CN111695498B - Wood identity detection method - Google Patents
Wood identity detection method Download PDFInfo
- Publication number
- CN111695498B CN111695498B CN202010525814.2A CN202010525814A CN111695498B CN 111695498 B CN111695498 B CN 111695498B CN 202010525814 A CN202010525814 A CN 202010525814A CN 111695498 B CN111695498 B CN 111695498B
- Authority
- CN
- China
- Prior art keywords
- point
- points
- key
- matching
- wood
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/693—Acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/698—Matching; Classification
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The wood identity detection method disclosed by the invention comprises the following steps: collecting image information of a cross section of the wood, extracting key points in the image, traversing all pixels in a gray picture, comparing gray values between a selected pixel point and a neighbor of the selected pixel point, marking as the key points if the difference of the gray values exceeds a specified threshold value, storing the key points in a key point set, further traversing each key point, calculating the centroid of a region where each key point is located, calculating a rotation angle between each key point and the centroid of the key point, and calculating descriptors of the key points by rotating the region where the key points are located. When the images are compared, the key points in the two images are extracted first, and then the similar characteristic points in the two images are calculated. If the number of the counted matches reaches the set threshold, the pictures are considered to be from the same wood. This scheme is through judging whether the same identity that realizes timber of timber tangent plane image judges, can be used to timber traceability system, the authentication of specially adapted precious woodwork.
Description
Technical Field
The invention belongs to the technical field of image recognition and analysis, and particularly relates to a method for identifying wood identity.
Background
The wood identity is a technology for judging whether wood individuals are replaced or not, different characteristic data of the wood are collected according to different algorithms when information is recorded, when identity identification is required, the new individual collected characteristic data is compared with existing records in a database, and whether the wood used in the information recording process and the currently sampled wood are the same or not is judged according to a comparison result.
The current situation is as follows:
1) Some people research and record the stereo data of the wood, and record the shape characteristics of the wood by using a 3D scanning device, so that the identity of the wood individuals is determined, and the defects are that the speed is low, and the wood products with the same appearance cannot be distinguished.
2) Someone shoots traces of saw teeth in the log and identifies identity by using a human fingerprint identification algorithm. The disadvantage is that the serrations are easily damaged during transport.
3) The method comprises the steps of collecting the geometric dimension of a log cross section, calculating a minimum external rectangle, calculating the ratio of the area to the external rectangle, calculating information such as the near-roundness rate and the like, and performing identity identification as the characteristics of wood. The method has the advantages that the method has high accuracy for identifying the identity of the log, but is difficult in data acquisition and is not suitable for wood products and plates with uniform appearance.
The data acquisition speed of the disclosed method for the wood is relatively slow, and the characteristics are easily damaged in the transportation process and are difficult to apply and popularize.
Disclosure of Invention
The invention aims to provide a method for judging the source tracing of precious wood by using an operation module of an image recognition technology embedded algorithm, and provides a method for identifying wood identity.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, an embodiment of the present invention provides a method for detecting wood identity, where the method includes:
the acquisition cross section cuts out image information of 300X300 pixels by a 20X magnifying glass,
extracting key points in the image by adopting an ORB algorithm, traversing all pixels in the gray level image one by one, comparing the gray level values between the selected pixel points and the neighbors thereof, if the gray level value difference exceeds a specified threshold value, marking as the key points, and storing in a key point set;
traversing the key points, calculating the centroid of the area where each key point is located, calculating the rotation angle between the key point and the centroid, rotating the area where the key point is located, and calculating the descriptor of the key point; the characteristic point marker is the difference value of the gray values of the key point and the neighbor of the key point;
counting the number of key points matched with the descriptors, defining matched points as feature points, if the number of the points successfully matched reaches a set threshold value, considering that the pictures are from the same wood, otherwise, considering that the pictures are from different woods; and finally, outputting the result.
