CN111435558A - Identity authentication method and device based on biological characteristic multi-mode image - Google Patents
Identity authentication method and device based on biological characteristic multi-mode image Download PDFInfo
- Publication number
- CN111435558A CN111435558A CN201811598761.6A CN201811598761A CN111435558A CN 111435558 A CN111435558 A CN 111435558A CN 201811598761 A CN201811598761 A CN 201811598761A CN 111435558 A CN111435558 A CN 111435558A
- Authority
- CN
- China
- Prior art keywords
- authentication
- palm
- detection
- image frame
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00563—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns
-
- 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
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
Abstract
The application discloses an identity authentication method based on biological characteristic images, which comprises the steps of obtaining images of various biological characteristic modalities; respectively executing detection identification authentication processes of each mode of biological characteristics in parallel on the same obtained image frame, and respectively obtaining authentication results of each mode process; judging identity authentication according to the authentication result of each modal process; the biometric modalities comprise at least two biometric modalities, and each biometric modality corresponds to a detection, identification and authentication process of the biometric modality. According to the method and the device, the images do not need to be distinguished by the control unit, so that the processing time for distinguishing the image frames by the control unit is saved; the parallel process processing has a more flexible and reliable mechanism, avoids delay and mutual dependence brought by serial processing, and judges the authentication results of the processes respectively obtained, so that the response of identity authentication is rapid, and the user experience is improved.
Description
Technical Field
The invention relates to the field of biological characteristic image recognition, in particular to an identity authentication method and device based on biological characteristic multi-mode images.
Background
Biometric identification technology is classified as one of ten major technologies that revolutionized human society in the 21 st century. The biological characteristic recognition technology is the most convenient and safe identity recognition technology at present, and people can be identified without external markers. The biological characteristic identification technology utilizes physiological characteristics and behavior characteristics of people to carry out identity identification, and mainly comprises fingerprint identification, face identification, iris identification, gait identification and the like, vein identification and palm print identification.
Currently, fusion recognition based on multi-modal biometric features has been widely applied. For example, a palm print and face fusion identification identity authentication method and device disclosed in publication No. CN 102332093. In the technical scheme, a control unit is mainly used for capturing pictures, then a face image and a palm print image are automatically distinguished, and if the face image is the face image, the face image is sent to a face recognition unit; if the image is a palm print image, sending the image into a palm print identification unit; in the identity authentication process, only after the authentication based on the face recognition is successful, the authentication based on the palm print recognition is carried out. The detection, identification and authentication processes based on the face image and the palm print image are all in a serial running mode, so that the identification and authentication processes are long, the efficiency is low, and the user experience is influenced.
Disclosure of Invention
The invention provides an identity authentication method based on a biological characteristic multi-mode image, which aims to improve the efficiency of an identity authentication process based on a biological characteristic image.
The application provides an identity authentication method based on a multi-mode image of biological characteristics, which comprises the following steps,
acquiring images of various biological characteristics modals;
respectively executing detection identification authentication processes of each mode of biological characteristics in parallel on the same obtained image frame, and respectively obtaining authentication results of each mode process;
according to the detection and identification of each mode, the authentication result of the authentication process is judged;
the biometric modalities comprise at least two biometric modalities, and each biometric modality corresponds to a detection, identification and authentication process of the biometric modality.
The application provides an identity authentication device based on a multi-mode image of biological characteristics, which comprises,
the image acquisition unit is used for acquiring images of all the modalities of biological characteristics and outputting the acquired same image frame to all the biological characteristic authentication module units in parallel;
each biological characteristic authentication module respectively executes the detection, identification and authentication processes of each mode of the biological characteristics in parallel and respectively outputs the authentication results of each mode to the judgment unit;
the judging unit judges whether the identity authentication is passed or not according to each authentication result from the biological characteristic authentication module;
the biometric authentication module comprises at least two biometric authentication modules; the detection, identification and authentication process of each biological characteristic mode is respectively operated in a biological characteristic authentication module.
Preferably, the authentication module based on palm print detection and identification comprises a microprocessor,
initiating gesture detection;
judging whether the detected gesture is a palm gesture of five fingers, and if so, starting palm print detection;
segmenting a palm center position and a palm center area from the image frame; edge detection is carried out on the segmented palm center area, and palm print image frames with rich textures are selected preferably according to the result of the edge detection;
extracting palm print features based on the preferred palm print image frames;
and matching the extracted first palm print characteristic with a pre-stored second palm print characteristic, and outputting an authentication result which passes the authentication if the matching is successful.
