 is configured to perform color inversion processing on the image blocks whose preliminary matching is unsuccessful, and re-match each image block with the fingerprint template after the color inversion processing;
  • the detection module 603 is configured to determine the inverted color area on the target fingerprint image according to the image block that is successfully matched again.
  • An embodiment of the present application also provides an electronic device, which includes the fingerprint chip described in any of the embodiments of the present application.
  • This embodiment also provides an electronic device, which includes the fingerprint identification device in the foregoing embodiment.
  • These electronic devices include but are not limited to:
  • Mobile communication equipment This type of equipment is characterized by mobile communication functions, and its main goal is to provide voice and data communications.
  • Such terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.
  • Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has calculation and processing functions, and generally also has mobile Internet features.
  • Such terminals include: PDA, MID and UMPC devices, such as iPad.
  • Portable entertainment equipment This type of equipment can display and play multimedia content.
  • Such devices include: audio, video players (such as iPod), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.
  • a programmable logic device Programmable Logic Device, PLD
  • FPGA Field Programmable Gate Array
  • HDL Hardware Description Language
  • ABEL Advanced Boolean Expression Language
  • AHDL Altera Hardware Description Language
  • HDCal JHDL
  • Lava Lava
  • Lola MyHDL
  • PALASM RHDL
  • VHDL Very-High-Speed Integrated Circuit Hardware Description Language
  • Verilog Verilog
  • the controller can be implemented in any suitable manner.
  • the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program codes (such as software or firmware) executable by the (micro)processor. , Logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers and embedded microcontrollers.
  • controllers include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicon Labs C8051F320, the memory controller can also be implemented as a part of the memory control logic.
  • controller in addition to implementing the controller in a purely computer-readable program code manner, it is entirely possible to program the method steps to make the controller use logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded The same function can be realized in the form of a microcontroller, etc. Therefore, such a controller can be regarded as a hardware component, and the devices included in it for implementing various functions can also be regarded as a structure within the hardware component. Or even, the device for realizing various functions can be regarded as both a software module for realizing the method and a structure within a hardware component.
  • a typical implementation device is a computer.
  • the computer may be, for example, a personal computer, a laptop computer, a cell phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or Any combination of these devices.
  • the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
  • a computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment.
  • the instructions provide steps for implementing functions specified in a flow or multiple flows in the flowchart and/or a block or multiple blocks in the block diagram.
  • the computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory.
  • processors CPU
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-permanent memory in computer readable media, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer readable media.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash memory
  • Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology.
  • the information can be computer-readable instructions, data structures, program modules, or other data.
  • Examples of computer storage media include: but not limited to phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.
  • this application can be provided as methods, systems, or computer program products. Therefore, this application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • This application may be described in the general context of computer-executable instructions executed by a computer, such as program modules.
  • program modules include routines, programs, objects, components, data structures, etc. that perform specific transactions or implement specific abstract data types.
  • This application can also be practiced in distributed computing environments. In these distributed computing environments, remote processing devices connected through a communication network execute transactions.
  • program modules can be located in local and remote computer storage media including storage devices.

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Collating Specific Patterns (AREA)
  • Image Analysis (AREA)

Abstract

一种反色区域的确定方法、指纹芯片及电子设备，反色区域的确定方法包括：对目标指纹图像进行切分得到若干个图像块，并将每个所述图像块分别与指纹模板进行初步匹配，以确定出初步匹配不成功的所述图像块(S101)；对初步匹配不成功的所述图像块进行反色处理，并将反色处理后每个所述图像块与所述指纹模板进行再次匹配(S102)；根据再次匹配成功的图像块，确定所述目标指纹图像上谷脊特征相反的反色区域(S103)。从而可有效地识别出指纹图像的反色区域，在指纹识别时，可以有效降低拒识率。

