WO2017008349A1 - 指纹识别的方法及装置 - Google Patents
指纹识别的方法及装置 Download PDFInfo
- Publication number
- WO2017008349A1 WO2017008349A1 PCT/CN2015/085828 CN2015085828W WO2017008349A1 WO 2017008349 A1 WO2017008349 A1 WO 2017008349A1 CN 2015085828 W CN2015085828 W CN 2015085828W WO 2017008349 A1 WO2017008349 A1 WO 2017008349A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- fingerprint
- matching
- image
- fingerprint image
- regions
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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 present invention relates to the field of fingerprint recognition technologies, and in particular, to a fingerprint recognition method and a fingerprint recognition device.
- Fingerprint recognition usually first collects fingerprint images. In the process of fingerprint image collection, because the orientation of each print is not exactly the same, different focus points will bring different degrees of deformation. Therefore, how to process the collected fingerprint images will be processed. Affects the accuracy of the entire fingerprint recognition.
- an image smaller than the original image (such as the image 102 shown in FIG. 1) is generated according to the collected original fingerprint image to reduce post-processing and storage related fingerprints.
- the amount of information is generated according to the collected original fingerprint image to reduce post-processing and storage related fingerprints.
- This method has certain defects: although the original image is reduced without damaging the useful information, theoretically, some image information is discarded, which reduces the amount of information in the fingerprint recognition process, thereby affecting the success rate of fingerprint recognition. And accuracy.
- the invention is based on at least one of the above technical problems, and proposes a fingerprint recognition scheme, which not only can quickly perform fingerprint recognition, but also can improve the utilization of fingerprint information in the fingerprint recognition process, thereby improving the success rate of fingerprint recognition. And accuracy.
- the present invention provides a fingerprint identification method, including: collecting a fingerprint image to be identified; dividing the fingerprint image into a plurality of regions, and corresponding to any one of the plurality of regions
- the fingerprint matching algorithm matches the fingerprint feature in the any region with the feature in the corresponding region of the reference fingerprint image; and determines the to-before according to the matching rate of the fingerprint feature in the any region Whether the identified fingerprint image matches the reference fingerprint image successfully.
- the fingerprint matching image is divided into a plurality of regions according to a fingerprint matching algorithm corresponding to any one of the plurality of regions.
- the fingerprint feature in any area is matched with the feature in the corresponding area of the reference fingerprint image, and the matching of the fingerprint image to be identified and the reference fingerprint image is determined according to the matching rate of the fingerprint feature in any area, so that The amount of information contained in an area is matched by a corresponding matching algorithm, and the fingerprint information in different areas can be effectively extracted, thereby improving the utilization of fingerprint information in the fingerprint identification process, and improving the fingerprint identification. Success rate and accuracy.
- the technical solution of the present invention can effectively reduce the storage space of the fingerprint information in the fingerprint identification process by performing related processing only on the divided multiple regions.
- the time taken for the entire fingerprint recognition process is shortened, and the fingerprint image is quickly recognized.
- the step of determining whether the fingerprint image to be identified and the reference fingerprint image are successfully matched according to a matching ratio of the fingerprint features in the any region includes: if the plurality of regions Determining that the fingerprint image to be identified matches the reference fingerprint image successfully if the matching rate of the fingerprint feature in any one of the regions is greater than or equal to a predetermined threshold, if any of the plurality of regions If the matching rate of the fingerprint feature is less than the predetermined threshold, it is determined that the fingerprint image to be identified fails to match the reference fingerprint image.
- the step of dividing the fingerprint image into a plurality of regions specifically includes: dividing the fingerprint image into a first region located at a center position of the fingerprint image and located outside the first region The second area.
- the fingerprint image is divided into a first area and a second area, wherein the first area is located at a central position of the fingerprint image, and the amount of fingerprint information is relatively large; the second area is located outside the first area, and the second area is included
- the amount of fingerprint information is less than the first area.
- the number of the divided areas of the fingerprint image and the manner of division of the fingerprint image are not limited, and those skilled in the art can perform the planning according to actual needs. Minute.
- the fingerprint feature in the any region is matched with the feature in the corresponding region of the reference fingerprint image according to a fingerprint matching algorithm corresponding to any one of the plurality of regions.
- the step specifically includes: matching the first area by using a full matching algorithm, and matching the second area by using a matching algorithm of multiple feature points.
- the first area contains the most fingerprint information
- the first area is matched by the full matching algorithm, which effectively improves the utilization of the fingerprint information, and is advantageous for improving the accuracy of fingerprint recognition;
- the two regions contain relatively small amount of fingerprint information, so matching by using a matching algorithm of multiple feature points instead of matching with a full matching algorithm can greatly shorten the time taken for the entire fingerprint identification process.
- the step of performing matching by using the all-matching algorithm on the first area includes: performing image enhancement processing on the first area to obtain a processed image; and extracting the processed image The feature information in the match is matched with a feature in a corresponding region of the reference fingerprint image.
- a device for fingerprint identification comprising: an acquisition unit, configured to collect a fingerprint image to be identified; a dividing unit, configured to divide the fingerprint image into multiple regions; and matching processing a unit, configured to match a fingerprint feature in the any region with a feature in a corresponding region of the reference fingerprint image according to a fingerprint matching algorithm corresponding to any one of the plurality of regions; Determining whether the fingerprint image to be identified and the reference fingerprint image match successfully according to a matching ratio of fingerprint features in any of the regions.
- the fingerprint matching image is divided into a plurality of regions according to a fingerprint matching algorithm corresponding to any one of the plurality of regions.
- the fingerprint feature in any area is matched with the feature in the corresponding area of the reference fingerprint image, and the matching of the fingerprint image to be identified and the reference fingerprint image is determined according to the matching rate of the fingerprint feature in any area, so that The amount of information contained in an area is matched by a corresponding matching algorithm, and the fingerprint information in different areas can be effectively extracted, thereby improving the utilization of fingerprint information in the fingerprint identification process, and improving the fingerprint identification. Success rate and accuracy.
- the technical solution of the present invention can effectively reduce the fingerprint recognition process by performing related processing only on the divided plurality of regions.
- the storage space of the fingerprint information shortens the time taken by the entire fingerprint recognition process, and realizes the rapid recognition of the fingerprint image.
