• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.5
• /
• pp.19-28
• /
• 2017

Various methods for reducing the load on the server have been implemented in performing face recognition remotely by the spread of IP security cameras. In this paper, IP surveillance cameras at remote sites are input through a DSP board equipped with face detection function, and then face detection is performed. Then, the facial region image is transmitted to the server, and the face recognition processing is performed through face recognition distributed processing. As a result, the overall server system load and significantly reduce processing and real-time face recognition has the advantage that you can perform while linked up to 256 cameras. The technology that can accomplish this is to perform 64-channel face recognition per server using distributed processing server technology and to process face search results through 250 camera channels when operating four distributed processing servers there was.

• International Journal of Internet, Broadcasting and Communication
• /
• v.8 no.2
• /
• pp.38-42
• /
• 2016

In this paper, we propose 3-factor mobile banking authentication scheme applied to face recognition techniques with existing certificate and OTP. An image of the user's face is captured by smart phone camera and its brightness processing of the contour of a face and background by n of X and Y points. Then, distance between the point of eyes, nose and mouth from captured user's face are compared with stored facial features. When the compared results corresponding to the data that stored in a face recognition DB, the user is authenticated.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.7
• /
• pp.2496-2511
• /
• 2014

Face recognition is considered a complex biometrics in the field of image processing mainly due to the constraints imposed by variation in the appearance of facial images. These variations in appearance are affected by differences in expressions and/or occlusions (sunglasses, scarf etc.). This paper discusses incremental Kernel Fisher Discriminate Analysis on sub-classes for dealing with partial occlusions and variant expressions. This framework focuses on the division of classes into fixed size sub-classes for effective feature extraction. For this purpose, it modifies the traditional Linear Discriminant Analysis into incremental approach in the kernel space. Experiments are performed on AR, ORL, Yale B and MIT-CBCL face databases. The results show a significant improvement in face recognition.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.243-245
• /
• 2017

In the face recognition technology, which has been studied a lot, the security of the face recognition technology is improved by receiving the depth data as a weak point for the 2D. In this paper, we expect the effect of cost reduction by enhancing the security of 2D by taking new features of eye flicker that each person possesses as new data information.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.6B
• /
• pp.1041-1049
• /
• 2000

A face recognition algorithm for the user identification procedure of automatic teller machine(ATM), as an application of the still image processing techniques is proposed in this paper. In the proposed algorithm, face recognition techniques, especially, face region detection, eye and mouth detection schemes, which can distinguish abnormal faces from normal faces, are proposed. We define normal face, which is acceptable, as a face without sunglasses or a mask, and abnormal face, which is non-acceptable, as that wearing both, or either one of them. The proposed face recognition algorithm is composed of three stages: the face region detection stage, the preprocessing stage for facial feature detection and the eye and mouth detection stage. Experimental results show that the proposed algorithm can distinguish abnormal faces from normal faces accurately from restrictive sample images.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.1
• /
• pp.68-75
• /
• 1999

Machine recognition of faces from still and video images is emerging as an active research area spanning several disciplines such as image processing, pattern recognition, computer vision and neural networks. In addition, human face identification has numerous applications such as human interface based systems and real-time video systems of surveillance and security. In this paper, we propose an algorithm that can identify a particular individual face. We consider human face identification system in color space, which hasn't often considered in conventional in conventional methods. In order to make the algorithm insensitive to luminance, we convert the conventional RGB coordinates into normalized CIE coordinates. The normalized-CIE-based facial images are KL-transformed. The transformed data are used as the input of multi-layered neural network and the network are trained using error-backpropagation methods. Finally, we verify the system performance of the proposed algorithm by experiments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.841-846
• /
• 2006

A real time system realization for binocular eyeball tracking cursor on the computer monitor screen is presented in the paper. The processing for searching iris and tracking the cursor are that a facial is acquired by the small CCD camera, convert it into binary image, search for the eye two using the five region mask method in the eye surroundings and the side four points diagonal positioning method is searched the each iris. The tracking cursor is matched by measuring the iris central moving position, The cursor controlling is achieved by comparing two related distances between the iris maximum moving and the cursor moving to calculate the moving stance from gazing position and screen. The experimental result are obtained by examining some adults person on the system.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.5
• /
• pp.295-302
• /
• 2011

This paper proposes facial feature tracking based on modified ART2 neural networks. And we also suggest new measurement devices such as 'Persistence Exponent' and 'Moving Space Exponent' for the criterion of input vector which consists features. The proposed methods have been applied to classify 48 students by 2-class (ADHD positive, ADHD negative). The results of the experiment have shown that the proposed methods are effective for ADHD Behavior Pattern Classification based on the Image Processing.

• International journal of advanced smart convergence
• /
• v.7 no.4
• /
• pp.40-49
• /
• 2018

We propose a more stable robust recognition algorithm which detects faces reliably even in cases where there are changes in lighting and angle of view, as well it satisfies efficiency in calculation and detection performance. We propose detects the face area alone after normalization through pre-processing and obtains a feature vector using (PCA). The feature vector is applied to LDA and using Euclidean distance of intra-class variance and inter class variance in the 2nd dimension, the final analysis and matching is performed. Experimental results show that the proposed method has a wider distribution when the input image is rotated $45^{\circ}$ left / right. We can improve the recognition rate by applying this feature value to a single algorithm and complex algorithm, and it is possible to recognize in real time because it does not require much calculation amount due to dimensional reduction.