Description

反色区域的确定方法、指纹芯片及电子设备 技术领域
本申请实施例涉及生物特征识别技术领域，尤其涉及一种反色区域的确定方法、指纹芯片及电子设备。
背景技术
由于指纹具有独一无二性，因此可用于身份验证等，以满足不同应用场景的安全、保密要求。如今指纹识别技术已广泛应用在各领域进行身份认证，以实现各种功能，常见的如支付、解锁、过关检测、考勤、安全认证等。目前的应用场景下，在产品实现指纹识别方案时，指纹采集模块采集指纹图像，并与存储的指纹模板进行匹配，从而完成指纹识别。
但是，现有技术中，指纹采集模块采集的指纹图像上，较暗的线对应手指指纹上的脊线(ridges)，较亮的线对应手指指纹上的谷线(valleys)，但是，实际上在采集到的指纹图像上，往往会出现手指谷特征和脊特征相反，即本来应该属于脊特征的，但是在指纹图像上确表现为谷特征，或者本来属于谷特征的，但是在确表现为脊特征，此种现象业界又称之反色。如果指纹图像存在反色，则由此会导致识别失败，进一步导致拒识率(False rejection rate，简称FRR)。
发明内容
有鉴于此，本发明实施例所解决的技术问题之一在于提供一种反色区域的确定方法、指纹芯片及电子设备，用以克服现有技术中的上述缺陷。
本申请实施例提供了一种反色区域的确定方法，其包括：
对目标指纹图像进行切分得到若干个图像块，并将每个所述图像块分别与指纹模板进行初步匹配，以确定出初步匹配不成功的所述图像块；
对初步匹配不成功的所述图像块进行反色处理，并将反色处理后每个所述图像块与所述指纹模板进行再次匹配；
根据再次匹配成功的图像块，确定所述目标指纹图像上谷脊特征相反的反色区域。
可选地，在本申请的任一实施例中，对目标指纹图像进行切分得到若 干个图像块，包括：基于分割视窗或者灰度值或者指纹纹路方向一致性，对目标指纹图像进行切分得到若干个图像块。
可选地，在本申请的任一实施例中，对目标指纹图像进行切分得到若干个图像块，并将每个所述图像块分别与指纹模板进行匹配，以确定出与所述指纹模板不匹配的所述图像块，包括：对原始目标指纹图像进行切分得到若干个原始图像块，并对每个所述原始图像块进行预处理得到对应的预处理图像块，所述预处理图像块分别与所述指纹模板进行初步匹配，以确定出与所述指纹模板初步匹配不成功的所述预处理图像块。
可选地，在本申请的任一实施例中，根据再次匹配成功的图像块，确定所述目标指纹图像上谷脊特征相反的反色区域，包括：根据再次匹配成功的图像块在目标指纹图像上的坐标以及图像块的大小，确定所述目标指纹图像上谷脊特征相反的反色区域。
可选地，在本申请的任一实施例中，还包括：对原始目标指纹图像进行预处理得到预处理目标指纹图像；对应地，对目标指纹图像进行切分得到若干个图像块，并将每个所述图像块分别与指纹模板进行匹配，以确定出与所述指纹模板不匹配的所述图像块，包括：对预处理目标指纹图像进行切分得到若干个预处理图像块，将每个预处理图像块分别与指纹模板进行匹配，以确定出与所述指纹模板不匹配的所述预处理图像块。
可选地，在本申请的任一实施例中，对与所述指纹模板不匹配的所述图像块进行反色处理，包括：对与所述指纹模板初步不匹配的所有所述图像块进行整体反色处理，或者，对与所述指纹模板初步不匹配的每个所述图像块进行单独反色处理。
可选地，在本申请的任一实施例中，所述预处理图像块为灰度图像块或者二值化图像块。
可选地，在本申请的任一实施例中，对与所述指纹模板不匹配的所述图像块进行反色处理，包括：对与所述指纹模板初步不匹配的所有所述图像块进行整体反色处理，并在经过整体反色处理后的每个所述图像块与所述指纹模板匹配不成功时，对与所述指纹模板初步不匹配的每个所述图像块进行单独反色处理。
可选地，在本申请的任一实施例中，还包括：将再次匹配不成功的图像块标识为待处理。
可选地，在本申请的任一实施例中，还包括：确定出初步匹配成功的 所述图像块；根据再次匹配成功的所述图像块以及初步匹配成功的所述图像块，判断所述目标指纹图像是否匹配成功。
可选地，在本申请的任一实施例中，根据再次匹配成功的图像块以及初步匹配成功的所述图像块，判断所述目标指纹图像是否匹配成功，包括：确定再次匹配成功的所述图像块以及初步匹配成功的所述图像块的总和，统计所述总和占切分得到的图像块的总数量的比例，根据所述比例与设定的比例门限，判断所述目标指纹图像是否匹配成功。
可选地，在本申请的任一实施例中，根据所述比例与设定的比例门限，判断所述目标指纹图像是否匹配成功，包括：若所述比例大于设定的比例门限，判定所述目标指纹图像匹配成功；否则，将标识为待处理的图像块进行增强处理得到增强图像块，将所述增强图像块与所述指纹模板进行匹配，确定匹配成功的所述增强图像块、初步匹配成功的所述图像块、再次匹配成功的所述图像块的总和，再次统计所述总和占切分得到的图像块的总数量的比例，若所述再次统计的比例大于设定的比例门限，则判定所述目标指纹图像匹配成功，否则判定所述目标指纹图像匹配不成功。
本申请实施例还提供一种指纹芯片，其包括处理器，所述处理器上配置有：
切分模块，用于对目标指纹图像进行切分得到若干个图像块，并将每个所述图像块分别与指纹模板进行初步匹配，以确定出初步匹配不成功的所述图像块；
反色模块，用于对初步匹配不成功的所述图像块进行反色处理，并将反色处理后每个所述图像块与所述指纹模板进行再次匹配；
检测模块，用于根据再次匹配成功的图像块，确定所述目标指纹图像上的反色区域。
本申请实施例还提供一种电子设备，其包括本申请任一实施例所述的指纹芯片。
本申请实施例提供的技术方案中，通过对目标指纹图像进行切分得到若干个图像块，并将每个所述图像块分别与指纹模板进行初步匹配，以确定出初步匹配不成功的所述图像块；对初步匹配不成功的所述图像块进行反色处理，并将反色处理后每个所述图像块与所述指纹模板进行再次匹配；根据再次匹配成功的图像块，确定所述目标指纹图像上谷脊特征相反的反色区域，从而可有效地识别出指纹图像的反色区域，在指纹识别时，可以有效降低拒识率。