- the determining unit is configured to: if the matching rate of the fingerprint features in any one of the multiple regions is greater than or equal to a predetermined threshold, determine the fingerprint to be identified And the image is successfully matched with the reference fingerprint image, and if the matching rate of the fingerprint features in any of the plurality of regions is less than the predetermined threshold, determining the fingerprint image to be recognized and the reference fingerprint image The match failed.
- the dividing unit is specifically configured to: divide the fingerprint image into a first area located at a center position of the fingerprint image and a second area located outside the first area.
- the fingerprint image is divided into a first area and a second area, wherein the first area is located at a central position of the fingerprint image, and the amount of fingerprint information is relatively large; the second area is located outside the first area, and the second area is included
- the amount of fingerprint information is less than the first area.
- the number of the divided areas of the fingerprint image and the manner of division of the fingerprint image are not limited, and those skilled in the art can divide according to actual needs.
- the matching processing unit is specifically configured to: perform matching by using a full matching algorithm on the first area, and perform matching by using a matching algorithm of multiple feature points in the second area.
- the first area contains the most fingerprint information
- the first area is matched by the full matching algorithm, which effectively improves the utilization of the fingerprint information, and is advantageous for improving the accuracy of fingerprint recognition;
- the two regions contain relatively small amount of fingerprint information, so matching by using a matching algorithm of multiple feature points instead of matching with a full matching algorithm can greatly shorten the time taken for the entire fingerprint identification process.
- the matching processing unit performs the matching of the first region by using a full matching algorithm, specifically: performing image enhancement processing on the first region to obtain a processed image; Characterizing the feature information in the processed image to the reference fingerprint image Match the features in the corresponding area.
- a terminal comprising: the device for fingerprint recognition as described in any one of the above technical solutions.
- FIG. 1 is a schematic diagram showing an effect of processing a collected fingerprint image in the related art
- FIG. 2 shows a schematic flow chart of a method of fingerprint recognition in accordance with one embodiment of the present invention
- FIG. 3 shows a schematic block diagram of an apparatus for fingerprint recognition in accordance with one embodiment of the present invention
- FIG. 4 is a schematic diagram showing a division area of a fingerprint image according to an embodiment of the present invention.
- FIG. 5 is a schematic diagram showing feature point extraction for the area 404 shown in FIG. 4;
- FIG. 6 shows a schematic diagram of matching different regions shown in FIG.
- FIG. 2 shows a schematic flow chart of a method of fingerprint recognition in accordance with one embodiment of the present invention.
- a method for fingerprint identification includes: Step 202: collecting a fingerprint image to be identified; Step 204, dividing the fingerprint image into a plurality of regions, and according to the A fingerprint matching algorithm corresponding to any one of the plurality of regions matches the fingerprint feature in the any region with the feature in the corresponding region of the reference fingerprint image; Step 206, according to the fingerprint feature in the any region
- the matching rate determines whether the fingerprint image to be identified matches the reference fingerprint image successfully.
- the fingerprint matching image is divided into a plurality of regions according to a fingerprint matching algorithm corresponding to any one of the plurality of regions.
- the fingerprint feature in any area is matched with the feature in the corresponding area of the reference fingerprint image, and the matching of the fingerprint image to be identified and the reference fingerprint image is determined according to the matching rate of the fingerprint feature in any area, so that The amount of information contained in an area is matched by a corresponding matching algorithm, and the fingerprint information in different areas can be effectively extracted, thereby improving the utilization of fingerprint information in the fingerprint identification process, and improving the fingerprint identification. Success rate and accuracy.
- the technical solution of the present invention can effectively reduce the storage space of the fingerprint information in the fingerprint identification process by performing related processing only on the divided multiple regions.
- the time taken for the entire fingerprint recognition process is shortened, and the fingerprint image is quickly recognized.
- the step of determining whether the fingerprint image to be identified and the reference fingerprint image are successfully matched according to a matching ratio of the fingerprint features in the any region includes: if the plurality of regions Determining that the fingerprint image to be identified matches the reference fingerprint image successfully if the matching rate of the fingerprint feature in any one of the regions is greater than or equal to a predetermined threshold, if any of the plurality of regions If the matching rate of the fingerprint feature is less than the predetermined threshold, it is determined that the fingerprint image to be identified fails to match the reference fingerprint image.
- the step of dividing the fingerprint image into a plurality of regions specifically includes: dividing the fingerprint image into a first region located at a center position of the fingerprint image and located outside the first region The second area.
- the fingerprint image is divided into a first area and a second area, wherein the first area is located at a central position of the fingerprint image, and the amount of fingerprint information is relatively large; the second area is located outside the first area, and the second area is included
- the amount of fingerprint information is less than the first area.
- the number of the divided areas of the fingerprint image and the manner of division of the fingerprint image are not limited, and those skilled in the art can divide according to actual needs.
- the fingerprint feature in the any region is matched with the feature in the corresponding region of the reference fingerprint image according to a fingerprint matching algorithm corresponding to any one of the plurality of regions.
- the step specifically includes: matching the first area by using a full matching algorithm, and matching the second area by using a matching algorithm of multiple feature points.
- the first area contains the most fingerprint information
- the first area is matched by the full matching algorithm, which effectively improves the utilization of the fingerprint information, and is advantageous for improving the accuracy of fingerprint recognition;
- the two regions contain relatively small amount of fingerprint information, so matching by using a matching algorithm of multiple feature points instead of matching with a full matching algorithm can greatly shorten the time taken for the entire fingerprint identification process.
- the step of performing matching by using the all-matching algorithm on the first area includes: performing image enhancement processing on the first area to obtain a processed image; and extracting the processed image The feature information in the match is matched with a feature in a corresponding region of the reference fingerprint image.
- FIG. 3 shows a schematic block diagram of an apparatus for fingerprint recognition in accordance with one embodiment of the present invention.
- the apparatus 300 for fingerprint recognition includes an acquisition unit 302, a division unit 304, a matching processing unit 306, and a determination unit 308.
- the collecting unit 302 is configured to collect the fingerprint image to be identified
- the dividing unit 304 is configured to divide the fingerprint image into multiple regions
- the matching processing unit 306 is configured to perform according to any one of the multiple regions.