The method comprises the steps of carrying out edge detection on a segmented palm area, preferably selecting a palm print image frame with rich textures according to an edge detection result, carrying out Sobel edge detection on the segmented palm area, judging whether the ratio of edge texture pixel points to all pixel points in the palm area is larger than or equal to a preset threshold value or not, if so, taking the current image frame as the preferred palm print image frame, and otherwise, starting gesture detection.
The method and the device have the advantages that the same obtained image frame is used for executing the detection, identification and authentication processes of all the biological feature modes respectively in parallel, a control unit is not needed for distinguishing the image, and the processing time for distinguishing the image frame by the control unit is saved; the parallel process processing has a more flexible and reliable mechanism, avoids delay and mutual dependence brought by serial processing, and judges the authentication results of the processes respectively obtained, so that the response of identity authentication is rapid, and the user experience is improved.
Drawings
Fig. 1 is a schematic diagram of a hardware structure of an identity authentication device based on a multi-modal biometric image according to an embodiment of the present application;
fig. 2 is another schematic diagram of the hardware structure of an identity authentication device based on a multi-modal biometric image.
Fig. 3 is a schematic flow chart of an authentication method based on face detection and identification and palm print detection and identification.
Detailed Description
For the purpose of making the objects, technical means and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings.
In order to solve the problem of long process caused by serial processing of fusion recognition and authentication of biological characteristic multiple modes in the prior art, the image recognition and authentication based on the biological characteristic multiple modes are processed in parallel, and the authentication result of the parallel processing is judged, so that the authentication efficiency is effectively improved.
Referring to fig. 1, fig. 1 is a schematic diagram of a hardware structure of an identity authentication apparatus based on a multi-modal biometric image according to an embodiment of the present application. The authentication device comprises a trigger unit for outputting a wake-up signal to trigger an image acquisition unit to acquire an image; the acquired same image frame is output to the image acquisition units of at least more than two biological characteristic authentication modules in parallel at the same time sequence; in at least more than two biological characteristic authentication modules, each module comprises a microprocessor used for biological characteristic-mode authentication, the biological characteristic modes comprise but are not limited to fingerprints, human faces, irises, gaits, veins, palmprints and the like, and after each biological characteristic authentication module carries out mode detection, identification and authentication of biological characteristics, authentication results are respectively output to a judgment unit; the determination unit determines whether the authentication is passed or not based on the weighted authentication result.
Wherein the content of the first and second substances,
in order to avoid the consumption of electric energy caused by the fact that the image acquisition unit is in a real-time acquisition state, the triggering unit outputs a wake-up signal through a sensing signal of the sensor so as to trigger the image acquisition unit to be switched from a dormant state to a real-time acquisition state; the trigger unit may trigger the generation of the wake-up signal based on a sensor sensing signal such as spectral sensing, current sensing, sound sensing, thermal sensing, living body sensing, etc.
Since the detection and identification accuracy and reliability of each mode of the biometric features are different, and the confidence degrees of the authentication results are different, the authentication results from each biometric feature authentication module can be weighted, and when the weighting result is greater than a preset first threshold value, the authentication is judged to be passed. The judgment processing mode can improve the reliability of authentication and is suitable for application with higher confidentiality requirement level; for applications with low security requirement level, the determination unit may perform an or logical operation on the authentication result, that is, determine that the authentication is passed as long as the authentication of any modality of the biometric features is passed.
Each biological characteristic authentication module also comprises a memory for storing programs for biological characteristic modal detection and identification authentication, and the programs stored in the memory are executed by the respective microprocessor to realize the authentication based on the biological characteristic modal; because each biological characteristic authentication module has an independent microprocessor and a memory, the efficiency of parallel authentication is favorably provided. In another embodiment, referring to fig. 2, fig. 2 is another schematic diagram of a hardware structure of an identity authentication device based on a multi-modal biometric image. The implementation mode can reduce the cost of hardware, wherein programs for performing modal detection, identification and authentication of the biological characteristics are respectively stored in different address spaces of the same memory.