附图说明
后文将参照附图以示例性而非限制性的方式详细描述本申请实施例的一些具体实施例。附图中相同的附图标记标示了相同或类似的部件或部分。本领域技术人员应该理解，这些附图未必是按比例绘制的。附图中：
图1为本申请实施例一中反色区域的确定方法流程示意图；
图2为本申请实施例二中反色区域的确定方法流程示意图；
图3为本申请实施例三中反色区域的确定方法流程示意图；
图4为本申请实施例四中反色区域的确定方法流程示意图；
图5为本申请实施例五中反色区域的确定方法流程示意图；
图6为本申请实施例六中指纹芯片的结构示意图。
具体实施方式
实施本发明实施例的任一技术方案必不一定需要同时达到以上的所有优点。
下面结合本发明实施例附图进一步说明本发明实施例具体实现。
本申请实施例提供的技术方案中，通过对目标指纹图像进行切分得到若干个图像块，并将每个所述图像块分别与指纹模板进行初步匹配，以确定出初步匹配不成功的所述图像块；对初步匹配不成功的所述图像块进行反色处理，并将反色处理后每个所述图像块与所述指纹模板进行再次匹配；根据再次匹配成功的图像块，确定所述目标指纹图像上谷脊特征相反的反色区域，从而可有效地识别出指纹图像的反色区域，在指纹识别时，可以有效降低拒识率。
图1为本申请实施例一中反色区域的确定方法流程示意图；如图1所示，其包括：
S101、对目标指纹图像进行切分得到若干个图像块，并将每个所述图像块分别与指纹模板进行初步匹配，以确定出初步匹配不成功的所述图像块；
本实施例中，图像块与指纹模板进行匹配的过程实际上可以理解为图像块上的指纹特征与指纹模板进行匹配，如果匹配度超过设定的匹配度阈值，则认为匹配成功，否则认为匹配不成功。实际上，每个图像块可以视为一个待匹配指纹图像。
本实施例中，步骤S101中对目标指纹图像进行切分得到若干个图像 块时，具体可以基于分割视窗或者灰度值，对目标指纹图像进行切分得到若干个图像块。
本实施例中，所述目标指纹图像具体可以是指对目标指纹原始图像进行前景和背景分离得到的指纹图像，直接基于该指纹图像进行分割，从而得到若干个图像块。进行前景和背景分离得到的指纹图像实际可以得到有效指纹区域，从而可进一步提高后续匹配的准确度。
具体地，在一种具体应用场景中，可以通过分割视窗，比如矩形的分割视窗，去对完成了上述前景和背景分离的指纹图像进行分块得到若干个矩形的图像块，每个矩形的图像块的大小可以相同也可以不同。此处，对于图像块均具有对应的尺寸大小参数以及在整幅指纹图像上的坐标位置。
具体地，在一种具体应用场景中，可以通过统计指纹图形的灰度值来进行图像块的分割。进一步地，在完成了前景和背景分离的指纹图像上，针对指纹图像上的有效指纹区域，选择一参考像素点，以该参考像素点为基准，选取其邻域内的若干个像素点，统计包括参考像素点以及所述参考像素点邻域内的若干个像素点围成的像素点区域的像素灰度均值，判断该像素灰度均值是否约等于设定的灰度均值阈值，如果是的话，则将参考像素点以及若干个像素点划分在同一个图像块，否则，扩充参考像素点的邻域以增加像素点的数量，直至包括参考像素点以及所述参考像素点邻域内的若干个像素点围成的像素点区域的像素灰度均值约等于设定的灰度均值阈值。依次类推，选择上一次确定出的图像块的一个边缘像素点作为新参考像素点，以该新参考像素点为基准，选取新参考像素点邻域内的若干个像素点(该若干个像素点不包括在已经得到的图像块之内)，统计包括新参考像素点以及所述新参考像素点邻域内的若干个像素点围成的像素点区域的像素灰度均值，判断该像素灰度均值是否约等于设定的灰度均值阈值，若是，则将参考像素点以及若干个像素点划分在同一个图像块，否则，扩充该参考像素点的邻域以增加像素点的数量，直至包括参考像素点以及所述参考像素点邻域内的若干个像素点围成的像素点区域的像素灰度均值约等于设定的灰度均值阈值。
当然，此处需要说明的是，上述通过像素点灰度均值的方式对指纹图像进行分割得到的多个图像块大小并不绝对相等。
具体地，在另一具体应用场景中，在上述统计灰度均值的基础上，还可以进一步增加灰度值方差，即在图像块分割的过程中，除了要考量统计灰度均值是否约等于灰度均值阈值，还要考量灰度值方差是否约等于灰度值方差 阈值，只有当统计灰度均值约等于灰度均值阈值，以及灰度值方差约等于灰度值方差阈值这两个条件均满足时，才认为完成了一个图像块的划分，即将满足这两个条件的参考像素点以及其领域内的若干个像素点组成一个图像块。由于灰度均值的大小代表了明暗程度，而灰度值方差的大小代表了对比度，灰度均值越大表示越亮，反之越暗，灰度方差代表了当前块的对比度，灰度方差越大,黑白越分明，反之则黑白界限比较模糊。因此，通缩上述当统计灰度均值约等于灰度均值阈值，以及灰度值方差约等于灰度值方差阈值这两个条件均满足的图像块分割方式，得到的图像块在对比度以及黑白分明度上比较均匀，从而进一步使得每一个图像块上尽可能都有有效的指纹特征数据，从而保证了后续匹配的准确性。
此处，需要说明的是，“约等于”实际上可理解为包括稍大或者稍小的情形。
S102、对初步匹配不成功的所述图像块进行反色处理，并将反色处理后每个所述图像块与所述指纹模板进行再次匹配；
本实施例中，考虑到反色区域实际上是由于谷脊特征在图像表现上呈现相反，即如前所述，本来应该属于脊特征的，但是在指纹图像上确表现为谷特征，或者本来属于谷特征的，但是确表现为脊特征。因此，理论来看，那些在步骤S101中匹配不成功的图像块很大可能上是存在反色区域，为此，当对这些图像块经过反色处理之后，在图像上，脊特征对应指纹中的脊，谷特征对应指纹中的谷，那再与指纹模板进行匹配时应该能匹配成功，或者说匹配成功的概率很高。因此，基于上述理论上的再将反色处理后的图像块与所述指纹模板进行再次匹配，以相对准确地能确定出那些图像块是真正存在反色现象的图像块。另外，基于该假设，因此对初步匹配不成功的所述图像块进行反色处理，也不会增加误识率(False accept rate，简称FAR)。