- the fingerprint matching algorithm corresponding to the region matches the fingerprint feature in the any region with the feature in the corresponding region of the reference fingerprint image;
- the determining unit 308 is configured to determine the matching rate of the fingerprint feature in the region Whether the fingerprint image to be identified and the reference fingerprint image match successfully.
- the fingerprint matching image is divided into a plurality of regions according to a fingerprint matching algorithm corresponding to any one of the plurality of regions.
- the fingerprint feature in any area is matched with the feature in the corresponding area of the reference fingerprint image, and the matching of the fingerprint image to be identified and the reference fingerprint image is determined according to the matching rate of the fingerprint feature in any area, so that The amount of information contained in an area is matched by a corresponding matching algorithm, and the fingerprint information in different areas can be effectively extracted, thereby improving the utilization of fingerprint information in the fingerprint identification process, and improving the fingerprint identification. Success rate and accuracy.
- the technical solution of the present invention can effectively reduce the storage space of the fingerprint information in the fingerprint identification process by performing related processing only on the divided multiple regions.
- the time taken for the entire fingerprint recognition process is shortened, and the fingerprint image is quickly recognized.
- the determining unit 308 is specifically configured to: if the matching rate of the fingerprint features in any one of the multiple regions is greater than or equal to a predetermined threshold, determine the to-be-identified The fingerprint image is successfully matched with the reference fingerprint image, and if the matching rate of the fingerprint features in any of the plurality of regions is less than the predetermined threshold, determining the fingerprint image to be identified and the reference fingerprint Image matching failed.
- the dividing unit 304 is specifically configured to: divide the fingerprint image into a first area located at a center position of the fingerprint image and a second area located outside the first area.
- the fingerprint image is divided into a first area and a second area, wherein the first area is located at a central position of the fingerprint image, and the amount of fingerprint information is relatively large; the second area is located outside the first area, and the second area is included
- the amount of fingerprint information is less than the first area.
- the number of the divided areas of the fingerprint image and the manner of division of the fingerprint image are not limited, and those skilled in the art can divide according to actual needs.
- the matching processing unit 306 is specifically configured to: perform matching on the first region by using a full matching algorithm, and perform matching on the second region by using a matching algorithm of multiple feature points.
- the first area contains the most fingerprint information
- the first area is matched by the full matching algorithm, which effectively improves the utilization of the fingerprint information, and is advantageous for improving the accuracy of fingerprint recognition;
- the two regions contain relatively small amount of fingerprint information, so matching by using a matching algorithm of multiple feature points instead of matching with a full matching algorithm can greatly shorten the time taken for the entire fingerprint identification process.
- the matching processing unit 306 adopts the first area.
- the matching operation of the all-matching algorithm specifically includes: performing image enhancement processing on the first region to obtain a processed image; and extracting feature information in the processed image to be in a corresponding region with the reference fingerprint image The characteristics are matched.
- the present invention also proposes a terminal (not shown) comprising: a device 300 for fingerprint recognition as shown in FIG.
- the fingerprint image collected by the fingerprint collector is divided into regions 402, which are located at the center of the fingerprint image, and a region 404 located outside the region 402, and the size of the region 402 is smaller than the image shown in FIG. The size of the area occupied by 102. And the image contained in the divided area 402 and the area 404 occupies less storage space than the image 102 shown in FIG.
- image enhancement and feature information extraction may be performed.
- multi-point feature information may be extracted to acquire a plurality of feature point information, and the black dots shown in FIG. 5 represent the extracted feature points. These feature points have the characteristics of obvious features and strong information.
- the region 402 is subjected to a full matching algorithm.
- the feature information in the area 402 is matched one by one to obtain a matching ratio P1; the single point feature information in the area 404 is matched to obtain a matching rate P2, and the matching ratios at P1 and P2 are both greater than or equal to P3 (P3 is a prior
- P3 is a prior
- the matching time is less than the matching time of the scheme shown in Figure 1.
- the area 402 is smaller than the divided image 102 shown in FIG. 1, so the matching time of the area 402 is smaller than the matching time of the image 102, and only the matching of the multi-point features is performed in the area 404, so the matching time of FIG. Match time.
- the fingerprint information of the area 402 is the easiest part to extract and the most information; the multi-point feature extraction for the area 404 is to improve the utilization of the fingerprint information and improve the accuracy of the fingerprint matching. Solution; discard other image parts because the part of the information may not be extracted (limited to the current fingerprint on the mobile phone) The size of the module), discarding this part does not affect the success rate of the match.
- the present invention proposes a new fingerprint recognition scheme, which divides the collected fingerprint images into different regions and processes different regions using different algorithms. It can quickly perform fingerprint recognition, and can improve the utilization of fingerprint information during fingerprint recognition, thereby improving the success rate and accuracy of fingerprint recognition.