In a second aspect, an embodiment of the present invention provides a method for detecting wood identity, which includes the following specific steps:
step 1:
selecting a cross section as a collecting part, and collecting 300X300 pixels by using a 20X magnifying glass electron microscope;
and 2, step:
extracting key points in the image by using an ORB algorithm, converting a color image into a gray-scale image, traversing all pixels in the image, and calculating gray-scale value differences between a change point and 4 neighbors (shown in figure 1) of the change point;
and step 3:
obtaining a key point set, traversing the key points and calculating the centroid of the area where each key point is located, wherein the area is a rectangular area with the key points as the center, the size of the area is 15x15, and the centroid of the area is calculated according to the set;
and 4, step 4:
defining the matched key points as feature points,
solving an included angle theta between a feature vector from a feature point to a centroid and an x coordinate axis in a feature region, and performing rotation operation on the feature region by using the theta angle to obtain a rotation matrix;
and 5:
any one of the feature point p descriptors is marked as f n (P)，
function if the gray value of x is greater than the gray value of y
Returning to 1, otherwise, returning to 0;
step 6: when the identification of the identity is carried out,
firstly, matching operation needs to be carried out on the feature points, then the proportion of successful matching is counted, and if the number of successful matching reaches a set threshold value, the two images are considered to be from the same wood individual. The similarity of the feature points is judged according to the Euler distance of the descriptors of the feature points and is judged according to the following formula,
when matching the feature points, firstly taking 2 matching points with the minimum distance from each point, finally judging the distance between the two feature points, if the distance of the first matching point is less than 70% of the distance of the second matching point, determining that the matching is successful, otherwise, canceling the matching;
defining a matching base S t The maximum value of the feature points of the two images is multiplied by 0.16, and if the number of successfully matched points is more than S t Both images are shown to be from the same individual wood.
In the above step, in step 1, assume that the currently traversed point is p, and its four neighbors are defined as 4 points p with a radius of 3 bits 1 ,p 2 ,p 3 ,p 4 Then, the difference between the points p and their gray values is calculated using equation (1) respectively;
d i ＝|I p -I pi | (1)，
wherein, I p Representing the gray value of the p point;
if the difference between the gray value of 2 neighbors in the four neighbors and the gray value of p exceeds a specified threshold, the p point is marked as a characteristic point. And after the picture is traversed, recording a plurality of feature points.
In the above step, in step 3, the specific algorithm is expressed as using the following formula (2)
Wherein, I (x, y) represents the gray value of the point (x, y), and p, q belongs to {0,1};
the centroid coordinate formula (3) of the region is expressed as
In the above step, in step 4, θ = atan2 (m) is obtained 01 ,m 10 ) With B θ ＝R θ B, the rotation matrix is
In the above step, in step 6, the matching base S t Is max (F) A ,F B )×0.16。
After matching, if the number of successfully matched points in the two images is more than S t And if the number of successfully matched points is less than S, the two images are from the same sample t Two images from different samples are illustrated.
In a third aspect, an embodiment of the present invention further provides a computer storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method in the first aspect.
Has the advantages that: compared with the prior art, the invention has the following advantages:
1) The method can be used in a timber traceability system, the recognition effect is accurate, the algorithm is simple, and the embedding and development are easy by using a machine automatic recognition mode.
2) The method can be used for the identity authentication work of precious wood products.
3) The feature can not be copied and transferred, and the credibility is high.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic diagram of feature point calculation provided in an embodiment of the present application.
Fig. 2 is an exemplary effect diagram of feature recognition provided in an embodiment of the present application.
Detailed Description
In order to facilitate understanding of those skilled in the art, the present invention will be further described with reference to the following examples and drawings, which are not intended to limit the present invention.
Examples
The embodiment provides a wood identity detection method, which comprises the following steps: the method comprises the steps of collecting image information of 300X300 pixels of a cross section, intercepting the image information by a 20X magnifier, extracting key points in the image by adopting an ORB algorithm to obtain a key point set, traversing all pixels in a gray level image one by one, comparing gray values between selected pixel points and neighbors of the selected pixel points, recording the gray values as key points if the gray value difference exceeds a specified threshold value, and storing the key points in the key point set. And traversing the key points, calculating the centroid of the area where each key point is located, and calculating the rotation angle between the key point and the centroid. And when image comparison is carried out, firstly extracting the key points in the two images, and then calculating similar characteristic points in the two images by using Euclidean distance. And counting the number of the matches, and if the number of the points successfully matched reaches a set threshold value, considering that the pictures are from the same wood, or else, considering that the pictures are from different woods. And finally, outputting the result.