此处，再次匹配的技术处理过程类上述初次匹配的过程，即实质上是将图像块上的指纹数据与指纹模板进行匹配，确定匹配度的过程。
本实施例中，由于之前基于灰度值进行图像块的分割，因此，直接得到的图像块也是基于灰度的，为此，在本实施例中，基于灰度值进行反色处理。具体地，用最高灰度级减去图像块中每个像素点的灰度值，即实现反色处理。
S103、根据再次匹配成功的图像块，确定所述目标指纹图像上谷脊特征相反的反色区域。
本实施例中，如前所述，基于反色的谷脊特征再经过反色处理，理论 上对应于正确的谷脊特征，为此，如果忽略其他除反色以外的因素，在再次匹配理论上应该可以匹配成功。因此，本实施例中，根据上述步骤S103的再次匹配处理，确定出再次匹配成功的图像块，则表明这些图像块(对应反色处理前)的图像块上存在反色现象。
如前所述，由于在图像块的分割之后，每个图像块都具有坐标值以及块大小值，因此，综合这些坐标值以及图像块的大小即可得知在目标指纹图像上存在反色区域，即根据再次匹配成功的图像块在目标指纹图像上的坐标以及图像块的大小，确定所述目标指纹图像上谷脊特征相反的反色区域。当然，这些反色区域并非一定是连通的一片区域，实际上也可可能是分散的多片区域。
图2为本申请实施例二中反色区域的确定方法流程示意图；如图2所示，其包括：
S201、对原始目标指纹图像进行切分得到若干个原始图像块，并对每个所述原始图像块进行预处理得到对应的预处理图像块；
与上述实施例不同的是，图1是在对目标原始图像进行前景和背景分离之后的指纹图像进行切分，而本实施例中，实际上是在前景和背景分离之前，在原始目标指纹图像上进行切分，之后，在对得到的原始图像块进行预处理得到预处理图像块。
此处，预处理包括：增益、去噪、前景和背景分离、图像归一化、图像增强、二值化等中的至少其一或者任意的组合。此处增益、去噪的目的在于使得指纹特征在图像的表现性能上初步优化，前景和背景分离如前所述目的在于去除掉背景，确定出前景中的有效指纹区域。由于按压力度的不一致，导致指纹采集模块采集到的原始指纹图像会有偏向，中间部分的脊特征颜色比较重，二边缘侧的脊特征则又细又不清楚，因此，通过图像归一化使图像在颜色亮度以及对比度上尽可能一致，从而使得图像的轮廓清晰可见。虽然经过归一化后的图像的轮廓清晰可见，但是对于精细的计算机来说仍然是有很多偏差。图像增强的处理目的在于图像上的谷脊特征更加清晰，并把断裂的谷特征、脊特征分别补齐或者补全。因此，得到图像质量较高的灰度指纹图像，再将该灰度指纹图像进行二值化得到二值化指纹图像，形成一副图像的特征表现上非黑即白，而没有所谓的中间灰的过度，从而使得图像更加清晰。
此处，需要说明的是，在进行预处理时，可以同时批量对所有的图像块进行预处理，也可以单独对每个图像块进行预处理。
本实施例中，实现切分的具体技术处理可以采用上述图1所示实施例 中的基于分割视窗或者灰度值，当然也可以基于指纹纹路方向一致性。指纹纹路方向一致性的原理大致为：在二值化指纹图像上，顺着纹路的方向对像素点进行投影运算，像素均值呈明显的正弦变化，而垂直于纹路的方向对像素进行投影运算，像素均值则是比较平坦的直线。
S202、所述预处理图像块分别与所述指纹模板进行初步匹配，以确定出与所述指纹模板初步匹配不成功的所述预处理图像块。
S203、对初步匹配不成功的所述预处理图像块进行反色处理，并将反色处理后每个所述预处理图像块与所述指纹模板进行再次匹配；
本实施例中，在步骤S203中对与所述指纹模板不匹配的所述图像块进行反色处理时，可以对与所述指纹模板初步不匹配的所有所述图像块进行整体反色处理，或者，也可以对与所述指纹模板初步不匹配的每个所述图像块进行单独反色处理。
与上述实施例不同的是，本实施例中是就有二值化指纹图像进行切分的，因此，得到的图像块实际上也是二值化图像，即像素点的灰度值非1即0，非0即1，因此，反色处理相对来说比较简单，即把灰度值为1的变为0，把灰度值为0的变为1。
如前所述，由于每个图像块均具有对应的尺寸大小参数以及在整幅指纹图像上的坐标位置，因此，在反色时，通过坐标位置以及尺寸大小即可准确的找到对应图像块。
本实施例中，初次匹配以及再次匹配的类上述实施例一。
S204、根据再次匹配成功的预处理图像块，确定所述目标指纹图像上谷脊特征相反的反色区域。
本实施例中，反色区域的确定方式类似上述实施例一，进一步地，在确定出反色区域后，可以直接在二值化指纹图像上进行标注。
图3为本申请实施例三中反色区域的确定方法流程示意图；如图3所示，其包括：
S301、对原始目标指纹图像进行预处理得到预处理目标指纹图像；
本实施例中，与上述实施例不同的是，在分割之前进行预处理，该预处理可以包括但不限于增益、去噪、前景和背景分离、图像归一化、图像增强、二值化等中的至少其一或者任意的组合，因此，最终得到预处理目标指纹图像实际上是一整幅二值化指纹图像。
S302、对预处理目标指纹图像进行切分得到若干个预处理图像块， 将每个预处理图像块分别与指纹模板进行匹配，以确定出与所述指纹模板不匹配的所述预处理图像块。
本实施例中，可以具体采用上述实施例一或者二的方式，对预处理目标指纹图像进行切分处理得到多个预处理图像块。进一步地，这些预处理图像块之间可以有重叠，也可以没有重叠。
S303、对初步匹配不成功的所述预处理图像块进行反色处理，并将反色处理后每个所述预处理图像块与所述指纹模板进行再次匹配；
本实施例中，在步骤S303中对与所述指纹模板不匹配的所述图像块进行反色处理时，可以对与所述指纹模板初步不匹配的所有所述图像块进行整体反色处理，或者，对与所述指纹模板初步不匹配的每个所述图像块进行单独反色处理。
具体地的反色处理可以参照上述针对二值化指纹图像的处理方式，即将预处理图像块上像素点的灰度值由1改为0，将像素点的灰度值由0改为1。