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)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
本发明提供了一种指纹识别的方法及装置,其中,所述指纹识别的方法,包括:采集待识别的指纹图像;将所述指纹图像划分为多个区域,并根据与所述多个区域中的任一区域相对应的指纹匹配算法将所述任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配;根据所述任一区域内的指纹特征的匹配率确定所述待识别的指纹图像与所述基准指纹图像是否匹配成功。本发明的技术方案通过将采集到的指纹图像进行不同区域划分,并对不同区域采用不同的算法进行处理,不仅能够快速地进行指纹识别,而且能够提高指纹识别过程中指纹信息的利用率,进而提高了指纹识别的成功率和准确性。
Description
本申请要求于2015年7月16日提交中国专利局,申请号为201510420617.3、发明名称为“指纹识别的方法及装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本发明涉及指纹识别技术领域,具体而言,涉及一种指纹识别的方法和一种指纹识别的装置。
目前,指纹识别技术作为一种较成熟的生物特征识别技术,已被广泛应用于多个领域中。而指纹识别通常首先要采集指纹图像,在指纹图像的采集过程中,由于每次捺印的方位不完全一样,着力点不同会带来不同程度的变形,因此如何对采集到的指纹图像进行处理会影响到整个指纹识别的准确性。
相关技术中,对于指纹图像的处理方法,通常是根据采集到的原指纹图像对应生成一个比原图小的图像(如图1中所示的图像102),以减少后期处理和存储的相关指纹信息量。该方法存在一定的缺陷:虽然在不损有用信息的情况下将原图像变小,但是理论上还是放弃掉了一部分图像信息,降低了指纹识别过程中的信息量,从而影响指纹识别的成功率和准确性。
因此,如何能够提高指纹识别过程中指纹信息的利用率,从而提高指纹识别的成功率和准确性成为亟待解决的技术问题。
发明内容
本发明正是基于上述技术问题至少之一,提出了一种指纹识别的方案,不仅能够快速地进行指纹识别,而且能够提高指纹识别过程中指纹信息的利用率,进而提高了指纹识别的成功率和准确性。
有鉴于此,本发明提出了一种指纹识别的方法,包括:采集待识别的指纹图像;将所述指纹图像划分为多个区域,并根据与所述多个区域中的任一区域相对应的指纹匹配算法将所述任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配;根据所述任一区域内的指纹特征的匹配率确定所述待
识别的指纹图像与所述基准指纹图像是否匹配成功。
在该技术方案中,由于指纹图像的不同位置包含的指纹信息量不同,因此通过将采集到指纹图像划分为多个区域,以根据与多个区域中的任一区域相对应的指纹匹配算法将任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配,并根据任一区域内的指纹特征的匹配率确定待识别的指纹图像与基准指纹图像是否匹配成功,使得能够针对任一区域内包含的信息量的多少采取相应的匹配算法进行匹配,并且能够对不同区域内的指纹信息都进行有效提取,从而提高了指纹识别过程中指纹信息的利用率,有利于提高指纹识别的成功率和准确性。
另外,相比于现有技术中对整个指纹图像进行处理的方案,本发明的技术方案由于仅对划分的多个区域进行相关处理,因此可以有效降低指纹识别过程中指纹信息的存储空间,同时缩短了整个指纹识别过程所耗费的时间,实现了对指纹图像的快速识别。
在上述技术方案中,优选地,根据所述任一区域内的指纹特征的匹配率确定所述待识别的指纹图像与所述基准指纹图像是否匹配成功的步骤具体包括:若所述多个区域中的任一区域内的指纹特征的匹配率均大于或等于预定阈值,则确定所述待识别的指纹图像与所述基准指纹图像匹配成功,若所述多个区域中的任一区域内的指纹特征的匹配率均小于所述预定阈值,则确定所述待识别的指纹图像与所述基准指纹图像匹配失败。
在该技术方案中,通过在多个区域中的任一区域内的指纹特征的匹配率均大于或等于预定阈值时,确定待识别的指纹图像与基准指纹图像匹配成功,否则,确定待识别的指纹图像与基准指纹图像匹配失败,使得能够提高指纹匹配的准确性。
在上述技术方案中,优选地,将所述指纹图像划分为多个区域的步骤具体包括:将所述指纹图像划分为位于所述指纹图像中心位置的第一区域和位于所述第一区域外侧的第二区域。
在该技术方案中,指纹图像被划分成第一区域和第二区域,其中第一区域位于指纹图像中心位置,其包含的指纹信息量比较多;第二区域位于第一区域外侧,其包含的指纹信息量少于第一区域。另外,本申请对指纹图像的划分区域的多少和划分方式并不限定,本领域的技术人员可以根据实际需求进行划
分。
在上述技术方案中,优选地,根据与所述多个区域中的任一区域相对应的指纹匹配算法将所述任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配的步骤具体包括:对所述第一区域采用全匹配算法进行匹配,对所述第二区域采用多个特征点的匹配算法进行匹配。
在该技术方案中,由于第一区域包含的指纹信息最多,所以通过对第一区域采用全匹配算法进行匹配,有效地提高了指纹信息的利用率,有利于提高指纹识别的准确性;由于第二区域包含的指纹信息量相对较少,所以通过采用多个特征点的匹配算法进行匹配,而非采用全匹配算法进行匹配,使得能够大大缩短整个指纹识别过程所耗费的时间。
在上述技术方案中,优选地,对所述第一区域采用全匹配算法进行匹配的步骤具体包括:对所述第一区域进行图像增强处理,得到处理后的图像;提取所述处理后的图像中的特征信息,以与所述基准指纹图像的对应区域内的特征进行匹配。
根据本发明的第二方面,还提出了一种指纹识别的装置,包括:采集单元,用于采集待识别的指纹图像;划分单元,用于将所述指纹图像划分为多个区域;匹配处理单元,用于根据与所述多个区域中的任一区域相对应的指纹匹配算法将所述任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配;确定单元,用于根据所述任一区域内的指纹特征的匹配率确定所述待识别的指纹图像与所述基准指纹图像是否匹配成功。
在该技术方案中,由于指纹图像的不同位置包含的指纹信息量不同,因此通过将采集到指纹图像划分为多个区域,以根据与多个区域中的任一区域相对应的指纹匹配算法将任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配,并根据任一区域内的指纹特征的匹配率确定待识别的指纹图像与基准指纹图像是否匹配成功,使得能够针对任一区域内包含的信息量的多少采取相应的匹配算法进行匹配,并且能够对不同区域内的指纹信息都进行有效提取,从而提高了指纹识别过程中指纹信息的利用率,有利于提高指纹识别的成功率和准确性。
另外,相比于现有技术中对整个指纹图像进行处理的方案,本发明的技术方案由于仅对划分的多个区域进行相关处理,因此可以有效降低指纹识别过程
中指纹信息的存储空间,同时缩短了整个指纹识别过程所耗费的时间,实现了对指纹图像的快速识别。