The following description will be made based on authentication based on face detection recognition and palm print detection recognition, taking an access control application as an example. Referring to fig. 3, fig. 3 is a schematic view of a flow of an authentication method based on face detection and palm print detection, in which an authentication process based on palm print detection and identification is executed in a palm print authentication module, and an authentication process based on face detection and identification is executed in a face authentication module; in this embodiment, the trigger unit employs a thermally-induced trigger unit.
The authentication process for palm print detection and identification comprises the following steps:
30513, segmenting the palm center position from the image frame, where the segmentation may be performed by using a skin detection and binarization method, for example, in three primary colors RGB (red, green, and blue) components in the image frame, if a determination condition of the foreground is satisfied: r is greater than 95, G is greater than 40, B is greater than or equal to 20, R is greater than or equal to G +15, R is greater than B, the current pixel is judged to be the foreground of the palm skin, and otherwise, the current pixel is judged to be the background; and after the whole image frame is subjected to foreground and background binarization distinguishing, selecting a foreground connected region of the largest skin as a divided palm center region.
For the segmented palm center region, Sobel edge detection is performed to determine whether there is abundant texture. If the ratio of the edge pixel points is greater than or equal to the set threshold, for example, the threshold is 2%, that is, the ratio of the edge texture pixel points to all pixel points in the palm center region is greater than or equal to 2%, determining that the preferred palm print image frame is credible, and using the preferred palm print image frame for identification in the subsequent step, otherwise, returning to step 30511.
Step 30515, determining whether the identification number is the registered identification number according to the similarity between the first palm print feature and the second palm print feature, that is, determining whether the authentication passes, if so, outputting the authentication result to the determining unit, otherwise, returning to execute step 30511.
In the above steps, the image frames with rich palm print textures are identified preferentially by using edge detection, so that a large amount of unnecessary palm print identification calculation is reduced, the process is effectively and quickly skipped back in advance, and the time consumption caused by continuously and directly identifying the palm prints and returning to re-executing the whole process when the identification result is not met or the identification fails in the technical scheme of the publication number CN102332093B is avoided.
The authentication process for face detection and recognition comprises the following steps:
step 30521, starting face detection, optionally, detecting the face by using Haar features and an AdaBoost cascade classification mode;
the preferred basis may be to perform screening based on the size of the face, for example, if the face pixels are less than 64 × 64, the process returns to step 30521, and if the face pixels are greater than or equal to 64 × 64, the image frame is taken as the preferred optimal face image frame.
And 30524, recognizing the human face based on the preferred human face image frame. In the present embodiment, SURF feature face recognition or deep learning based face recognition of the fast-RCNN network model is adopted.
30525, determining whether the identification number is the registered identification number according to the identification result, if so, outputting the authentication result to the determining unit, otherwise, returning to the step 30521.
The judging unit receives the authentication results from the palm print authentication module and the face authentication module respectively, and once the authentication result of any module is authenticated, the judging unit judges that the identity authentication is passed and starts an unlocking mechanism of the entrance guard.
The palm print authentication is adopted in the embodiment, and compared with other modalities of biological characteristics, the palm print authentication has the following advantages: compared with the fingerprint, the palm print has larger identification area, is relatively not easy to be worn and contains more characteristic information; compared with the human face, the palm print is not influenced by factors such as glasses, expressions, easiness and the like, the stability is high, and in the aspect of user acceptance, the collection mode of the palm print is more friendly to the user; compared with the iris, the palm print acquisition device has obvious advantages in the aspects of equipment cost and identification adaptability compared with the iris, although the accuracy of the palm print cannot reach the iris level; compared with sound, although voiceprints are a very potential technical way, in some silent scenes, palmprints have complementary advantages, and voiceprints have unstable change characteristics along with the growth of time; compared with handwriting, signature handwriting has unstable change characteristics along with time and is easy to forge; relative to gait, gait has some unstable changing characteristics over time and is easy to forge; compared with DNA, DNA belongs to the field of professional medicine, and has high cost and wide application range.
Compared with the technical scheme of the publication number CN102332093B, the embodiment of the application does not need a control unit to distinguish the images, thereby saving the processing time for distinguishing the image frames by the control unit; the image is identified based on the optimized optimal image frame, so that the image identification efficiency is further improved; the parallel process processing has a more flexible and reliable mechanism, avoids delay and mutual dependence brought by serial processing, enables the response of the identity authentication to be rapid, and improves the user experience.