S304、根据再次匹配成功的预处理图像块，确定所述目标指纹图像上谷脊特征相反的反色区域。
本实施例中，步骤S304请参照上述实施例一或者二。
图4为本申请实施例四中反色区域的确定方法流程示意图；本实施例中，与上述实施例3不同的是，在进行反色处理时，考虑到有必要进行单独反色以及整体反色处理的需求，为此，本实施例中，其包括：
S401、对原始目标指纹图像进行预处理得到预处理目标指纹图像；
S402、对预处理目标指纹图像进行切分得到若干个预处理图像块，将每个预处理图像块分别与指纹模板进行匹配，以确定出与所述指纹模板不匹配的所述预处理图像块。
S403、对与所述指纹模板初步不匹配的所有所述图像块进行整体反色处理，并将整体反色处理后每个所述预处理图像块与所述指纹模板进行再次匹配；
本实施例中，步骤S401、S402、S403请参见上述实施例的描述。
S404A、若匹配成功，根据再次匹配成功的预处理图像块，确定所述目标指纹图像上谷脊特征相反的反色区域。
S404B、若匹配不成功，对与所述指纹模板初步不匹配的每个所述图像块进行单独反色处理，并将单独反色处理后每个所述预处理图像块与所述指纹模板进行再次匹配；若匹配成功，则跳转到S404A；否则，将执行步骤S405；
S405、将再次匹配不成功的所述预处理图像块标识为待处理。
本实施例中，与上述实施例不同的是，先对初步不匹配的所有所述图像块进行整体反色处理，之后再去进行再次匹配，如果再次匹配不成功，则将再次匹配不成功的图像块进行单独反色处理，之后，再次进行再次匹配，从而提高反色区域判断的准确性。
此处需要说明的是，步骤S405中将再次匹配不成功的所述预处理图像块标识为待处理，其主要是考虑到由于确定反色区域的最终目的是要对目标值进行识别，如果根据再次匹配成功的所述图像块以及初步匹配成功的所述图像块，可判定所述目标指纹图像匹配成功，则实际上可视为标识为待处理的预处理图像块对所述目标指纹图像匹配的判定结果影响不大或者没有影响。如果根据再次匹配成功的所述图像块以及初步匹配成功的所述图像块，无法判定所述目标指纹图像匹配成功，因此需要利用这些标识为待处理的预处理图像块，进一步判断所述目标指纹图像是否匹配成功。
关于利用上述标识为待处理的预处理图像块进行所述目标指纹图像是否匹配成功的判断，详见下述实施例五的记载。
图5为本申请实施例五中反色区域的确定方法流程示意图；本实施例中，实际上可理解在确定出反色区域后如何进一步判断指纹图像是否匹配成功。如图5所示，其包括：
S501、对原始目标指纹图像进行预处理得到预处理目标指纹图像；
S502、对预处理目标指纹图像进行切分得到若干个预处理图像块，将每个预处理图像块分别与指纹模板进行匹配，以确定出与所述指纹模板不匹配的所述预处理图像块。
S503、对与所述指纹模板初步不匹配的所有所述图像块进行整体反色处理，并将整体反色处理后每个所述预处理图像块与所述指纹模板进行再次匹配；
S504A、若匹配成功，根据再次匹配成功的预处理图像块，确定所述目标指纹图像上谷脊特征相反的反色区域。
S504B、若匹配不成功，对与所述指纹模板初步不匹配的每个所述图像块进行单独反色处理，并将单独反色处理后每个所述预处理图像块与所述指纹模板进行再次匹配；若匹配成功，则跳转到S504A；否则，将执行步骤S505；
S505、将再次匹配不成功的所述预处理图像块标识为待处理。
S506、确定出初步匹配成功的所述图像块；根据再次匹配成功的所 述图像块以及初步匹配成功的所述图像块，判断所述目标指纹图像是否匹配成功。
若判定所述目标指纹图像匹配成功，则执行步骤S507A；否则，执行步骤S507B。
S507A、输出所述目标指纹图像匹配成功的判定结果；
S507B、将标识为待处理的图像块进行增强处理得到增强图像块，将所述增强图像块与所述指纹模板进行匹配；
S508、根据匹配成功的所述增强图像块、初步匹配成功的所述图像块、再次匹配成功的所述图像块，判断所述目标指纹图像是否匹配成功。
本实施例中，根据步骤S503得到的再次匹配成功的所述图像块以及初步匹配成功的所述图像块，判断所述目标指纹图像是否匹配成功。比如，具体地，确定再次匹配成功的所述图像块以及初步匹配成功的所述图像块的总和，统计所述总和占切分得到的图像块的总数量的比例，根据所述比例与设定的比例门限，判断所述目标指纹图像是否匹配成功。如果所述比例大于等于设定的比例门限，则判定所述目标指纹图像匹配成功；否则，判定所述目标指纹图像匹配不成功。因此，为了提高所述目标指纹图像匹配成功与否的判断准确性，进一步结合标识为待处理的所述预处理图像块进一步判断所述目标指纹图像是否匹配成功。
具体地，通过执行上述步骤S507、S508，确定出匹配成功的所述增强图像块、初步匹配成功的所述图像块、再次匹配成功的所述图像块的总和，再次统计所述总和占切分得到的图像块的总数量的比例，若所述再次统计的比例大于设定的比例门限，则判定所述目标指纹图像匹配成功，否则判定所述目标指纹图像匹配不成功。
图6为本申请实施例六中指纹芯片的结构示意图；如图6所示，其包括处理器，所述处理器上配置有：
切分模块601，用于对目标指纹图像进行切分得到若干个图像块，并将每个所述图像块分别与指纹模板进行初步匹配，以确定出初步匹配不成功的所述图像块；
反色模块602，用于对初步匹配不成功的所述图像块进行反色处理，并将反色处理后每个所述图像块与所述指纹模板进行再次匹配；
检测模块603，用于根据再次匹配成功的图像块，确定所述目标指纹图像上的反色区域。
本申请实施例还提供一种电子设备，其包括本申请任一实施例所述的指纹芯片。
本实施例还提供一种电子设备，其包括上述实施例中的指纹识别装置。
这些电子设备包括但不限于：
(1)移动通信设备:这类设备的特点是具备移动通信功能，并且以提供话音、数据通信为主要目标。这类终端包括:智能手机(例如iPhone)、多媒体手机、功能性手机，以及低端手机等。