在上述技术方案中,优选地,所述确定单元具体用于:若所述多个区域中的任一区域内的指纹特征的匹配率均大于或等于预定阈值,则确定所述待识别的指纹图像与所述基准指纹图像匹配成功,若所述多个区域中的任一区域内的指纹特征的匹配率均小于所述预定阈值,则确定所述待识别的指纹图像与所述基准指纹图像匹配失败。
在该技术方案中,通过在多个区域中的任一区域内的指纹特征的匹配率均大于或等于预定阈值时,确定待识别的指纹图像与基准指纹图像匹配成功,否则,确定待识别的指纹图像与基准指纹图像匹配失败,使得能够提高指纹匹配的准确性。
在上述技术方案中,优选地,所述划分单元具体用于:将所述指纹图像划分为位于所述指纹图像中心位置的第一区域和位于所述第一区域外侧的第二区域。
在该技术方案中,指纹图像被划分成第一区域和第二区域,其中第一区域位于指纹图像中心位置,其包含的指纹信息量比较多;第二区域位于第一区域外侧,其包含的指纹信息量少于第一区域。另外,本申请对指纹图像的划分区域的多少和划分方式并不限定,本领域的技术人员可以根据实际需求进行划分。
在上述技术方案中,优选地,所述匹配处理单元具体用于:对所述第一区域采用全匹配算法进行匹配,对所述第二区域采用多个特征点的匹配算法进行匹配。
在该技术方案中,由于第一区域包含的指纹信息最多,所以通过对第一区域采用全匹配算法进行匹配,有效地提高了指纹信息的利用率,有利于提高指纹识别的准确性;由于第二区域包含的指纹信息量相对较少,所以通过采用多个特征点的匹配算法进行匹配,而非采用全匹配算法进行匹配,使得能够大大缩短整个指纹识别过程所耗费的时间。
在上述技术方案中,优选地,所述匹配处理单元对所述第一区域采用全匹配算法进行匹配的操作具体包括:对所述第一区域进行图像增强处理,得到处理后的图像;提取所述处理后的图像中的特征信息,以与所述基准指纹图像的
对应区域内的特征进行匹配。
根据本发明的第三方面,还提出了一种终端,包括:如上述任一项技术方案中所述的指纹识别的装置。
通过以上技术方案,通过将采集到的指纹图像进行不同区域划分,并对不同区域采用不同的算法进行处理,不仅能够快速地进行指纹识别,而且能够提高指纹识别过程中指纹信息的利用率,进而提高了指纹识别的成功率和准确性。
图1示出了相关技术中对采集到的指纹图像进行处理的效果示意图;
图2示出了根据本发明的一个实施例的指纹识别的方法的示意流程图;
图3示出了根据本发明的一个实施例的指纹识别的装置的示意框图;
图4示出了根据本发明的一个实施例的对指纹图像划分区域的示意图;
图5示出了对图4中所示的区域404进行特征点提取的示意图;
图6示出了对图4中所示的不同区域进行匹配的示意图。
为了能够更清楚地理解本发明的上述目的、特征和优点,下面结合附图和具体实施方式对本发明进行进一步的详细描述。需要说明的是,在不冲突的情况下,本申请的实施例及实施例中的特征可以相互组合。
在下面的描述中阐述了很多具体细节以便于充分理解本发明,但是,本发明还可以采用其他不同于在此描述的其他方式来实施,因此,本发明的保护范围并不受下面公开的具体实施例的限制。
图2示出了根据本发明的一个实施例的指纹识别的方法的示意流程图。
如图2所示,根据本发明的一个实施例的指纹识别的方法,包括:步骤202,采集待识别的指纹图像;步骤204,将所述指纹图像划分为多个区域,并根据与所述多个区域中的任一区域相对应的指纹匹配算法将所述任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配;步骤206,根据所述任一区域内的指纹特征的匹配率确定所述待识别的指纹图像与所述基准指纹图像是否匹配成功。
在该技术方案中,由于指纹图像的不同位置包含的指纹信息量不同,因此通过将采集到指纹图像划分为多个区域,以根据与多个区域中的任一区域相对应的指纹匹配算法将任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配,并根据任一区域内的指纹特征的匹配率确定待识别的指纹图像与基准指纹图像是否匹配成功,使得能够针对任一区域内包含的信息量的多少采取相应的匹配算法进行匹配,并且能够对不同区域内的指纹信息都进行有效提取,从而提高了指纹识别过程中指纹信息的利用率,有利于提高指纹识别的成功率和准确性。
另外,相比于现有技术中对整个指纹图像进行处理的方案,本发明的技术方案由于仅对划分的多个区域进行相关处理,因此可以有效降低指纹识别过程中指纹信息的存储空间,同时缩短了整个指纹识别过程所耗费的时间,实现了对指纹图像的快速识别。
在上述技术方案中,优选地,根据所述任一区域内的指纹特征的匹配率确定所述待识别的指纹图像与所述基准指纹图像是否匹配成功的步骤具体包括:若所述多个区域中的任一区域内的指纹特征的匹配率均大于或等于预定阈值,则确定所述待识别的指纹图像与所述基准指纹图像匹配成功,若所述多个区域中的任一区域内的指纹特征的匹配率均小于所述预定阈值,则确定所述待识别的指纹图像与所述基准指纹图像匹配失败。
在该技术方案中,通过在多个区域中的任一区域内的指纹特征的匹配率均大于或等于预定阈值时,确定待识别的指纹图像与基准指纹图像匹配成功,否则,确定待识别的指纹图像与基准指纹图像匹配失败,使得能够提高指纹匹配的准确性。
在上述技术方案中,优选地,将所述指纹图像划分为多个区域的步骤具体包括:将所述指纹图像划分为位于所述指纹图像中心位置的第一区域和位于所述第一区域外侧的第二区域。
在该技术方案中,指纹图像被划分成第一区域和第二区域,其中第一区域位于指纹图像中心位置,其包含的指纹信息量比较多;第二区域位于第一区域外侧,其包含的指纹信息量少于第一区域。另外,本申请对指纹图像的划分区域的多少和划分方式并不限定,本领域的技术人员可以根据实际需求进行划分。
在上述技术方案中,优选地,根据与所述多个区域中的任一区域相对应的指纹匹配算法将所述任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配的步骤具体包括:对所述第一区域采用全匹配算法进行匹配,对所述第二区域采用多个特征点的匹配算法进行匹配。
在该技术方案中,由于第一区域包含的指纹信息最多,所以通过对第一区域采用全匹配算法进行匹配,有效地提高了指纹信息的利用率,有利于提高指纹识别的准确性;由于第二区域包含的指纹信息量相对较少,所以通过采用多个特征点的匹配算法进行匹配,而非采用全匹配算法进行匹配,使得能够大大缩短整个指纹识别过程所耗费的时间。
在上述技术方案中,优选地,对所述第一区域采用全匹配算法进行匹配的步骤具体包括:对所述第一区域进行图像增强处理,得到处理后的图像;提取所述处理后的图像中的特征信息,以与所述基准指纹图像的对应区域内的特征进行匹配。
图3示出了根据本发明的一个实施例的指纹识别的装置的示意框图。
如图3所示,根据本发明的一个实施例的指纹识别的装置300,包括:采集单元302、划分单元304、匹配处理单元306和确定单元308。
其中,采集单元302,用于采集待识别的指纹图像;划分单元304,用于将所述指纹图像划分为多个区域;匹配处理单元306,用于根据与所述多个区域中的任一区域相对应的指纹匹配算法将所述任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配;确定单元308,用于根据所述任一区域内的指纹特征的匹配率确定所述待识别的指纹图像与所述基准指纹图像是否匹配成功。
