WO2023107065A1 - Intelligent system that detects suspects with gait analysis and facial recognition hybrid model - Google Patents
Intelligent system that detects suspects with gait analysis and facial recognition hybrid model Download PDFInfo
- Publication number
- WO2023107065A1 WO2023107065A1 PCT/TR2022/051415 TR2022051415W WO2023107065A1 WO 2023107065 A1 WO2023107065 A1 WO 2023107065A1 TR 2022051415 W TR2022051415 W TR 2022051415W WO 2023107065 A1 WO2023107065 A1 WO 2023107065A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- face
- gait
- video
- suspects
- people
- 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.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
- G06V40/25—Recognition of walking or running movements, e.g. gait recognition
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06V40/172—Classification, e.g. identification
- G06V40/173—Classification, e.g. identification face re-identification, e.g. recognising unknown faces across different face tracks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Definitions
- This invention is related to the intelligent system that detects suspects with gait analysis and facial recognition hybrid model, which allows predicting those whose face is not visible in the video from the video images of suspects by their gait, and those whose face appears only in a small frame and whose gait is not visible by their face.
- the person's gait is included in the classification when the facial recognition outcome in the videos is low in various challenging environments, and the person's face is included in the classification when the gait recognition success in the videos is low.
- Berksan (2019) aimed to determine the gender and age of people by conducting gait analysis in his thesis study, the algorithm has calculated the genders correctly at a rate of 97.45%. In addition, in this study, an average absolute error rate of 5.74 years was formed as the margin of error for age estimation.
- Ba ⁇ aran (2020) has divided facial recognition into two main elements as detection and verification in his thesis study. Consequently, there is a need for new technology that can overcome the disadvantages mentioned above. He proposes a model against the problems that occur during the re-recognition of the person. In addition, body parts have also been included in deep learning methods in order to obtain their local attributes. Thanks to this method, the re-recognition of persons has been detected at a high rate.
- the invention deals with a attendance system based on gait recognition and belongs to the field of attendance machines.
- the gait recognition-based continuation system includes a central processing unit, a feature classification and combination module, and a feature analysis module that is in turn signal-connected, a gait feature recognition processing module, an image processing module, and a feature analysis module electrically connected to the camera.
- This invention is an intelligent system that detects suspects with a hybrid model of gait analysis and facial recognition, and its feature is; it is a new technology that increases the accurate prediction rate by performing face recognition and gait analysis together.
- the invention in order to realize all the objectives mentioned above and which will emerge from the detailed description below; It provides the detection of suspects by analyzing the images obtained from actively used security cameras. Face recognition systems are one of the systems used in terms of security. Gait analysis, on the other hand, provides the detection of suspects when correct images and algorithms are provided, as well as revealing many different characteristic features and separating people with gait analysis.
- Figure 1 Schematic view of the system.
- the obtained information is transferred to a different system from the developed desktop/mobile/web-based system automatically and securely using data sharing technologies.
- an intelligent system is created by making use of artificial intelligence algorithms, gait analysis and facial recognition analysis in video images.
- the process steps of the system are in the following order:
- the database is collected from different physical environments for face and gait, height, weight, eye color, hair color, hair type, skin color, facial hair type the type of the moustache, ethnicity, race, etc. be recording (10), including the soft biometric features,
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
This invention is related to the intelligent system that detects suspects with gait analysis and facial recognition hybrid model, which allows predicting those whose face is not visible in the video from the video images of suspects by their gait, and those whose face appears only in a small frame and whose gait is not visible by their face and its feature; height, weight, eye color, hair color, hair type, skin color, beard type, mustache type, ethnicity, race, etc. of the face and gait database collected from people with various soft biometric characteristics with the help of a camera or from different physical environments, soft biometric features to be recording (10), the people in the video-assisted artificial intelligence developed desktop/mobile/web-based system through the training of the face and marches of the analyzed system (20) has not been submitted earlier trained the system by which the result of giving a new video recording data (30) that is given in the video to the system with the unidentified person/people images of the classification (40) is that it includes the steps of the process.
Description
INTELLIGENT SYSTEM THAT DETECTS SUSPECTS WITH GAIT ANALYSIS AND FACIAL RECOGNITION HYBRID MODEL
Technical Field:
This invention is related to the intelligent system that detects suspects with gait analysis and facial recognition hybrid model, which allows predicting those whose face is not visible in the video from the video images of suspects by their gait, and those whose face appears only in a small frame and whose gait is not visible by their face. In addition, the person's gait is included in the classification when the facial recognition outcome in the videos is low in various challenging environments, and the person's face is included in the classification when the gait recognition success in the videos is low.