In the embodiment of the present application, the Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), for example, at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The microprocessor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the following steps:
acquiring images of various biological characteristics modals;
respectively executing detection identification authentication processes of each mode of biological characteristics in parallel on the same obtained image frame, and respectively obtaining authentication results of each mode process;
judging identity authentication according to the authentication result of each modal process;
the biometric modalities comprise at least two biometric modalities, and each biometric modality corresponds to a detection, identification and authentication process of the biometric modality.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (32)
1. An identity authentication method based on a multi-mode image with biological characteristics is characterized by comprising the following steps,
acquiring images of various biological characteristics modals;
respectively executing detection identification authentication processes of each mode of biological characteristics in parallel on the same obtained image frame, and respectively obtaining authentication results of each mode process;
according to the detection and identification of each mode, the authentication result of the authentication process is judged;
the biometric modalities comprise at least two biometric modalities, and each biometric modality corresponds to a detection, identification and authentication process of the biometric modality.
2. The method of claim 1, wherein the acquiring images of the biometric modalities further comprises triggering acquisition of images of the biometric modalities according to a trigger condition;
the detection, identification and authentication processes of all the biological characteristics are respectively operated in all the biological characteristic authentication modules at least composed of microprocessors.
3. The method according to claim 1, wherein the determining of the identity authentication according to the authentication result of each modal process comprises weighting the authentication result of each modal process, and determining the identity authentication according to the weighted result.
4. The method according to claim 1, wherein the determining of identity authentication according to the authentication result of each modal process comprises performing an or logical operation on the authentication result of each modal process, and performing identity authentication determination according to the or logical operation.
5. The method according to claim 2, wherein the triggering condition is whether the detected current temperature after the mutation in the effective range is greater than a set first temperature threshold value and whether the change in the temperature is greater than or equal to a preset temperature change threshold value.
6. The method of claim 2, wherein the biometric modalities are a palm print and a human face; the detection, identification and authentication processes of the biological characteristics in the modes are respectively a palm print detection, identification and authentication process and a face detection, identification and authentication process.
7. The method of claim 6, wherein the detection of the palm print identifies an authentication process comprising,
initiating gesture detection;
judging whether the detected gesture is a palm gesture of five fingers, and if so, starting palm print detection;
segmenting a palm center position and a palm center area from the image frame; edge detection is carried out on the segmented palm center area, and palm print image frames with rich textures are selected preferably according to the result of the edge detection;
extracting palm print features based on the preferred palm print image frames;
and matching the extracted first palm print characteristic with a pre-stored second palm print characteristic, and outputting an authentication result which passes the authentication if the matching is successful.
8. The method of claim 7, wherein the gesture detection adopts Haar features and AdaBoost cascade classification to detect gestures;
judging whether the detected gesture is a palm gesture with five fingers expanded or not comprises judging whether the gesture is the palm gesture with five fingers expanded or not according to confidence degrees of cascade classification, and if the confidence degree is higher than a preset confidence degree threshold value, judging that the gesture is the palm gesture.
9. The method of claim 7, wherein said segmenting the palm position and palm region from the image frames comprises,
judging whether red, green and blue three-component components in the image frame meet the judgment condition of the image foreground, if so, judging that the current pixel is the foreground of the palm skin, otherwise, judging that the current pixel is the background; and carrying out foreground and background binarization distinguishing on the image frame, and selecting a foreground connected region of the largest skin as a segmented palm area.
10. The method as claimed in claim 7, wherein the edge detection is performed on the segmented palm center region, and the selecting the palm print image frame with rich texture based on the result of the edge detection comprises,
and performing Sobel edge detection on the segmented palm region, judging whether the ratio of edge texture pixel points to all pixel points in the palm region is greater than or equal to a preset threshold value, if so, taking the current image frame as a preferred palm print image frame, and otherwise, starting gesture detection.
11. The method of claim 6, wherein the detecting of the face identifies an authentication process comprising,
starting face detection;
judging whether the image frame comprises a human face or not, and if so, preferably selecting the optimal human face image frame;
performing face recognition based on the preferred face image frame;
and outputting an authentication result which passes the authentication according to the identification result.
