• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.11
• /
• pp.1445-1454
• /
• 1995

In this study, we have developed a prototype of the automatic defects detection system for capsule inspection using the computer vision techniques. The subjects for inspection are empty hard capsules of various sizes which are made of gelatine. To inspect both sides of a capsule, 2-stage recognition is performed. Features we have used are various lengths of a capsule, area, linearity, symmetricity, head curvature and so on. Decision making is performed based on average value which is computed from 20 good capsules in training and permission bounds in factories. Most of time-consuming process for feature extraction is computed by hardware to meet the inspection speed of more than 20 capsules/sec. The main logic for control and arithmetic computation is implemented using EPLD for the sake of easy change of design and reduction in time for developement. As a result of experiment, defects on size or contour of binary images are detected over 95%. Because of dead zone in imaging system, detection ratio of defects on surface, such as bad joint, chip, speck, etc, is lower than the former case. In this case, detection ratio is 50-85%. Defects such as collet pinch and mashed cap/body seldom appear in binary image, and detection ratio is very low. So we have to process the gray-level image directly in partial region.

• Journal of Broadcast Engineering
• /
• v.25 no.7
• /
• pp.1081-1094
• /
• 2020

With the recent development of deep learning, most computer vision-related tasks are being solved with deep learning-based network technologies such as CNN and RNN. Computer vision tasks such as object detection or object segmentation use intermediate features extracted from the same backbone such as Resnet or FPN for training and inference for object detection and segmentation. In this paper, an experiment was conducted to find out the compression efficiency and the effect of encoding on task inference performance when the features extracted in the intermediate stage of CNN are encoded. The feature map that combines the features of 256 channels into one image and the original image were encoded in HEVC to compare and analyze the inference performance for object detection and segmentation. Since the intermediate feature map encodes the five levels of feature maps (P2 to P6), the image size and resolution are increased compared to the original image. However, when the degree of compression is weakened, the use of feature maps yields similar or better inference results to the inference performance of the original image.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.108-111
• /
• 2022

Applying deep learning to machine vision systems for defect detection of products requires vast amounts of training data about various defect cases. However, since data imbalance occurs according to the type of defect in the actual manufacturing industry, it takes a lot of time to collect product images enough to generalize defect cases. In this paper, we apply a Siamese neural network that can be learned with even a small amount of data to product defect detection, and modify the image pairing method and contrastive loss function by properties the situation of product defect image data. We indirectly evaluated the embedding performance of Siamese neural networks using AUC-ROC, and it showed good performance when the images only paired among same products, not paired among defective products, and learned with exponential contrastive loss.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.183-185
• /
• 2021

Detecting bacteria in blood could be an important research area in medicine and computer vision. In this paper, we propose a method for detecting bacteria in blood from 366 darkfield microscopy images acquired at Kaggle. Generate a training dataset through preprocessing and data augmentation using image processing techniques, and define a deep learning model for learning it. As a result of the experiment, it was confirmed that the proposed deep learning model effectively detects red blood cells and bacteria in darkfield microscopy images. In this paper, we learned using a relatively simple model, but it seems that more accurate results can be obtained by using a deeper model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.540-542
• /
• 2023

Due to the serious issues posed by facial manipulation technologies, many researchers are becoming increasingly interested in the identification of face forgeries. The majority of existing face forgery detection methods leverage powerful data adaptation ability of neural network to derive distinguishing traits. These deep learning-based detection methods frequently treat the detection of fake faces as a binary classification problem and employ softmax loss to track CNN network training. However, acquired traits observed by softmax loss are insufficient for discriminating. To get over these limitations, in this study, we introduce a novel discriminative feature learning based on Vision Transformer architecture. Additionally, a separation-center loss is created to simply compress intra-class variation of original faces while enhancing inter-class differences in the embedding space.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.1
• /
• pp.9-19
• /
• 2024

Deep learning-based computer vision anomaly detection algorithms are widely utilized in various fields. Especially in the manufacturing industry, the difficulty in collecting abnormal data compared to normal data, and the challenge of defining all potential abnormalities in advance, have led to an increasing demand for unsupervised learning methods that rely on normal data. In this study, we conducted a comparative analysis of deep learning-based unsupervised learning algorithms that define and detect abnormalities that can occur when transparent contact lenses are immersed in liquid solution. We validated and applied the unsupervised learning algorithms used in this study to the existing anomaly detection benchmark dataset, MvTecAD. The existing anomaly detection benchmark dataset primarily consists of solid objects, whereas in our study, we compared unsupervised learning-based algorithms in experiments judging the shape and presence of lenses submerged in liquid. Among the algorithms analyzed, EfficientAD showed an AUROC and F1-score of 0.97 in image-level tests. However, the F1-score decreased to 0.18 in pixel-level tests, making it challenging to determine the locations where abnormalities occurred. Despite this, EfficientAD demonstrated excellent performance in image-level tests classifying normal and abnormal instances, suggesting that with the collection and training of large-scale data in real industrial settings, it is expected to exhibit even better performance.

