• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.46-54
• /
• 2006

Recently, the important of a personal identification is increasing according to expansion using each on-line commercial transaction and personal ID-card. Although a personal ID-card embedded RFID(Radio Frequency Identification) tag is gradually increased, the way for a person's identification is deficiency. So we need automatic methods. Because RFID tag is vary small storage capacity of memory, it needs effective feature extraction method to store personal biometrics information. We need new recognition method to compare each feature. In this paper, we studied the face verification system using Hippocampal neuron modeling algorithm which can remodel the hippocampal neuron as a principle of a man's brain in engineering, then it can learn the feature vector of the face images very fast. and construct the optimized feature each image. The system is composed of two parts mainly. One is feature extraction using NMF(Non-negative Matrix Factorization) and LDA(Linear Discriminants Analysis) mixture algorithm and the other is hippocampal neuron modeling and recognition simulation experiments confirm the each recognition rate, that are face changes, pose changes and low-level quality image. The results of experiments, we can compare a feature extraction and learning method proposed in this paper of any other methods, and we can confirm that the proposed method is superior to the existing method.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.388-396
• /
• 2017

Since there are many variables such as various poses, illuminations and occlusions in a face detection problem, a high performance detection system is required. Although CNN is excellent in image classification, CNN operatioin requires high-performance hardware resources. But low cost low power environments are essential for small and mobile systems. So in this paper, the CPU-FPGA integrated system is designed based on 3-stage cascade CNN architecture using small size FPGA. Adaptive Region of Interest (ROI) is applied to reduce the number of CNN operations using face information of the previous frame. We use a Field Programmable Gate Array(FPGA) to accelerate the CNN computations. The accelerator reads multiple featuremap at once on the FPGA and performs a Multiply-Accumulate (MAC) operation in parallel for convolution operation. The system is implemented on Altera Cyclone V FPGA in which ARM Cortex A-9 and on-chip SRAM are embedded. The system runs at 30FPS with HD resolution input images. The CPU-FPGA integrated system showed 8.5 times of the power efficiency compared to systems using CPU only.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.2C
• /
• pp.141-149
• /
• 2007

Associating the shoulder line with head location of the human body is useful in verifying, localizing and tracking persons in an image. Since the head line and the shoulder line, what we call ${\Omega}$-shape, move together in a consistent way within a limited range of deformation, we can build a statistical shape model using Active Shape Model (ASM). However, when the conventional ASM is applied to ${\Omega}$-shape fitting, it is very sensitive to background edges and clutter because it relies only on the local edge or gradient. Even though appearance is a good alternative feature for matching the target object to image, it is difficult to learn the appearance of the ${\Omega}$-shape because of the significant difference between people's skin, hair and clothes, and because appearance does not remain the same throughout the entire video. Therefore, instead of teaming appearance or updating appearance as it changes, we model the discriminative appearance where each pixel is classified into head, torso and background classes, and update the classifier to obtain the appropriate discriminative appearance in the current frame. Accordingly, we make use of two features in fitting ${\Omega}$-shape, edge gradient which is used for localization, and discriminative appearance which contributes to stability of the tracker. The simulation results show that the proposed method is very robust to pose change, occlusion, and illumination change in tracking the head and shoulder line of people. Another advantage is that the proposed method operates in real time.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.3
• /
• pp.151-158
• /
• 2019

Patients with disabilities from various reasons such as disasters, injuries or chronic illness or elderly with limited body motion range due to aging are recommended to participate in rehabilitation programs at hospitals. But typically, it's not as simple for them to commute without help as they have limited access outside of the home. Also, regarding the perspectives of hospitals, having to maintain the workforce and have them take care of the rehabilitation sessions leads them to more expenses in cost aspects. For those reasons, in this paper, a home-based remote rehabilitation system using motion recognition is developed without needing help from others. This system can be executed by a personal computer and a stereo camera at home, the real-time user motion status is monitored using motion recognition feature. The system tracks the joint range of motion(Joint ROM) of particular body parts of users to check the body function improvement. For demonstration, total of 4 subjects with various ages and health conditions participated in this project. Their motion data were collected during all 3 exercise sessions, and each session was repeated 9 times per person and was compared in the results.

• Convergence Security Journal
• /
• v.19 no.2
• /
• pp.91-104
• /
• 2019

In this paper, we present a novel local descriptor, Local Prominent Directional Pattern (LPDP), to represent the description of facial images for gender recognition purpose. To achieve a clearly discriminative representation of local shape, presented method encodes a target pixel with the prominent directional variations in local structure from an analysis of statistics encompassed in the histogram of such directional variations. Use of the statistical information comes from the observation that a local neighboring region, having an edge going through it, demonstrate similar gradient directions, and hence, the prominent accumulations, accumulated from such gradient directions provide a solid base to represent the shape of that local structure. Unlike the sole use of gradient direction of a target pixel in existing methods, our coding scheme selects prominent edge directions accumulated from more samples (e.g., surrounding neighboring pixels), which, in turn, minimizes the effect of noise by suppressing the noisy accumulations of single or fewer samples. In this way, the presented encoding strategy provides the more discriminative shape of local structures while ensuring robustness to subtle changes such as local noise. We conduct extensive experiments on gender recognition datasets containing a wide range of challenges such as illumination, expression, age, and pose variations as well as sketch images, and observe the better performance of LPDP descriptor against existing local descriptors.