12. The method of claim 11, wherein the face recognition adopts Haar features and an AdaBoost cascade classification mode to detect the face;
and judging whether the image frame comprises a face or not according to the confidence coefficient of the cascade classification, and if the confidence coefficient is higher than a preset confidence coefficient threshold, judging that the image frame comprises the face.
13. The method of claim 11, wherein said preferred best human face image frame comprises,
and screening according to the size of the face pixels, and if the face pixels are larger than the set pixel threshold value, taking the image frame as the optimal preferred face image frame.
14. The method of claim 11, wherein said preferred best human face image frame comprises,
and weighting the image frame based on the face angle, the face pixels and the face definition, and performing optimization according to the weighted value.
15. An identity authentication device based on multi-modal images of biological features, the device comprising,
the image acquisition unit is used for acquiring images of all the modalities of biological characteristics and outputting the acquired same image frame to all the biological characteristic authentication module units in parallel;
each biological characteristic authentication module respectively executes the detection, identification and authentication processes of each mode of the biological characteristics in parallel and respectively outputs the authentication results of each mode to the judgment unit;
the judging unit judges whether the identity authentication is passed or not according to each authentication result from the biological characteristic authentication module;
the biometric authentication module comprises at least two biometric authentication modules; the detection, identification and authentication process of each biological characteristic mode is respectively operated in a biological characteristic authentication module.
16. The apparatus of claim 15, further comprising,
and the triggering unit outputs a wake-up signal to the image acquisition unit according to the triggering condition so that the image acquisition unit is switched from a dormant state to a real-time acquisition state.
17. The apparatus according to claim 15, wherein each of the biometric authentication modules comprises a microprocessor for executing a biometric authentication procedure of the biometric mode, and a memory storing a code of the biometric authentication procedure; the microprocessors are connected with the memories in a one-to-one correspondence mode.
18. The apparatus according to claim 15, wherein each of the biometric authentication modules comprises a microprocessor for performing a detection recognition authentication process of the biometric mode; the detection, identification and authentication processes of the biological characteristics in the modes are respectively stored in the storage spaces of the same memory; the microprocessors are respectively connected with the memories.
19. The apparatus according to claim 15, wherein the determination unit weights each authentication result from the biometric authentication module, and determines whether or not the authentication is passed based on the weighted result.
20. The apparatus according to claim 15, wherein the determination unit performs an or logical operation on each authentication result from the biometric authentication module, and determines whether or not the authentication is passed based on a result of the logical operation.
21. The apparatus of claim 16, wherein the trigger unit further comprises a sensor to collect the sensing signal.
22. The apparatus of claim 21, wherein the sensor is a thermal sensor, and the triggering condition is whether a current temperature after a sudden change in the effective range detected by the thermal sensor is greater than a set first temperature threshold and a change in the temperature is greater than or equal to a preset temperature change threshold.
23. The apparatus of claim 15, wherein the biometric modalities are a palm print and a human face; the biometric authentication modules are respectively an authentication module based on palm print detection and identification and an authentication module based on face detection and identification; the detection, identification and authentication processes of the biological characteristics in the modes are a palm print detection, identification and authentication process and a face detection, identification and authentication process respectively.
24. The apparatus of claim 23, wherein the microprocessor of the authentication module based on palm print detection identification comprises,
initiating gesture detection;
judging whether the detected gesture is a palm gesture of five fingers, and if so, starting palm print detection;
segmenting a palm center position and a palm center area from the image frame; edge detection is carried out on the segmented palm center area, and palm print image frames with rich textures are selected preferably according to the result of the edge detection;
extracting palm print features based on the preferred palm print image frames;
and matching the extracted first palm print characteristic with a pre-stored second palm print characteristic, and outputting an authentication result which passes the authentication if the matching is successful.
25. The apparatus of claim 24, wherein the gesture detection employs Haar features and AdaBoost cascade classification for gesture detection;
judging whether the detected gesture is a palm gesture with five fingers expanded or not comprises judging whether the gesture is the palm gesture with five fingers expanded or not according to confidence degrees of cascade classification, and if the confidence degree is higher than a preset confidence degree threshold value, judging that the gesture is the palm gesture.
26. The apparatus of claim 24, wherein said segmenting the palm position and the palm region from the image frame comprises determining whether red, green and blue components in the image frame satisfy a determination condition of the image foreground, if so, determining that the current pixel is the foreground of the palm skin, otherwise, determining that the current pixel is the background; and carrying out foreground and background binarization distinguishing on the image frame, and selecting a foreground connected region of the largest skin as a segmented palm area.
27. The apparatus of claim 24, wherein the performing edge detection on the segmented palm area to select a palm print image frame with rich texture based on the result of the edge detection comprises performing Sobel edge detection on the segmented palm area to determine whether a ratio of edge texture pixel points to all pixel points in the palm area is greater than or equal to a preset threshold, and if so, taking the current image frame as the preferred palm print image frame, otherwise, initiating gesture detection.
28. The apparatus of claim 23, wherein the microprocessor of the authentication module based on face detection recognition comprises,
starting face detection;
judging whether the image frame comprises a human face or not, and if so, preferably selecting the optimal human face image frame;
performing face recognition based on the preferred face image frame;
and outputting an authentication result which passes the authentication according to the identification result.
29. The apparatus of claim 28, wherein the face recognition employs Haar features and AdaBoost cascade classification to detect the face;
and judging whether the image frame comprises a face or not according to the confidence coefficient of the cascade classification, and if the confidence coefficient is higher than a preset confidence coefficient threshold, judging that the image frame comprises the face.
30. The apparatus of claim 28, wherein said optimizing the best human face image frame comprises filtering based on a pixel size of the human face, and if the human face pixel is greater than a set pixel threshold, then treating the image frame as the preferred best human face image frame.
31. The apparatus of claim 28, wherein said optimizing the best face image frame comprises weighting the image frames based on face angle, face pixels, face sharpness, and optimizing based on weighting values.
32. A computer-readable storage medium storing a computer program for the biometric image-based identity authentication method according to any one of claims 1 to 14.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811598761.6A CN111435558A (en) | 2018-12-26 | 2018-12-26 | Identity authentication method and device based on biological characteristic multi-mode image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811598761.6A CN111435558A (en) | 2018-12-26 | 2018-12-26 | Identity authentication method and device based on biological characteristic multi-mode image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111435558A true CN111435558A (en) | 2020-07-21 |
Family
ID=71579731
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811598761.6A Pending CN111435558A (en) | 2018-12-26 | 2018-12-26 | Identity authentication method and device based on biological characteristic multi-mode image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111435558A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112183959A (en) * | 2020-09-10 | 2021-01-05 | 国网物资有限公司 | Safety control terminal, server and system for standard evaluation base |
| CN113420629A (en) * | 2021-06-17 | 2021-09-21 | 浙江大华技术股份有限公司 | Image processing method, device, equipment and medium |
| CN114780769A (en) * | 2022-06-13 | 2022-07-22 | 杭州合众数据技术有限公司 | Personnel checking method based on bloom filter |
| CN117173813A (en) * | 2023-08-18 | 2023-12-05 | 鹿客科技(北京)股份有限公司 | Door lock motor assembly control method, intelligent door lock and computer readable medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0749612A4 (en) * | 1994-03-11 | 1997-10-29 | Identix Inc | An electro-optic palm scanner system employing a non-planar platen |
| CN102332084A (en) * | 2010-07-23 | 2012-01-25 | 中国农业大学 | Identity identification method based on palm print and human face feature extraction |
| CN104680154A (en) * | 2015-03-13 | 2015-06-03 | 合肥工业大学 | Identity recognition method based on fusion of face characteristic and palm print characteristic |
| CN105913514A (en) * | 2016-04-08 | 2016-08-31 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| CN105930811A (en) * | 2016-04-26 | 2016-09-07 | 济南梦田商贸有限责任公司 | Palm texture feature detection method based on image processing |
| CN107153811A (en) * | 2017-03-20 | 2017-09-12 | 中国建设银行股份有限公司 | Know method for distinguishing, apparatus and system for multi-modal biological characteristic |
| CN108647654A (en) * | 2018-05-15 | 2018-10-12 | 合肥岚钊岚传媒有限公司 | The gesture video image identification system and method for view-based access control model |
| CN108830975A (en) * | 2018-04-27 | 2018-11-16 | 安徽继远软件有限公司 | A kind of Intelligent human-face identification gate control system and control method |
-
2018
- 2018-12-26 CN CN201811598761.6A patent/CN111435558A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0749612A4 (en) * | 1994-03-11 | 1997-10-29 | Identix Inc | An electro-optic palm scanner system employing a non-planar platen |
| CN102332084A (en) * | 2010-07-23 | 2012-01-25 | 中国农业大学 | Identity identification method based on palm print and human face feature extraction |
| CN104680154A (en) * | 2015-03-13 | 2015-06-03 | 合肥工业大学 | Identity recognition method based on fusion of face characteristic and palm print characteristic |
| CN105913514A (en) * | 2016-04-08 | 2016-08-31 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| CN105930811A (en) * | 2016-04-26 | 2016-09-07 | 济南梦田商贸有限责任公司 | Palm texture feature detection method based on image processing |
| CN107153811A (en) * | 2017-03-20 | 2017-09-12 | 中国建设银行股份有限公司 | Know method for distinguishing, apparatus and system for multi-modal biological characteristic |
| CN108830975A (en) * | 2018-04-27 | 2018-11-16 | 安徽继远软件有限公司 | A kind of Intelligent human-face identification gate control system and control method |
| CN108647654A (en) * | 2018-05-15 | 2018-10-12 | 合肥岚钊岚传媒有限公司 | The gesture video image identification system and method for view-based access control model |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112183959A (en) * | 2020-09-10 | 2021-01-05 | 国网物资有限公司 | Safety control terminal, server and system for standard evaluation base |
| CN113420629A (en) * | 2021-06-17 | 2021-09-21 | 浙江大华技术股份有限公司 | Image processing method, device, equipment and medium |
| CN114780769A (en) * | 2022-06-13 | 2022-07-22 | 杭州合众数据技术有限公司 | Personnel checking method based on bloom filter |
| CN117173813A (en) * | 2023-08-18 | 2023-12-05 | 鹿客科技(北京)股份有限公司 | Door lock motor assembly control method, intelligent door lock and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10728242B2 (en) | System and method for biometric authentication in connection with camera-equipped devices | |
| CN111435558A (en) | Identity authentication method and device based on biological characteristic multi-mode image | |
| Masupha et al. | Face recognition techniques, their advantages, disadvantages and performance evaluation | |
| JP2018032391A (en) | Liveness test method and apparatus | |
| JP2015529365A5 (en) | ||
| CN105825176A (en) | Identification method based on multi-mode non-contact identity characteristics | |
| Garland | Parallel computing with CUDA | |
| Khan et al. | Low dimensional representation of dorsal hand vein features using principle component analysis (PCA) | |
| Sujay et al. | Face recognition using extended LBP features and multilevel SVM classifier | |
| CN103856614A (en) | Method and device for avoiding error hibernation of mobile terminal | |
| Omoyiola | Overview of biometric and facial recognition techniques | |
| Fischer et al. | A novel palm vein recognition approach based on enhanced local Gabor binary patterns histogram sequence | |
| Anthony et al. | A review of face anti-spoofing methods for face recognition systems | |
| Choras | Multimodal biometrics for person authentication | |
| Khan et al. | Representation of hand dorsal vein features using a low dimensional representation integrating cholesky decomposition | |
| JP2005259049A (en) | Face collation device | |
| Zayed et al. | A comprehensive survey on finger vein biometric | |
| KR101037759B1 (en) | Robust Face Recognition Method using AAM and Gabor Feature Vectors | |
| Moganeshwaran et al. | Fingerprint-fingervein multimodal biometric authentication system in field programmable gate array | |
| KR20070118806A (en) | Method of detecting face for embedded system | |
| Li et al. | Iris recognition on mobile devices using near-infrared images | |
| Khan et al. | Feature Extraction of Dorsal Hand Vein Pattern using a fast modified PCA algorithm based on Cholesky decomposition and Lanczos technique | |
| Trabelsi et al. | A bi-modal palmvein palmprint biometric human identification based on fusing new CDSDP features | |
| Leung et al. | A FPGA implementation of facial feature extraction | |
| Shukla et al. | Comparison of Face Recognition algorithms & its subsequent impact on side face |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200721 |