(2)超移动个人计算机设备:这类设备属于个人计算机的范畴，有计算和处理功能，一般也具备移动上网特性。这类终端包括:PDA、MID和UMPC设备等，例如iPad。
(3)便携式娱乐设备:这类设备可以显示和播放多媒体内容。该类设备包括:音频、视频播放器(例如iPod)，掌上游戏机，电子书，以及智能玩具和便携式车载导航设备。
(4)其他具有数据交互功能的电子装置。
至此，已经对本主题的特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作可以按照不同的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序，以实现期望的结果。在某些实施方式中，多任务处理和并行处理可以是有利的。
在20世纪90年代，对于一个技术的改进可以很明显地区分是硬件上的改进(例如，对二极管、晶体管、开关等电路结构的改进)还是软件上的改进(对于方法流程的改进)。然而，随着技术的发展，当今的很多方法流程的改进已经可以视为硬件电路结构的直接改进。设计人员几乎都通过将改进的方法流程编程到硬件电路中来得到相应的硬件电路结构。因此，不能说一个方法流程的改进就不能用硬件实体模块来实现。例如，可编程逻辑器件(Programmable Logic Device,PLD)(例如现场可编程门阵列(Field Programmable Gate Array，FPGA))就是这样一种集成电路，其逻辑功能由用户对器件编程来确定。由设计人员自行编程来把一个数字***“集成”在一片PLD上，而不需要请芯片制造厂商来设计和制作专用的集成电路芯片。而且，如今，取代手工地制作集成电路芯片，这种编程也多半改用“逻辑编译器(logic compiler)”软件来实现，它与程序开发撰写时所用的软件编译器相类似，而要编译之前的原始代码也得用特定的编程语言来撰写，此称之为硬件描述语言 (Hardware Description Language，HDL)，而HDL也并非仅有一种，而是有许多种，如ABEL(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language)等，目前最普遍使用的是VHDL(Very-High-Speed Integrated Circuit Hardware Description Language)与Verilog。本领域技术人员也应该清楚，只需要将方法流程用上述几种硬件描述语言稍作逻辑编程并编程到集成电路中，就可以很容易得到实现该逻辑方法流程的硬件电路。
控制器可以按任何适当的方式实现，例如，控制器可以采取例如微处理器或处理器以及存储可由该(微)处理器执行的计算机可读程序代码(例如软件或固件)的计算机可读介质、逻辑门、开关、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程逻辑控制器和嵌入微控制器的形式，控制器的例子包括但不限于以下微控制器：ARC 625D、Atmel AT91SAM、Microchip PIC18F26K20以及Silicone Labs C8051F320，存储器控制器还可以被实现为存储器的控制逻辑的一部分。本领域技术人员也知道，除了以纯计算机可读程序代码方式实现控制器以外，完全可以通过将方法步骤进行逻辑编程来使得控制器以逻辑门、开关、专用集成电路、可编程逻辑控制器和嵌入微控制器等的形式来实现相同功能。因此这种控制器可以被认为是一种硬件部件，而对其内包括的用于实现各种功能的装置也可以视为硬件部件内的结构。或者甚至，可以将用于实现各种功能的装置视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
上述实施例阐明的***、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机。具体的，计算机例如可以为个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任何设备的组合。
为了描述的方便，描述以上装置时以功能分为各种单元分别描述。当然，在实施本申请时可以把各单元的功能在同一个或多个软件和/或硬件中实现。
本领域内的技术人员应明白，本申请的实施例可提供为方法、***、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其 中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(***)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括：但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白，本申请的实施例可提供为方法、***或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请可以在由计算机执行的计算机可执行指令的一般上下文中描述，例如程序模块。一般地，程序模块包括执行特定事务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本申请，在这些分布式计算环境中，由通过通信网络而被连接的远程处理设备来执行事务。在分布式计算环境中，程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于***实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
以上所述仅为本申请的实施例而已，并不用于限制本申请。对于本领域技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本申请的权利要求范围之内。