The embodiment provides a wood identity detection method, which comprises the following specific steps:
step 1:
selecting a cross section as a collecting part, and collecting 300X300 pixels by using a 20X magnifier electron microscope;
step 2:
extracting characteristic points in the image by using an ORB algorithm, converting a color picture into a gray-scale image, traversing all pixels in the image, and calculating gray value differences between a changed point and 4 adjacent points of the changed point;
and step 3:
obtaining a feature point set, traversing the feature points and calculating the centroid of the area where each feature point is located, wherein the area is a rectangular area with the feature points as the center, the size of the area is 15x15, and the centroid of the area is calculated according to the set;
and 4, step 4:
solving an included angle theta between a feature vector from a feature point to a centroid and an x coordinate axis in a feature region, and performing rotation operation on the feature region by using the theta angle to obtain a rotation matrix;
and 5:
any one of the feature point p descriptors is denoted as f n (P)，
function if the gray value of x is greater than the gray value of y
Returning to 1, otherwise, returning to 0;
step 6: when the identification of the identity is carried out,
firstly, matching operation needs to be carried out on the feature points, then the proportion of successful matching is counted, and if the number of successful matching reaches a set threshold value, the two images are considered to be from the same wood individual. The similarity of the feature points is judged according to the Euler distance of the descriptors of the feature points and is judged according to the following formula,
when matching the feature points, firstly, taking 2 matching points with the minimum distance from each point, finally, judging the distance between the two feature points, if the distance of the first matching point is less than 70 percent of the distance of the second matching point, considering the matching as a successful matching, and if not, canceling the matching;
defining a matching base S t Is the maximum value of the number of the characteristic points of the two images multiplied by 0.16, if the points are successfully matchedIs greater than S t Both images are shown to be from the same individual wood.
In the above method, in step 1, assume that the currently traversed point is p, and its four neighbors are defined as 4 points p with a radius of 3 bits 1 ，p 2 ，p 3 ，p 4 Then, the difference between the point p and their gray values is calculated using the formula (1);
d i ＝|I p -I pi | (1)
wherein, I p Representing the gray value of the p point;
if the difference between the gray value of 2 neighbors in the four neighbors and the gray value of p exceeds a specified threshold, the point p is marked as a feature point. And after the picture is traversed, recording a plurality of feature points.
In the above method, in step 3, the specific algorithm is expressed by the following formula (2)
Wherein, I (x, y) represents the gray value of the point (x, y), and p, q belongs to {0,1};
the centroid coordinate formula (3) of the region is expressed as
In the above method, in step 4, θ = atan2 (m) is obtained 01 ,m 10 ) With B θ ＝R θ B, the rotation matrix is
In the above method, in step 6, the matching base S t Is max (F) A ,F B )×0.16。
The present embodiment provides a computer storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above-described method.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments, or alternatives may be employed, by those skilled in the art, without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (5)
1. A wood identity detection method is characterized by comprising the following steps:
the acquisition cross section cuts picture information of 300X300 pixels by a 20X magnifying glass,
then, extracting key points in the image by adopting an ORB algorithm, traversing all pixels in the gray level image one by one, comparing gray levels between the selected pixel point and the neighbor of the selected pixel point, recording the gray levels as the key points if the gray level difference exceeds a specified threshold value, and storing the key points in a key point set;
traversing the key points, calculating the centroid of the area where each key point is located, calculating the rotation angle between the key point and the centroid, rotating the area where the key point is located, and calculating the descriptor of the key point; the characteristic point is the difference value of the gray values of the key point and the neighbor of the key point;
counting the number of matched key points of the descriptor, defining matched points as feature points, if the number of the successfully matched points reaches a set threshold value, considering that the pictures are from the same wood, otherwise, considering that the pictures are from different woods; finally, outputting a result;
the method comprises the following specific steps:
step 1:
selecting a cross section as a collecting part, and collecting image information of 300X300 pixels by using a 20X magnifying glass electron microscope;
step 2:
extracting key points in the image by using an ORB algorithm, converting a color image into a gray-scale image, traversing all pixels in the image, and calculating the gray-scale value difference of the point and 4 neighbors of the point;
and 3, step 3:
obtaining a key point set, traversing the key points and calculating the centroid of the area where each key point is located, wherein the area is a rectangular area with the key points as the center, the size of the area is 15x15, and the centroid of the area is calculated according to the set;
and 4, step 4:
defining the matched key points as feature points,
solving an included angle theta between a feature vector from a feature point to a centroid and an x coordinate axis in a feature area, and performing rotation operation on the feature area by using the theta angle to obtain a rotation matrix;
and 5:
any one of the feature point p descriptors is denoted as f n (P)，
function if the gray value of x is greater than the gray value of y
Returning to 0, otherwise, returning to 1;
and 6: when the identification of the identity is carried out,
firstly, matching operation is carried out on the feature points, then the proportion of successful matching is counted, and if the number of successful matching reaches a set threshold value, two images are considered to be from the same wood individual; the similarity of the feature points is judged according to the Euler distance of the descriptors of the feature points and is judged according to the following formula,
when matching the feature points, firstly, taking 2 matching points with the minimum distance from each point, finally, judging the distance between the two feature points, if the distance of the first matching point is less than 70 percent of the distance of the second matching point, considering the matching as a successful matching, and if not, canceling the matching;
definition matching base S t The maximum value of the feature points of the two images is multiplied by 0.16, and if the number of successfully matched points is more than S t Displaying that the two images are from the same wood individual;
in step 3, the specific algorithm is expressed as follows (2)
Wherein, I (x, y) represents the gray value of the point (x, y), and p, q belongs to {0,1};
the centroid coordinate formula (3) of the region is expressed as
2. The wood identity detection method according to claim 1, wherein: in step 1, assume that the currently traversed point is p, and its four neighbors are defined as 4 points p with a 3-bit radius 1 ,p 2 ,p 3 ,p 4 Then, the difference between the points p and their gray values is calculated using equation (1) respectively;
d i ＝|I p -I pi | (1)，
wherein, I p Representing the gray value of the p point;
if the difference between the gray value of 2 neighbors in the four neighbors and the gray value of p exceeds a specified threshold, marking the p point as a characteristic point; and after the picture is traversed, recording a plurality of feature points.
3. The wood identity detection method according to claim 1, wherein: in step 4, θ = atan2 (m) is obtained 01 ,m 10 ) With B θ ＝R θ B, the rotation matrix is
4. The wood identity detection method according to claim 1, wherein: in step 6, the matching base S t Is max (F) A ,F B )×0.16。
5. A computer storage medium having a computer program stored thereon, characterized in that: the program when executed by a processor implementing the steps of the method as claimed in any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010525814.2A CN111695498B (en) | 2020-06-10 | 2020-06-10 | Wood identity detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010525814.2A CN111695498B (en) | 2020-06-10 | 2020-06-10 | Wood identity detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111695498A CN111695498A (en) | 2020-09-22 |
| CN111695498B true CN111695498B (en) | 2023-04-07 |
Family
ID=72480300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010525814.2A Active CN111695498B (en) | 2020-06-10 | 2020-06-10 | Wood identity detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695498B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112861875B (en) * | 2021-01-20 | 2022-10-04 | 西南林业大学 | Method for distinguishing different wood products |
| CN113344007B (en) * | 2021-06-02 | 2022-07-15 | 中国科学技术大学 | Log fingerprint extraction and matching method |
| JP7499387B1 (en) | 2023-06-28 | 2024-06-13 | 綾子 高橋 | Information processing system, information processing device, information processing method, and program |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004178402A (en) * | 2002-11-28 | 2004-06-24 | Casio Comput Co Ltd | Face image processing device, face image processing method and face image processing program |
| WO2013136603A1 (en) * | 2012-03-15 | 2013-09-19 | オムロン株式会社 | Image matching method and image matching device and program using such method |
| WO2014205768A1 (en) * | 2013-06-28 | 2014-12-31 | 中国科学院自动化研究所 | Feature and model mutual matching face tracking method based on increment principal component analysis |
| CN111951223A (en) * | 2020-07-16 | 2020-11-17 | 西南林业大学 | Automatic image identification method and system for wood knot flaws |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2359884B (en) * | 1999-11-25 | 2004-06-30 | Canon Kk | Image processing method and apparatus |