State of the Art:
Today, studies on the gait analysis process have just begun. Gbkmen (2018), one of the studies conducted on this subject, has studied gait analysis using k-NN classification algorithm in his thesis study. As a result of the procedure applied on 100 people, 65% success was achieved with dynamic parameters. When this process was applied with dynamic and anthropometric parameters, it made accurate identification at a rate of 81%. With anthropometric parameters alone, it achieved an 89% success rate.
Berksan (2019) aimed to determine the gender and age of people by conducting gait analysis in his thesis study, the algorithm has calculated the genders correctly at a rate of 97.45%. In addition, in this study, an average absolute error rate of 5.74 years was formed as the margin of error for age estimation.
Paia (2019) tested the success in face recognition analysis rates under challenging environments by comparing deep learning algorithms in her thesis study.
Open face, VGGFace2 and Arc face, which are deep learning models, were evaluated and it was stated that these three models achieved low detection results in face recognition under challenging factors such as blur, contrast or noise.
Ba§aran (2020) has divided facial recognition into two main elements as detection and verification in his thesis study. Consequently, there is a need for new technology that can overcome the disadvantages mentioned above. He proposes a model against the problems that occur during the re-recognition of the person. In addition, body parts have also been included in deep learning methods in order to obtain their local attributes. Thanks to this method, the re-recognition of persons has been detected at a high rate.
Basaran, E. (2020). Face Recognition And Person Re-Identification For Person Recognition Unpublished Master Thesis. Istanbul Technical University, Istanbul.
Berksan, M. (2019). Gender recognition and age estimation based on human gait. Unpublished Master Thesis. Ba§kent University, Ankara.
Gokmen, M. S. (2018). Extraction and Identification of Gait Characteristics Using Dynamic and Anthropometric Parameters. Unpublished Master Thesis. Karabiik University, Karabiik.
Paia, G. (2019). A Comparative Study Of Deep Learning Based Face Recognition Algorithms For Video Under Adverse Conditions. Maramara Universty. Istanbul.
In the patent application numbered CN111028374A, “Gait Recognition Based Attendance Machine and Attendance System” is explained. The invention deals with a attendance system based on gait recognition and belongs to the field of attendance machines. The gait recognition-based continuation system includes a central processing unit, a feature classification and combination module, and a feature analysis module that is in turn signal-connected, a gait feature recognition processing module, an image processing module, and a feature analysis module electrically connected to the camera.
In the previous techniques mentioned above, an intelligent system that detects suspects using different soft biometrics as an aid has not been developed when facial and gait recognition has not been successfully achieved under challenging conditions.
As a result, there is a need for a new technology that can overcome the disadvantages mentioned above and increase the accurate prediction rate by performing facial recognition and gait analysis together.
Description of the Invention:
This invention is an intelligent system that detects suspects with a hybrid model of gait analysis and facial recognition, and its feature is; it is a new technology that increases the accurate prediction rate by performing face recognition and gait analysis together.
The invention in order to realize all the objectives mentioned above and which will emerge from the detailed description below; It provides the detection of suspects by analyzing the images obtained from actively used security cameras. Face recognition systems are one of the systems used in terms of security. Gait analysis, on the other hand, provides the detection of suspects when correct images and algorithms are provided, as well as revealing many different characteristic features and separating people with gait analysis.
With the study that is the subject of the invention, it is aimed to significantly increase the accuracy in suspicious detection processes by evaluating these two methods together. It is aimed to match the data transferred to the database more accurately with the developed system by minimizing the aspects that may be missing, such as the inability to obtain images at the right angle in situations where these two methods are used alone, the blur in the images, and the analysis results in poor performance in low light environments. With the developed system, the data analyzed by video processing techniques are processed and stored. With the database created, an intelligent system has been created in which newly received data from the active system can be classified using artificial intelligence techniques.
It is thought that the invention will attract attention by many institutions, especially in terms of judicial cases, such as the Police Criminal, Gendarmerie Criminal, MIT, the Ministry of Justice, by adapting the invention to different fields.
As a result of the researches, no direct competitor of the invention was found. An example of possible competitors can be given to systems that can predict identity from facial images, but these competitors are not our direct competitors since they do not use hybrid models for successful classification under difficult conditions as our system can do, and their success is low.
The characteristic features of the products of the invention and the advantages outlined below and all structural shapes, and these shapes by making references to the detailed written description will be understood more clearly and, therefore, must be made in consideration of the evaluation of these figures and detailed description.
Description of the Figures:
The invention will be described with reference to the accompanying figures, so that the features of the invention will be more clearly understood and appreciated, but the purpose of this is not to limit the invention to these certain regulations. On the contrary, it is intended to cover all alternatives, changes and equivalences that can be included in the
area of the invention defined by the accompanying claims. The details shown should be understood that they are shown only for the purpose of describing the preferred embodiments of the present invention and are presented in order to provide the most convenient and easily understandable description of both the shaping of methods and the rules and conceptual features of the invention. In these drawings.
Figure 1 Schematic view of the system.
The figures to help understand the present invention are numbered as indicated in the attached image and are given below along with their names.
Description of References:
10. Recording
20. analyzed System
30. Recording data
40. Classification
Description of The Invention:
The invention of the camera with the help from various people that have soft biometric features, or face database collected from different physical environments and gait, height, weight, eye color, hair color, hair type, skin color, facial hair type the type of the moustache, ethnicity, race, etc. soft biometric features to be recording (10), developed artificial intelligence of the people in the video-assisted desktop/mobile/web-based system through the training of the face and marches of the analyzed system (20) has not been submitted earlier trained the system by which the result of giving a new video recording data (30) that is given in the video to the system with the unidentified person/classification (40) of images of people includes the process steps.
In the invention, the obtained information is transferred to a different system from the developed desktop/mobile/web-based system automatically and securely using data sharing technologies.
Detailed Description of The Invention:
In this invention, an intelligent system is created by making use of artificial intelligence algorithms, gait analysis and facial recognition analysis in video images. The process steps of the system are in the following order:
1- With the help of various people that have soft biometric features from the camera, or the database is collected from different physical environments for face and gait, height, weight, eye color, hair color, hair type, skin color, facial hair type the type of the moustache, ethnicity, race, etc. be recording (10), including the soft biometric features,
2- Analyzing system (20) by analyzing the faces and gaits of the people in the video via the artificial intelligence supported desktop/mobile/web-based system,
3- Giving a new video recording data (30) to the trained system that has not been given to the system before,
4- Classification (40) of images of unknown person(s) in the video given to the system with high success,
5- Automatic and secure transfer of the obtained information from the developed desktop/mobile/web-based system to a different system when necessary.
Claims
1- The invention is an intelligent system that detects suspects with a hybrid model of gait analysis and face recognition, which includes the steps of recording (10) the face and gait database including soft biometric features, and training the system by giving these data to the artificial intelligence analyzed system (20) is related to, its feature; height, weight, eye color, hair color, hair type, skin color, beard type, mustache type, ethnicity, race, etc. of the face and gait database collected from people with various soft biometric characteristics with the help of a camera or from different physical environments, soft biometric features to be recording (10), the people in the video-assisted artificial intelligence developed desktop/mobile/web-based system through the training of the face and marches of the analyzed system (20) has not been submitted earlier trained the system by which the result of giving a new video recording data (30) that is given in the video to the system with the unidentified person/people images of the classification (40) is that it includes the steps of the process.
2- As mentioned in Claim 1, it is an intelligent system that detects suspects with a hybrid model of gait analysis and facial recognition, and its feature; it is characterized by the fact that the information obtained is automatically and securely transferred from the developed desktop / mobile / web-based system to a different system using data sharing technologies.
7
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TR2021/019127 | 2021-12-06 | ||
| TR2021/019127A TR2021019127A2 (en) | 2021-12-06 | 2021-12-06 | INTELLIGENT SYSTEM TO DETECT SUSPECTS WITH GAIT ANALYSIS AND FACE RECOGNITION HYBRID MODEL |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023107065A1 true WO2023107065A1 (en) | 2023-06-15 |
Family
ID=85114543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/TR2022/051415 Ceased WO2023107065A1 (en) | 2021-12-06 | 2022-12-05 | Intelligent system that detects suspects with gait analysis and facial recognition hybrid model |
Country Status (2)
| Country | Link |
|---|---|
| TR (1) | TR2021019127A2 (en) |
| WO (1) | WO2023107065A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116524602A (en) * | 2023-07-03 | 2023-08-01 | 华东交通大学 | Re-identification method and system for changing clothes pedestrians based on gait features |
| CN120279599A (en) * | 2025-04-17 | 2025-07-08 | 山东大学 | Automatic identification method and application of obesity patient based on gait analysis |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108549946A (en) * | 2018-04-10 | 2018-09-18 | 阳光暖果（北京）科技发展有限公司 | A kind of plant maintenance and maintenance artificial intelligence supervisory systems and method |
| CN112926491A (en) * | 2021-03-17 | 2021-06-08 | 中国工商银行股份有限公司 | User identification method and device, electronic equipment and storage medium |
| CN113723188A (en) * | 2021-07-28 | 2021-11-30 | 国网浙江省电力有限公司电力科学研究院 | Dress uniform person identity verification method combining face and gait features |
-
2021
- 2021-12-06 TR TR2021/019127A patent/TR2021019127A2/en unknown
-
2022
- 2022-12-05 WO PCT/TR2022/051415 patent/WO2023107065A1/en not_active Ceased
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108549946A (en) * | 2018-04-10 | 2018-09-18 | 阳光暖果（北京）科技发展有限公司 | A kind of plant maintenance and maintenance artificial intelligence supervisory systems and method |
| CN112926491A (en) * | 2021-03-17 | 2021-06-08 | 中国工商银行股份有限公司 | User identification method and device, electronic equipment and storage medium |
| CN113723188A (en) * | 2021-07-28 | 2021-11-30 | 国网浙江省电力有限公司电力科学研究院 | Dress uniform person identity verification method combining face and gait features |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116524602A (en) * | 2023-07-03 | 2023-08-01 | 华东交通大学 | Re-identification method and system for changing clothes pedestrians based on gait features |
| CN116524602B (en) * | 2023-07-03 | 2023-09-19 | 华东交通大学 | Method and system for re-identification of pedestrians changing clothes based on gait characteristics |
| CN120279599A (en) * | 2025-04-17 | 2025-07-08 | 山东大学 | Automatic identification method and application of obesity patient based on gait analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| TR2021019127A2 (en) | 2021-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10565433B2 (en) | Age invariant face recognition using convolutional neural networks and set distances | |
| US20080260212A1 (en) | System for indicating deceit and verity | |
| US11694476B2 (en) | Apparatus, system, and method of providing a facial and biometric recognition system | |
| Masala et al. | Real time detection of driver attention: Emerging solutions based on robust iconic classifiers and dictionary of poses | |
| Arigbabu et al. | Recent advances in facial soft biometrics | |
| Heusch et al. | Pulse-based features for face presentation attack detection | |
| Ouarda et al. | MLP Neural Network for face recognition based on Gabor Features and Dimensionality Reduction techniques | |
| Soltane et al. | Multi-modal biometric authentications: concept issues and applications strategies | |
| WO2023107065A1 (en) | Intelligent system that detects suspects with gait analysis and facial recognition hybrid model | |
| Heusch et al. | Remote blood pulse analysis for face presentation attack detection | |
| Akhdan et al. | Face recognition with anti spoofing eye blink detection | |
| KR101195539B1 (en) | Door on/off switching system using face recognition and detection method therefor | |
| Arbab‐Zavar et al. | On forensic use of biometrics | |
| Oluwatobi et al. | A soft computing model of soft biometric traits for gender and ethnicity classification | |
| Yu et al. | An efficient hybrid eye detection method | |
| Das et al. | An introduction to biometric authentication systems | |
| Bigun et al. | Combining biometric evidence for person authentication | |
| Ibitayo et al. | Development Of Iris Based Age And Gender Detection System | |
| Reddy et al. | MDLNN Approach for Alcohol Detection using IRIS | |
| KR102674496B1 (en) | Method and Apparatus for Detecting Fake Faces Using Remote Photoplethysmography Signals | |
| Siregar et al. | Identity recognition of people through face image using principal component analysis | |
| Arif et al. | Siamese Networks for Multiple Face-Detection and Identification | |
| Setiawan et al. | Real-time facial expression recognition to track non-verbal behaviors as lie indicators during interview | |
| Tin | The performance evaluation for personal identification using palmprint and face recognition | |
| Kasinathan et al. | An extensive study on generic facial recognition phases and classification of 2D algorithms |
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: 22904828 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: 22904828 Country of ref document: EP Kind code of ref document: A1 |