• The Korean Journal of Health Service Management
• /
• v.2 no.1
• /
• pp.125-136
• /
• 2008

Government came to enforce long-term care insurance system in preparation for the rapid aging society. Whether this system is successful or not depends on the professionalism of long-term care-givers who are professional population in charge of care service. Currently in the early stage of enforcement, such problems as a race cutting fee resulted from numerical increase of educational facilities, insolvent operation, degradation of education level resulted from unprofessional instructor, are pointed out. As a mean of manpower-training on long-term care insurance system, this study is to research public-private-university network model of the Academy of Continuing Education attached to Ko Sin University which is the case of Yong Do Gu Busan city. Networking between the vision and development strategy of Yong Do Gu on continuing education city, education system on community manpower-training supported by Ko Sin University, and service field of welfare for the elderly can not only contribute to the professionalism of long-term care-givers but also play an ideal role in manpower-utilization and arrangement of community. Through this networking, high quality of education level and circumstance, using the existing infra, manpower-training and utilization for continuing education of Yong Do Gu can be accomplished. Additionally, the connection with facilities related with welfare for the elderly can contribute to professionalism and accountability of manpower-networking.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.10
• /
• pp.137-145
• /
• 2007

The purpose of this study is developing a virtual bicycle system for improving the ability of postural balance control for adults in various age groups. The system consists of an exercise bicycle that allows tilt in accordance with the postural balance of the subject in the system, a visual display that shows virtual road, and a visual feedback system. The rider of the system tries to maintain balance on the bicycle with a visual feedback of a virtual road while the pedaling speed, the heading direction, and various weight distribution information are updated to the subject as visual feedbacks in the display. A series of experiments were performed with various subjects to find the factors related to postural balance control in the system. The related parameters obtained were weight shift, magnitude of the deviation from the center of the virtual road, and variables related to the movement of the center of pressure. The results found that the ability to control postural balance in the system improved with the presentation of visual feedback information of the distribution of weight. It was also found that the general performance of the subject on balance in the system improved after ten days long training. The results show that the newly developed system can be used for the diagnosis of postural balance as well as for the stimulation of various senses such as vision and somatic sense in the field of rehabilitation training.

• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.214-222
• /
• 2022

Convolutional Neural networks (CNNs) are a category of deep learning networks that have proven very effective in computer vision tasks such as image classification. Notwithstanding, not much has been seen in its use for remote sensing image classification in developing countries. This is majorly due to the scarcity of training data. Recently, transfer learning technique has successfully been used to develop state-of-the art models for remote sensing (RS) image classification tasks using training and testing data from well-known RS data repositories. However, the ability of such model to classify RS test data from a different dataset has not been sufficiently investigated. In this paper, we propose a deep CNN model that can classify RS test data from a dataset different from the training dataset. To achieve our objective, we first, re-trained a ResNet-50 model using EuroSAT, a large-scale RS dataset to develop a base model then we integrated Augmentation and Ensemble learning to improve its generalization ability. We further experimented on the ability of this model to classify a novel dataset (Nig_Images). The final classification results shows that our model achieves a 96% and 80% accuracy on EuroSAT and Nig_Images test data respectively. Adequate knowledge and usage of this framework is expected to encourage research and the usage of deep CNNs for land cover mapping in cases of lack of training data as obtainable in developing countries.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1993.10a
• /
• pp.1243-1253
• /
• 1993

Visual features of a mushroom(Lentinus Edodes L) are critical in sorting and grading as most agricultural products are. Because of its complex and various visual features, grading and sorting of mushrooms have been done manually by the human expert. Though actions involved in human grading looks simple, a decision making undereath the simple action comes form the results of the complex neural processing of the visual image. And processing details involved in the visual recognition of the human brain has not been fully investigated yet. Recently, however, an artificial neural network has drawn a great attention because of its functional capability as a partial substitute of the human brain. Since most agricultural products are not uniquely defined in its physical properties and do not have a well defined job structure, a research of the neuro-net based human like information processing toward the agricultural product and processing are widely open and promising. In this pape , neuro-net based grading and sorting system was developed for a mushroom . A computer vision system was utilized for extracting and quantifying the qualitative visual features of sampled mushrooms. The extracted visual features and their corresponding grades were used as input/output pairs for training the neural network and the trained results of the network were presented . The computer vision system used is composed of the IBM PC compatible 386DX, ITEX PFG frame grabber, B/W CCD camera , VGA color graphic monitor , and image output RGB monitor.