在该技术方案中,由于指纹图像的不同位置包含的指纹信息量不同,因此通过将采集到指纹图像划分为多个区域,以根据与多个区域中的任一区域相对应的指纹匹配算法将任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配,并根据任一区域内的指纹特征的匹配率确定待识别的指纹图像与基准指纹图像是否匹配成功,使得能够针对任一区域内包含的信息量的多少采取相应的匹配算法进行匹配,并且能够对不同区域内的指纹信息都进行有效提取,从而提高了指纹识别过程中指纹信息的利用率,有利于提高指纹识别的成功率和准确性。
另外,相比于现有技术中对整个指纹图像进行处理的方案,本发明的技术方案由于仅对划分的多个区域进行相关处理,因此可以有效降低指纹识别过程中指纹信息的存储空间,同时缩短了整个指纹识别过程所耗费的时间,实现了对指纹图像的快速识别。
在上述技术方案中,优选地,所述确定单元308具体用于:若所述多个区域中的任一区域内的指纹特征的匹配率均大于或等于预定阈值,则确定所述待识别的指纹图像与所述基准指纹图像匹配成功,若所述多个区域中的任一区域内的指纹特征的匹配率均小于所述预定阈值,则确定所述待识别的指纹图像与所述基准指纹图像匹配失败。
在该技术方案中,通过在多个区域中的任一区域内的指纹特征的匹配率均大于或等于预定阈值时,确定待识别的指纹图像与基准指纹图像匹配成功,否则,确定待识别的指纹图像与基准指纹图像匹配失败,使得能够提高指纹匹配的准确性。
在上述技术方案中,优选地,所述划分单元304具体用于:将所述指纹图像划分为位于所述指纹图像中心位置的第一区域和位于所述第一区域外侧的第二区域。
在该技术方案中,指纹图像被划分成第一区域和第二区域,其中第一区域位于指纹图像中心位置,其包含的指纹信息量比较多;第二区域位于第一区域外侧,其包含的指纹信息量少于第一区域。另外,本申请对指纹图像的划分区域的多少和划分方式并不限定,本领域的技术人员可以根据实际需求进行划分。
在上述技术方案中,优选地,所述匹配处理单元306具体用于:对所述第一区域采用全匹配算法进行匹配,对所述第二区域采用多个特征点的匹配算法进行匹配。
在该技术方案中,由于第一区域包含的指纹信息最多,所以通过对第一区域采用全匹配算法进行匹配,有效地提高了指纹信息的利用率,有利于提高指纹识别的准确性;由于第二区域包含的指纹信息量相对较少,所以通过采用多个特征点的匹配算法进行匹配,而非采用全匹配算法进行匹配,使得能够大大缩短整个指纹识别过程所耗费的时间。
在上述技术方案中,优选地,所述匹配处理单元306对所述第一区域采用
全匹配算法进行匹配的操作具体包括:对所述第一区域进行图像增强处理,得到处理后的图像;提取所述处理后的图像中的特征信息,以与所述基准指纹图像的对应区域内的特征进行匹配。
本发明还提出了一种终端(图中未示出),包括:如图3中所示的指纹识别的装置300。
以下对本发明的技术方案进一步说明。
如图4所示,对指纹采集器采集到指纹图像进行区域划分,划分为位于指纹图像中心位置的区域402和位于区域402外侧的区域404,并且区域402的大小小于图1中所示的图像102所占用的区域大小。并且划分后的区域402和区域404所包含的图像占用的存储空间小于图1中所示的图像102所占用的存储空间。
对于区域402,可以进行图像增强和特征信息提取,对于区域404可以进行多点特征信息的提取,以获取多个特征点信息,如图5中所示的黑色圆点表示提取到的特征点,这些特征点具备特征明显,信息量强的特点。
将图4和图5中处理过的指纹图像与指纹模板图像进行匹配时,如图6所示,对指纹图像的不同区域采用不同的匹配算法,具体地,对区域402采用全匹配算法,对区域402内的特征信息进行逐一的匹配,得到匹配率P1;对区域404中的单点特征信息进行匹配,得到匹配率P2,并在P1和P2的匹配率均大于或等于P3(P3是预先设定的匹配成功的阀值)时,判定匹配成功,否则匹配失败。
本发明的上述技术方案有以下优点:
1、小于现有指纹识别的存储空间。图4中所示的区域402的存储空间+区域404的存储空间<图1中所示的指纹图像分割后的图像102的存储空间;
2、匹配时间小于图1所示方案的匹配时间。区域402小于图1中所示的分割后的图像102,所以区域402的匹配时间小于图像102的匹配时间,而区域404中只是做多点特征的匹配,所以图4的匹配时间<图1的匹配时间。
3、具有更准确,充足的指纹特征信息。在图4中,区域402的指纹信息是最容易提取到而且是信息量最多的部分;对于区域404只做多点特征的提取,是提高指纹信息利用率,以及提高指纹匹配准确度的最佳方案;对于其他图像部分进行舍弃,因为该部分信息不一定能够提取到(限于目前手机上指纹
模组的大小),舍弃该部分也不影响匹配的成功率。
以上结合附图详细说明了本发明的技术方案,本发明提出了一种新的指纹识别的方案,通过将采集到的指纹图像进行不同区域划分,并对不同区域采用不同的算法进行处理,不仅能够快速地进行指纹识别,而且能够提高指纹识别过程中指纹信息的利用率,进而提高了指纹识别的成功率和准确性。
以上所述仅为本发明的优选实施例而已,并不用于限制本发明,对于本领域的技术人员来说,本发明可以有各种更改和变化。凡在本发明的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本发明的保护范围之内。
Claims (10)
- 一种指纹识别的方法,其特征在于,包括:采集待识别的指纹图像;将所述指纹图像划分为多个区域,并根据与所述多个区域中的任一区域相对应的指纹匹配算法将所述任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配;根据所述任一区域内的指纹特征的匹配率确定所述待识别的指纹图像与所述基准指纹图像是否匹配成功。
- 根据权利要求1所述的指纹识别的方法,其特征在于,根据所述任一区域内的指纹特征的匹配率确定所述待识别的指纹图像与所述基准指纹图像是否匹配成功的步骤具体包括:若所述多个区域中的任一区域内的指纹特征的匹配率均大于或等于预定阈值,则确定所述待识别的指纹图像与所述基准指纹图像匹配成功,若所述多个区域中的任一区域内的指纹特征的匹配率均小于所述预定阈值,则确定所述待识别的指纹图像与所述基准指纹图像匹配失败。
- 根据权利要求1或2所述的指纹识别的方法,其特征在于,将所述指纹图像划分为多个区域的步骤具体包括:将所述指纹图像划分为位于所述指纹图像中心位置的第一区域和位于所述第一区域外侧的第二区域。
- 根据权利要求3所述的指纹识别的方法,其特征在于,根据与所述多个区域中的任一区域相对应的指纹匹配算法将所述任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配的步骤具体包括:对所述第一区域采用全匹配算法进行匹配,对所述第二区域采用多个特征点的匹配算法进行匹配。
- 根据权利要求4所述的指纹识别的方法,其特征在于,对所述第一区域采用全匹配算法进行匹配的步骤具体包括:对所述第一区域进行图像增强处理,得到处理后的图像;提取所述处理后的图像中的特征信息,以与所述基准指纹图像的对应区域内的特征进行匹配。
- 一种指纹识别的装置,其特征在于,包括:采集单元,用于采集待识别的指纹图像;划分单元,用于将所述指纹图像划分为多个区域;匹配处理单元,用于根据与所述多个区域中的任一区域相对应的指纹匹配算法将所述任一区域内的指纹特征与基准指纹图像的对应区域内的特征进行匹配;确定单元,用于根据所述任一区域内的指纹特征的匹配率确定所述待识别的指纹图像与所述基准指纹图像是否匹配成功。