| JP4704804B2 (en) * | 2005-05-18 | 2011-06-22 | 株式会社名南製作所 | Wood section exploration method, apparatus and program |
| KR20140108726A (en) * | 2012-02-27 | 2014-09-12 | 아셀산 엘렉트로닉 사나이 베 티카렛 아노님 시르케티 | System and method for identifying scale invariant features of object outlines on images |
| CN104598878A (en) * | 2015-01-07 | 2015-05-06 | 深圳市唯特视科技有限公司 | Multi-modal face recognition device and method based on multi-layer fusion of gray level and depth information |
| US11216905B2 (en) * | 2016-12-27 | 2022-01-04 | Fordaq SA | Automatic detection, counting, and measurement of lumber boards using a handheld device |
| CN106778791A (en) * | 2017-03-01 | 2017-05-31 | 成都天衡电科科技有限公司 | A kind of timber visual identity method based on multiple perceptron |
| CN107967482A (en) * | 2017-10-24 | 2018-04-27 | 广东中科南海岸车联网技术有限公司 | Icon-based programming method and device |
| CN109101867A (en) * | 2018-06-11 | 2018-12-28 | 平安科技（深圳）有限公司 | A kind of image matching method, device, computer equipment and storage medium |
| GB2584660B (en) * | 2019-06-10 | 2022-08-24 | Univ China Petroleum East China | Automatic identification method and system for different mineral pores of mud shale |
| CN110503051B (en) * | 2019-08-27 | 2023-04-07 | 西南林业大学 | Precious wood identification system and method based on image identification technology |
| CN112149630A (en) * | 2020-10-20 | 2020-12-29 | 云南省林业和草原科学院 | Wood microscopic identification system |
| CN112861875B (en) * | 2021-01-20 | 2022-10-04 | 西南林业大学 | Method for distinguishing different wood products |
| CN113011498B (en) * | 2021-03-22 | 2023-09-26 | 华南理工大学 | Feature point extraction and matching method, system and medium based on color image |
| CN113591949A (en) * | 2021-07-19 | 2021-11-02 | 浙江农林大学 | Standing tree feature point matching method, device, equipment and medium |
-
2020
- 2020-06-10 CN CN202010525814.2A patent/CN111695498B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004178402A (en) * | 2002-11-28 | 2004-06-24 | Casio Comput Co Ltd | Face image processing device, face image processing method and face image processing program |
| WO2013136603A1 (en) * | 2012-03-15 | 2013-09-19 | オムロン株式会社 | Image matching method and image matching device and program using such method |
| WO2014205768A1 (en) * | 2013-06-28 | 2014-12-31 | 中国科学院自动化研究所 | Feature and model mutual matching face tracking method based on increment principal component analysis |
| CN111951223A (en) * | 2020-07-16 | 2020-11-17 | 西南林业大学 | Automatic image identification method and system for wood knot flaws |
Non-Patent Citations (1)
| Title |
|---|
| 陈宇 ; 臧美英 ; 李红波 ; .SIFT算法在木材纹理分类上的应用.哈尔滨理工大学学报.2016,(04),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111695498A (en) | 2020-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111695498B (en) | Wood identity detection method | |
| US6895104B2 (en) | Image identification system | |
| WO2019061661A1 (en) | Image tamper detecting method, electronic device and readable storage medium | |
| Li et al. | Person-independent head pose estimation based on random forest regression | |
| WO2019033574A1 (en) | Electronic device, dynamic video face recognition method and system, and storage medium | |
| TWI254891B (en) | Face image detection method, face image detection system, and face image detection program | |
| CN1137659A (en) | Process for encrypting fingerprint onto I.D. card | |
| CN101114335A (en) | Full angle rapid fingerprint identification method | |
| CN111191649A (en) | Method and equipment for identifying bent multi-line text image | |
| CN101582162A (en) | Virtu identifying method based on texture analysis | |
| US20180373960A1 (en) | Trademark graph element identification method, apparatus and system, and computer storage medium | |
| CN110288612B (en) | Nameplate positioning and correcting method and device | |
| CN112215780B (en) | Image evidence obtaining and resistance attack defending method based on class feature restoration fusion | |
| CN105488486A (en) | Face recognition method and device for preventing photo attack | |
| CN114842524B (en) | Face false distinguishing method based on irregular significant pixel cluster | |
| US8005262B2 (en) | System and method for video object identification | |
| CN116597438A (en) | Improved fruit identification method and system based on Yolov5 | |
| Fadl et al. | Copy-rotate-move forgery detection based on spatial domain | |
| Tripathi et al. | Automated image splicing detection using texture based feature criterion and fuzzy support vector machine based classifier | |
| CN116383791A (en) | Customer identity authentication method, device, electronic equipment and medium | |
| US7957555B2 (en) | Method and apparatus for localizing an object part in digital image data by updating an initial position estimate based on a displacement of the object part | |
| CN112396638A (en) | Image processing method, terminal and computer readable storage medium | |
| CN109165640B (en) | Hand back vein identification method and identification system based on bit plane internal block mutual information | |
| Khoh et al. | Spatiotemporal spectral histogramming analysis in hand gesture signature recognition | |
| CN111915582B (en) | Image tampering detection method based on brightness characteristic coupling information quantity constraint |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |