• Journal of Korea Multimedia Society
• /
• v.21 no.4
• /
• pp.478-484
• /
• 2018

The choice of the motion features influences the result of the human action recognition method directly. Many factors often influence the single feature differently, such as appearance of the human body, environment and video camera. So the accuracy of action recognition is restricted. On the bases of studying the representation and recognition of human actions, and giving fully consideration to the advantages and disadvantages of different features, the Dense Trajectories(DT) algorithm is a very classic algorithm in the field of behavior recognition feature extraction, but there are some defects in the use of optical flow images. In this paper, we will use the improved Dense Trajectories(iDT) algorithm to optimize and extract the optical flow features in the movement of human action, then we will combined with Support Vector Machine methods to identify human behavior, and use the image in the KTH database for training and testing.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1202-1205
• /
• 2005

This paper describes a method for vision-based person identification that can detect, track, and recognize person from video using multiple cues: height and dressing colors. The method does not require constrained target's pose or fully frontal face image to identify the person. First, the system, which is connected to a pan-tilt-zoom camera, detects target using motion detection and human cardboard model. The system keeps tracking the moving target while it is trying to identify whether it is a human and identify who it is among the registered persons in the database. To segment the moving target from the background scene, we employ a version of background subtraction technique and some spatial filtering. Once the target is segmented, we then align the target with the generic human cardboard model to verify whether the detected target is a human. If the target is identified as a human, the card board model is also used to segment the body parts to obtain some salient features such as head, torso, and legs. The whole body silhouette is also analyzed to obtain the target's shape information such as height and slimness. We then use these multiple cues (at present, we uses shirt color, trousers color, and body height) to recognize the target using a supervised self-organization process. We preliminary tested the system on a set of 5 subjects with multiple clothes. The recognition rate is 100% if the person is wearing the clothes that were learned before. In case a person wears new dresses the system fail to identify. This means height is not enough to classify persons. We plan to extend the work by adding more cues such as skin color, and face recognition by utilizing the zoom capability of the camera to obtain high resolution view of face; then, evaluate the system with more subjects.

• Journal of Fashion Business
• /
• v.19 no.4
• /
• pp.168-182
• /
• 2015

The purpose of this study is to classify students' attitudes towards uniform modification and analyze their subjective experience regarding appearance, and body satisfaction. Questionnaires were administered to 369 middle and high school girls living in Deagu Metropolitan City. Frequency, factor analysis, reliability analysis, correlation analysis, ${\chi}^2$-test, and t-test are all used for data analysis. Our findings are as follows. Two hundred thirty students (62.3%) agreed to modify their school uniforms to express their personalities and follow fashion trends. Motives for uniform modification had to do with social life, physical attractiveness, and practicality. Attitudes toward appearance are found to be shaped by appearance internalization, active management of appearance, appearance needs, social recognition, and conformity. The motives for uniform modification reveal a significant correlation with attitudes toward appearance. Uniform modification satisfaction differed depending on sub-variables of attitude toward appearance(active management of appearance, personalized appearance needs, social recognition, and body satisfaction, such as satisfaction with height and BMI). There was a significant difference in expression of intention for future plastic surgery depending on body image.

• Proceedings of the KSCN Conference
• /
• 2005.10a
• /
• pp.57-58
• /
• 2005

• Journal of Internet Computing and Services
• /
• v.18 no.6
• /
• pp.85-92
• /
• 2017

Recently, in the field of video surveillance, a Deep Learning based learning method has been applied to a method of detecting a moving person in a video and analyzing the behavior of a detected person. The human activity recognition, which is one of the fields this intelligent image analysis technology, detects the object and goes through the process of detecting the body keypoint to recognize the behavior of the detected object. In this paper, we propose a method for Body Keypoint Localization based on Object Detection using RGB-D information. First, the moving object is segmented and detected from the background using color information and depth information generated by the two cameras. The input image generated by rescaling the detected object region using RGB-D information is applied to Convolutional Pose Machines for one person's pose estimation. CPM are used to generate Belief Maps for 14 body parts per person and to detect body keypoints based on Belief Maps. This method provides an accurate region for objects to detect keypoints an can be extended from single Body Keypoint Localization to multiple Body Keypoint Localization through the integration of individual Body Keypoint Localization. In the future, it is possible to generate a model for human pose estimation using the detected keypoints and contribute to the field of human activity recognition.