- 根据权利要求6所述的指纹识别的装置,其特征在于,所述确定单元具体用于:若所述多个区域中的任一区域内的指纹特征的匹配率均大于或等于预定阈值,则确定所述待识别的指纹图像与所述基准指纹图像匹配成功,若所述多个区域中的任一区域内的指纹特征的匹配率均小于所述预定阈值,则确定所述待识别的指纹图像与所述基准指纹图像匹配失败。
- 根据权利要求6或7所述的指纹识别的装置,其特征在于,所述划分单元具体用于:将所述指纹图像划分为位于所述指纹图像中心位置的第一区域和位于所述第一区域外侧的第二区域。
- 根据权利要求8所述的指纹识别的装置,其特征在于,所述匹配处理单元具体用于:对所述第一区域采用全匹配算法进行匹配,对所述第二区域采用多个特征点的匹配算法进行匹配。
- 根据权利要求9所述的指纹识别的装置,其特征在于,所述匹配处理单元对所述第一区域采用全匹配算法进行匹配的操作具体包括:对所述第一区域进行图像增强处理,得到处理后的图像;提取所述处理后的图像中的特征信息,以与所述基准指纹图像的对应区域内的特征进行匹配。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510420617.3A CN105608409B (zh) | 2015-07-16 | 2015-07-16 | 指纹识别的方法及装置 |
CN201510420617.3 | 2015-07-16 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017008349A1 true WO2017008349A1 (zh) | 2017-01-19 |
Family
ID=55988336
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2015/085828 WO2017008349A1 (zh) | 2015-07-16 | 2015-07-31 | 指纹识别的方法及装置 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN105608409B (zh) |
WO (1) | WO2017008349A1 (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109558611A (zh) * | 2017-09-27 | 2019-04-02 | 中芯国际集成电路制造(上海)有限公司 | 图形匹配方法及其匹配*** |
Families Citing this family (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10339178B2 (en) * | 2015-06-30 | 2019-07-02 | Samsung Electronics Co., Ltd. | Fingerprint recognition method and apparatus |
CN105975833B (zh) * | 2016-05-27 | 2019-04-09 | Oppo广东移动通信有限公司 | 一种指纹解锁方法及终端 |
CN106055952A (zh) * | 2016-05-27 | 2016-10-26 | 广东欧珀移动通信有限公司 | 一种指纹解锁方法、装置及用户终端 |
CN106022069B (zh) * | 2016-05-30 | 2019-08-20 | Oppo广东移动通信有限公司 | 一种解锁控制方法及移动终端 |
CN106096358B (zh) | 2016-05-30 | 2019-04-26 | Oppo广东移动通信有限公司 | 一种解锁控制方法及移动终端 |
CN106055961B (zh) * | 2016-05-31 | 2019-02-05 | Oppo广东移动通信有限公司 | 一种指纹解锁方法及移动终端 |
CN105912918B (zh) * | 2016-06-17 | 2019-04-02 | Oppo广东移动通信有限公司 | 一种指纹解锁方法及终端 |
CN106022074B (zh) * | 2016-06-17 | 2017-09-29 | 广东欧珀移动通信有限公司 | 一种指纹解锁方法及终端 |
CN106127000B (zh) * | 2016-06-17 | 2017-09-29 | 广东欧珀移动通信有限公司 | 一种指纹解锁方法及终端 |
CN105912919B (zh) * | 2016-06-17 | 2018-03-27 | 广东欧珀移动通信有限公司 | 一种指纹解锁方法及终端 |
CN106203151B (zh) * | 2016-06-21 | 2019-02-12 | Oppo广东移动通信有限公司 | 一种打开文件的方法及终端设备 |
CN107528691A (zh) * | 2016-06-21 | 2017-12-29 | 中兴通讯股份有限公司 | 通讯安全控制方法及可穿戴设备 |
CN106295559B (zh) * | 2016-08-08 | 2019-08-02 | 京东方科技集团股份有限公司 | 一种数据处理的方法、指纹识别装置以及显示装置 |
CN106250876B (zh) * | 2016-08-19 | 2019-10-22 | 深圳市金立通信设备有限公司 | 一种指纹识别方法及终端 |
CN106778557B (zh) * | 2016-11-30 | 2020-06-23 | 努比亚技术有限公司 | 指纹识别装置及方法 |
CN107066852B (zh) * | 2016-12-14 | 2021-03-05 | 上海摩软通讯技术有限公司 | 应用的密码生成方法及密码生成装置 |
KR102459852B1 (ko) * | 2017-02-08 | 2022-10-27 | 삼성전자주식회사 | 지문 인식을 위한 후보 지문 이미지를 선정하는 장치 및 방법 |
CN107111762A (zh) * | 2017-03-20 | 2017-08-29 | 深圳市汇顶科技股份有限公司 | 指纹识别方法和装置 |
CN106934389B (zh) * | 2017-04-20 | 2019-01-22 | 维沃移动通信有限公司 | 一种指纹识别方法及移动终端 |
CN107358183B (zh) * | 2017-06-30 | 2020-09-01 | Oppo广东移动通信有限公司 | 虹膜活体检测方法及相关产品 |
CN107341482B (zh) * | 2017-07-13 | 2020-07-10 | 海信视像科技股份有限公司 | 指纹识别方法、装置及计算机可读存储介质 |
CN107980140B (zh) * | 2017-10-16 | 2021-09-14 | 厦门熵基科技有限公司 | 一种掌静脉的识别方法及装置 |
CN108090475A (zh) * | 2018-01-17 | 2018-05-29 | 深圳市爱克信智能股份有限公司 | 一种指纹识别算法 |
CN108182424B (zh) * | 2018-01-29 | 2020-05-22 | 上海天马微电子有限公司 | 显示装置及其指纹识别方法 |