Claims (14)

  1. 一种反色区域的确定方法，其特征在于，包括：
    对目标指纹图像进行切分得到若干个图像块，并将每个所述图像块分别与指纹模板进行初步匹配，以确定出初步匹配不成功的所述图像块；
    对初步匹配不成功的所述图像块进行反色处理，并将反色处理后每个所述图像块与所述指纹模板进行再次匹配；
    根据再次匹配成功的图像块，确定所述目标指纹图像上谷脊特征相反的反色区域。
  2. 根据权利要求1所述的方法，其特征在于，对目标指纹图像进行切分得到若干个图像块，包括：基于分割视窗或者灰度值或者指纹纹路方向一致性，对目标指纹图像进行切分得到若干个图像块。
  3. 根据权利要求1所述的方法，其特征在于，对目标指纹图像进行切分得到若干个图像块，并将每个所述图像块分别与指纹模板进行匹配，以确定出与所述指纹模板不匹配的所述图像块，包括：对原始目标指纹图像进行切分得到若干个原始图像块，并对每个所述原始图像块进行预处理得到对应的预处理图像块，所述预处理图像块分别与所述指纹模板进行初步匹配，以确定出与所述指纹模板初步匹配不成功的所述预处理图像块。
  4. 根据权利要求1所述的方法，其特征在于，根据再次匹配成功的图像块，确定所述目标指纹图像上谷脊特征相反的反色区域，包括：根据再次匹配成功的图像块在目标指纹图像上的坐标以及图像块的大小，确定所述目标指纹图像上谷脊特征相反的反色区域。
  5. 根据权利要求1所述的方法，其特征在于，还包括：对原始目标指纹图像进行预处理得到预处理目标指纹图像；对应地，对目标指纹图像进行切分得到若干个图像块，并将每个所述图像块分别与指纹模板进行匹配，以确定出与所述指纹模板不匹配的所述图像块，包括：对预处理目标指纹图像进行切分得到若干个预处理图像块，将每个预处理图像块分别与指纹模板进行匹配，以确定出与所述指纹模板不匹配的所述预处理图像块。
  6. 根据权利要求1所述的方法，其特征在于，对与所述指纹模板不匹配的所述图像块进行反色处理，包括：对与所述指纹模板初步不匹配的所有所述图像块进行整体反色处理，或者，对与所述指纹模板初步不匹配的每个所述图像块进行单独反色处理。
  7. 根据权利要求3或5所述的方法，其特征在于，所述预处理图像块为灰度图像块或者二值化图像块。
  8. 根据权利要求1-7所述的方法，其特征在于，对与所述指纹模板不匹配的所述图像块进行反色处理，包括：对与所述指纹模板初步不匹配的所有所述图像块进行整体反色处理，并在经过整体反色处理后的每个所述图像块与所述指纹模板匹配不成功时，对与所述指纹模板初步不匹配的每个所述图像块进行单独反色处理。
  9. 根据权利要求8所述的方法，其特征在于，还包括：将再次匹配不成功的图像块标识为待处理。
  10. 根据权利要求9所述的方法，其特征在于，还包括：确定出初步匹配成功的所述图像块；根据再次匹配成功的所述图像块以及初步匹配成功的所述图像块，判断所述目标指纹图像是否匹配成功。
  11. 根据权利要求10所述的方法，其特征在于，根据再次匹配成功的图像块以及初步匹配成功的所述图像块，判断所述目标指纹图像是否匹配成功，包括：确定再次匹配成功的所述图像块以及初步匹配成功的所述图像块的总和，统计所述总和占切分得到的图像块的总数量的比例，根据所述比例与设定的比例门限，判断所述目标指纹图像是否匹配成功。
  12. 根据权利要求11所述的方法，其特征在于，根据所述比例与设定的比例门限，判断所述目标指纹图像是否匹配成功，包括：若所述比例大于设定的比例门限，判定所述目标指纹图像匹配成功；否则，将标识为待处理的图像块进行增强处理得到增强图像块，将所述增强图像块与所述指纹模板进行匹配，确定匹配成功的所述增强图像块、初步匹配成功的所述图像块、再次匹配成功的所述图像块的总和，再次统计所述总和占切分得到的图像块的总数量的比例，若所述再次统计的比例大于设定的比例门限，则判定所述目标指纹图像匹配成功，否则判定所述目标指纹图像匹配不成功。
  13. 一种指纹芯片，其特征在于，其包括处理器，所述处理器上配置有：
    切分模块，用于对目标指纹图像进行切分得到若干个图像块，并将每个所述图像块分别与指纹模板进行初步匹配，以确定出初步匹配不成功的所述图像块；
    反色模块，用于对初步匹配不成功的所述图像块进行反色处理，并将反色处理后每个所述图像块与所述指纹模板进行再次匹配；
    检测模块，用于根据再次匹配成功的图像块，确定所述目标指纹图像上的 反色区域。
  14. 一种电子设备，其特征在于，包括权利要求13所述的指纹芯片。
PCT/CN2019/088650 2019-05-27 2019-05-27 反色区域的确定方法、指纹芯片及电子设备 WO2020237481A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2019/088650 WO2020237481A1 (zh) 2019-05-27 2019-05-27 反色区域的确定方法、指纹芯片及电子设备
CN201980000858.9A CN110383287B (zh) 2019-05-27 2019-05-27 反色区域的确定方法、指纹芯片及电子设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/088650 WO2020237481A1 (zh) 2019-05-27 2019-05-27 反色区域的确定方法、指纹芯片及电子设备