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.49-59
• /
• 2023

There are various items in the safety and health standards of the manufacturing industry, but they can be divided into work-related diseases and musculoskeletal diseases according to the standards for sickness and accident victims. Musculoskeletal diseases occur frequently in manufacturing and can lead to a decrease in labor productivity and a weakening of competitiveness in manufacturing. In this paper, to detect the musculoskeletal harmful factors of manufacturing workers, we defined the musculoskeletal load work factor analysis, harmful load working postures, and key points matching, and constructed data for Artificial Intelligence(AI) learning. To check the effectiveness of the suggested dataset, AI algorithms such as YOLO, Lite-HRNet, and EfficientNet were used to train and verify. Our experimental results the human detection accuracy is 99%, the key points matching accuracy of the detected person is @AP0.5 88%, and the accuracy of working postures evaluation by integrating the inferred matching positions is LEGS 72.2%, NECT 85.7%, TRUNK 81.9%, UPPERARM 79.8%, and LOWERARM 92.7%, and considered the necessity for research that can prevent deep learning-based musculoskeletal diseases.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1321-1330
• /
• 2023

This study attempts to address the problem of 3D pose estimation for multiple human objects through a single image generated during the character development process that can be used in augmented reality. In the existing top-down method, all objects in the image are first detected, and then each is reconstructed independently. The problem is that inconsistent results may occur due to overlap or depth order mismatch between the reconstructed objects. The goal of this study is to solve these problems and develop a single network that provides consistent 3D reconstruction of all humans in a scene. Integrating a human body model based on the SMPL parametric system into a top-down framework became an important choice. Through this, two types of collision loss based on distance field and loss that considers depth order were introduced. The first loss prevents overlap between reconstructed people, and the second loss adjusts the depth ordering of people to render occlusion inference and annotated instance segmentation consistently. This method allows depth information to be provided to the network without explicit 3D annotation of the image. Experimental results show that this study's methodology performs better than existing methods on standard 3D pose benchmarks, and the proposed losses enable more consistent reconstruction from natural images.

• Journal of Yeungnam Medical Science
• /
• v.16 no.1
• /
• pp.34-42
• /
• 1999

The effects of hyperglycemia and hyperlipidemia on utilization of muscle glycogen during 45 minute Session of treadmill running(26 m/min, 8% grade) were evaluated using Sprague Dawley rats, and the characteristics of the 4 different type of muscles, I.e., soleus, white and red gastrocnemius, and plantaris, on glycogen utilization were simultaneously investigated. Hyperglycemia was induced by 145-165 mg/dL of oral glucose administration, and hyperlipidemia was induced by combined treatment of intraperitoneal heparine injection of 444 uEq/L and 10 % intralipose oral adminstration. During the hyperglycemic trial, the glycogen utilization of plantaris muscle was decreased by 13 % in 45 minute session of treadmill running compared to the control trial(p<0.05), and the glycogen utilization of white gastrocnemius was also decreased. The sparing tendency of glycogen was observed in soleus and red gastrocnemius by 5-13 % during 30 and 45 minute session of treadmill running in hyperglycemic trial. There was no glycogen sparing effect of hyperlipidemia in soleus, red gastrocnemius and plantaris muscle subjected in this experiment during exercise. However, only a slight sparing tendency of white gastrocnemius muscle was observed. In summary, the glycogen sparing effect of hyperglycemia during exercise was observed in plantaris and white gastrocnemius muscles in rats. However, there was no glycogen sparing effect of hyperlipidemia in the 4 hindlimb muscles. It was observed that the glycogen sparing effect of hyperglycemia is more prominent in fast glycolytic muscle fibers.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.8
• /
• pp.91-106
• /
• 2021

The purpose of this study is to define the process of leading to self-realization and social solidarity through the process of contents planning, production, and distribution as Contents Activism, and to categorize specific execution steps. Based on this, we try to analyze concrete cases to find out the social meaning and effect of the practice of Contents Activism. As for the research method, after examining the differences between traditional activism and Contents Activism through a review of previous studies, the implementation process of Contents Activism was categorized into 7 steps. By applying this model, this study analyzed two cases of Contents Activism. The first case is the 100 laps challenge in the backyard planned by an elderly man ahead of his 100th birthday in early 2020, when the fear of COVID-19 spread. Sir Tom Moore, who lives in the UK, challenged to walk 100 laps in the backyard to help medical staff from the National Health Service as COVID-19 infections and deaths increased due to a lack of protective equipment. His challenge, which is difficult to walk without assistive devices due to cancer surgery and fall aftereffects, drew sympathy and participation from many people, leading to global solidarity. The second case analyzes the case of 'The Unfreedom of Expression, Afterwards' by Kim Seo-kyung and Kim Woon-seong, who were invited to the 2019 Aichi Triennale special exhibition in Japan. The 'Unfreedom of Expression, After' exhibition was a project to display the Statue of Peace and the lives of comfort women in the Japanese military, but it was withdrawn after three days of war due to threats and attacks from the far-right forces. Overseas artists who heard this news resisted the Triennale's decision, took and shared photos in the same pose as the Statue of Peace on social media such as Twitter and Instagram, empathizing with the historical significance of the Statue of Peace. Activism, which began with artists, has expanded through social media to the homes, workplaces, and streets of ordinary citizens living in various regions. The two cases can be said to be Contents Activism that led to social practice while solidifying and communicating with someone through contents.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.