• Journal of Korea Multimedia Society
• /
• v.6 no.7
• /
• pp.1139-1148
• /
• 2003

Biometric system has been studied as an optimal solution for preventing or reducing the peculation or loss of ID. Nowadays, face recognition has been spot-lighted as a future biometric system because it is not forced to contact the part of human body with the specific input area of the system. However, there is some limitations to get the constant facial features because the size of face area is varied by the capturing distance or tilt of the face. In this paper, we can extract constant facial features within the predefined threshold using the simple geometric processing such as image scaling, transformation, and rotation for frontal face images. This face recognition system identifies faces with 92% of accuracy for the 400 images of 40 different people.

• International Journal of Contents
• /
• v.18 no.3
• /
• pp.11-20
• /
• 2022

Human Emotion Recognition is an exciting topic that has been attracting many researchers for a lengthy time. In recent years, there has been an increasing interest in exploiting contextual information on emotion recognition. Some previous explorations in psychology show that emotional perception is impacted by facial expressions, as well as contextual information from the scene, such as human activities, interactions, and body poses. Those explorations initialize a trend in computer vision in exploring the critical role of contexts, by considering them as modalities to infer predicted emotion along with facial expressions. However, the contextual information has not been fully exploited. The scene emotion created by the surrounding environment, can shape how people perceive emotion. Besides, additive fusion in multimodal training fashion is not practical, because the contributions of each modality are not equal to the final prediction. The purpose of this paper was to contribute to this growing area of research, by exploring the effectiveness of the emotional scene gist in the input image, to infer the emotional state of the primary target. The emotional scene gist includes emotion, emotional feelings, and actions or events that directly trigger emotional reactions in the input image. We also present an attention-based fusion network, to combine multimodal features based on their impacts on the target emotional state. We demonstrate the effectiveness of the method, through a significant improvement on the EMOTIC dataset.

• The Research Journal of the Costume Culture
• /
• v.24 no.1
• /
• pp.67-78
• /
• 2016

The Indonesian population is estimated at 250 million and ranked as the world's fourth-largest. It is also one of the world's largest Muslim nations. Seventy percent of the population of Indonesia is young consumers in their 20s and 30s. In additions, Indonesian consumers have recently developed a great interest in fashion in general and Korean fashion in particular. This paper addresses issues related to young Indonesian consumers' clothing behavior in terms of clothing image, clothing style, body image, clothing and attitudes toward Korean fashion brands. The survey method was used as a primary research instrument. All measurements were adapted from the existing scales from previous studies. A total of 172 questionnaires were used for the final statistical analysis. Empirical results showed that Indonesian consumers' preferences regarding clothing image were new, casual, humorous, futuristic, soft, interesting and active. In terms of style, Indonesian consumers scored high in their preferences of casual and classic styles. With regard to body image, Indonesian consumers have significant concern for their appearance and body, but at the same time they are more satisfied with their body shape. More than half of the respondents had experience in purchasing Korean fashion products. Indonesian consumers recognized the clothing image of Korean fashion brands as new, futuristic, and hi-tech. Furthermore, they perceive the clothing style of Korean fashion brands as casual, feminine, and sexy. Korean fashion brand purchase intension was significantly influenced by recognition and preference of Korean fashion brand.

• Journal of the Ergonomics Society of Korea
• /
• v.24 no.3
• /
• pp.43-52
• /
• 2005

A two-dimensional posture measurement system was developed to evaluate the risks of work-related musculoskeletal disorders(MSDs) easily on various conditions of work. The posture measurement system is an essential tool to analyze the workload for preventing work-related musculoskeletal disorders. Although several posture measurement systems have been developed for workload assessment, some restrictions in industry still exist because of its difficulty on measuring work postures. In this study, an image recognition algorithm was developed based on a neural network method to measure work posture. Each joint angle of human body was automatically measured from the recognized images through the algorithm, and the measurement system makes it possible to evaluate the risks of work-related musculoskeletal disorders easily on various working conditions. The validation test on upper body postures was carried out to examine the accuracy of the measured joint angle data from the system, and the results showed good measuring performance for each joint angle. The differences between the joint angles measured directly and the angles measured by posture measurement software were not statistically significant. It is expected that the result help to properly estimate physical workload and can be used as a postural analysis system to evaluate the risk of work-related musculoskeletal disorders in industry.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.226-228
• /
• 2021

We propose a fall recognition system using the Pose Detection of Google ML kit using video data. Using the Pose detection algorithm, 33 three-dimensional feature points extracted from the body are used to recognize the fall. The algorithm that recognizes the fall by analyzing the extracted feature points uses k-NN. While passing through the normalization process in order not to be influenced in the size of the human body within the size of image and image, analyzing the relative movement of the feature points and the fall recognizes, thirteen of the thriteen test videos recognized the fall, showing an 100% success rate.