Publications (1)

Publication Number Publication Date
WO2020237481A1 true WO2020237481A1 (zh) 2020-12-03

Family

ID=68261530

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/088650 WO2020237481A1 (zh) 2019-05-27 2019-05-27 反色区域的确定方法、指纹芯片及电子设备

Country Status (2)

Country Link
CN (1) CN110383287B (zh)
WO (1) WO2020237481A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116994007A (zh) * 2023-09-26 2023-11-03 支付宝(杭州)信息技术有限公司 商品纹理检测处理方法及装置

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112560813B (zh) * 2021-02-19 2021-05-25 深圳阜时科技有限公司 窄条形指纹的识别方法、存储介质及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090310831A1 (en) * 2008-06-17 2009-12-17 The Hong Kong Polytechnic University Partial fingerprint recognition
CN105912916A (zh) * 2016-05-27 2016-08-31 广东欧珀移动通信有限公司 一种指纹解锁方法及终端
CN106056037A (zh) * 2015-04-15 2016-10-26 三星电子株式会社 用于识别指纹的方法和设备
CN109086677A (zh) * 2018-07-09 2018-12-25 保山市质量技术监督综合检测中心 一种基于指纹识别的身份验证方法及***
CN109376632A (zh) * 2018-10-12 2019-02-22 Oppo（重庆）智能科技有限公司 指纹识别方法、电子装置及计算机可读取介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090310831A1 (en) * 2008-06-17 2009-12-17 The Hong Kong Polytechnic University Partial fingerprint recognition
CN106056037A (zh) * 2015-04-15 2016-10-26 三星电子株式会社 用于识别指纹的方法和设备
CN105912916A (zh) * 2016-05-27 2016-08-31 广东欧珀移动通信有限公司 一种指纹解锁方法及终端
CN109086677A (zh) * 2018-07-09 2018-12-25 保山市质量技术监督综合检测中心 一种基于指纹识别的身份验证方法及***
CN109376632A (zh) * 2018-10-12 2019-02-22 Oppo（重庆）智能科技有限公司 指纹识别方法、电子装置及计算机可读取介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116994007A (zh) * 2023-09-26 2023-11-03 支付宝(杭州)信息技术有限公司 商品纹理检测处理方法及装置
CN116994007B (zh) * 2023-09-26 2024-03-19 支付宝(杭州)信息技术有限公司 商品纹理检测处理方法及装置

Also Published As

Publication number Publication date
CN110383287A (zh) 2019-10-25
CN110383287B (zh) 2022-08-30

Similar Documents

Publication Publication Date Title
US20200160040A1 (en) Three-dimensional living-body face detection method, face authentication recognition method, and apparatuses
US9697416B2 (en) Object detection using cascaded convolutional neural networks
US20220092882A1 (en) Living body detection method based on facial recognition, and electronic device and storage medium
CN110414507B (zh) 车牌识别方法、装置、计算机设备和存储介质
CN110427932B (zh) 一种识别图像中多个票据区域的方法及装置
WO2022037541A1 (zh) 图像处理模型训练方法、装置、设备及存储介质
US20150206318A1 (en) Method and apparatus for image enhancement and edge verificaton using at least one additional image
US8781177B2 (en) Method and computer program product for extracting feature vectors from a palm image
US9575566B2 (en) Technologies for robust two-dimensional gesture recognition
TW202111498A (zh) 指紋識別方法、晶片及電子裝置
CN112085701B (zh) 一种人脸模糊度检测方法、装置、终端设备及存储介质
CN112396050B (zh) 图像的处理方法、设备以及存储介质
CN110969046B (zh) 人脸识别方法、设备及计算机可读存储介质
CN110619656B (zh) 基于双目摄像头的人脸检测跟踪方法、装置及电子设备
CN114550177A (zh) 图像处理的方法、文本识别方法及装置
US20190050659A1 (en) Method of processing biometric image and apparatus including the same
CN110570442A (zh) 一种复杂背景下轮廓检测方法、终端设备及存储介质
CN115631112B (zh) 一种基于深度学习的建筑轮廓矫正方法及装置
WO2020237481A1 (zh) 反色区域的确定方法、指纹芯片及电子设备
CN111291797A (zh) 一种防伪识别方法、装置及电子设备
CN111368632A (zh) 一种签名识别方法及设备
CN111047496A (zh) 阈值确定方法、水印检测方法、装置和电子设备
CN108960247B (zh) 图像显著性检测方法、装置以及电子设备
CN115461792A (zh) 手写文本识别方法、装置和***，手写文本搜索方法和***，以及计算机可读存储介质
CN109978903B (zh) 一种标识点识别方法、装置、电子设备及存储介质

Legal Events

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

Ref document number: 19931328

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19931328

Country of ref document: EP

Kind code of ref document: A1