CN108304709B (zh) * | 2018-01-31 | 2022-01-04 | Oppo广东移动通信有限公司 | 人脸解锁方法及相关产品 |
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*** |
TW202215289A (zh) * | 2020-10-14 | 2022-04-16 | 王建華 | 用於指紋圖像識別的方法、設備及計算機可讀介質 |
CN115984948B (zh) * | 2023-03-20 | 2023-05-26 | 广东广新信息产业股份有限公司 | 应用于温度感测的人脸识别方法及电子设备 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1512437A (zh) * | 2002-12-30 | 2004-07-14 | 北京汉王科技有限公司 | 多功能脱机***机 |
CN1521684A (zh) * | 2003-02-13 | 2004-08-18 | 合肥工业大学 | 协同指纹识别方法 |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1664847A (zh) * | 2005-03-17 | 2005-09-07 | 上海交通大学 | 嵌入式***指纹的识别与匹配方法 |
CN100492395C (zh) * | 2006-03-28 | 2009-05-27 | 北京握奇数据***有限公司 | 指纹特征快速匹配方法、装置及其应用 |
EP2600307B1 (en) * | 2010-07-29 | 2020-12-02 | Fujitsu Limited | Biometric authentication device, biometric authentication method and computer program for biometric authentication |
CN104036266A (zh) * | 2014-07-03 | 2014-09-10 | 南昌欧菲生物识别技术有限公司 | 指纹注册方法、指纹识别方法、指纹识别装置及终端设备 |
-
2015
- 2015-07-16 CN CN201510420617.3A patent/CN105608409B/zh active Active
- 2015-07-31 WO PCT/CN2015/085828 patent/WO2017008349A1/zh active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1512437A (zh) * | 2002-12-30 | 2004-07-14 | 北京汉王科技有限公司 | 多功能脱机***机 |
CN1521684A (zh) * | 2003-02-13 | 2004-08-18 | 合肥工业大学 | 协同指纹识别方法 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109558611A (zh) * | 2017-09-27 | 2019-04-02 | 中芯国际集成电路制造(上海)有限公司 | 图形匹配方法及其匹配*** |
CN109558611B (zh) * | 2017-09-27 | 2023-04-07 | 中芯国际集成电路制造(上海)有限公司 | 图形匹配方法及其匹配*** |
Also Published As
Publication number | Publication date |
---|---|
CN105608409B (zh) | 2019-01-11 |
CN105608409A (zh) | 2016-05-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2017008349A1 (zh) | 指纹识别的方法及装置 | |
US10043061B2 (en) | Facial matching system | |
WO2017080278A1 (zh) | 指纹识别方法、装置及终端设备 | |
US8995774B1 (en) | Automated document recognition, identification, and data extraction | |
WO2017206914A1 (zh) | 指纹识别方法、指纹识别***、及电子设备 | |
TWI437501B (zh) | 基於生物特徵之身分驗證裝置及其方法 | |
KR20050010102A (ko) | 손가락의 슬라이딩/롤링에 따른 지문영상획득방법 | |
WO2019042195A1 (zh) | 一种人体目标身份识别方法及装置 | |
CN108009472A (zh) | 一种基于卷积神经网络和贝叶斯分类器的指背关节纹识别方法 | |
WO2010069166A1 (zh) | 快速指纹搜索方法及快速指纹搜索*** | |
Bong et al. | Palm print verification system | |
WO2017054276A1 (zh) | 一种生物特征身份识别方法及装置 | |
JP2008251029A (ja) | 文字認識装置、ナンバープレート認識システム | |
US11651618B2 (en) | Fingerprint identification method and apparatus, storage medium and terminal | |
CN116758590B (zh) | 用于身份认证的手掌特征处理方法、装置、设备和介质 | |
CN110765856B (zh) | 基于卷积的低质量手指静脉图像边缘检测算法 | |
TWI744647B (zh) | 提升指紋識別率的指紋識別方法及指紋識別晶片 | |
CN111222367B (zh) | 一种指纹识别方法及装置、存储介质、终端 | |
KR20160127206A (ko) | 홍채영역에서의 속눈썹 제거 시스템 및 그 방법 | |
CN108537213A (zh) | 增强虹膜识别精度的***和方法 | |
CN108009464B (zh) | 一种指纹识别方法和装置 | |
Dahia et al. | Automatic dataset annotation to learn CNN pore description for fingerprint recognition | |
JP2008217688A (ja) | 照合装置 | |
CN111191550B (zh) | 一种基于图像锐度自动动态调整的视觉感知装置及方法 | |
Patil et al. | Neural network based fingerprint classification |
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: 15898076 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: 15898076 Country of ref document: EP Kind code of ref document: A1 |