• The Journal of the Korea Contents Association
• /
• v.21 no.8
• /
• pp.1-9
• /
• 2021

Deep learning in computer vision has made accelerated improvement over a short period but large-scale learning data and computing power are still essential that required time-consuming trial and error tasks are involved to derive an optimal network model. In this study, we propose a similar image classification performance improvement method based on CR (Confusion Rate) that considers only the characteristics of the data itself regardless of network optimization or data reinforcement. The proposed method is a technique that improves the performance of the deep learning model by calculating the CRs for images in a dataset with similar characteristics and reflecting it in the weight of the Loss Function. Also, the CR-based recognition method is advantageous for image identification with high similarity because it enables image recognition in consideration of similarity between classes. As a result of applying the proposed method to the Resnet18 model, it showed a performance improvement of 0.22% in HanDB and 3.38% in Animal-10N. The proposed method is expected to be the basis for artificial intelligence research using noisy labeled data accompanying large-scale learning data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.675-681
• /
• 2022

Recently, with the development of IoT technology and AI, unmanned and automated in various fields, interest in video processing, which is the basis for automation such as object recognition and object classification, is increasing. Various studies have been conducted on noise removal in the video processing process, which has a significant impact on image quality and system accuracy and reliability, but there is a problem that it is difficult to restore images for areas with high impulse noise density. In this paper proposes a filter algorithm based on partial mask and Lagrange interpolation to restore the damaged area of impulse noise in the image. In the proposed algorithm, the filtering process was switched by comparing the filtering mask with the noise estimate and the purge weight was calculated based on the low frequency component and the high frequency component of the image to restore the image.

• Journal of the Korean Society of Visualization
• /
• v.21 no.2
• /
• pp.83-90
• /
• 2023

The shape of an airfoil is a critical factor in determining aerodynamic characteristics such as lift and drag. Aerodynamic properties of an airfoil have a decisive impact on the performance of various engineering applications, including airplane wings and wind turbine blades. Therefore, it is essential to analyze the aerodynamic characteristics of airfoils. Various analytical tools such as experiments, computational fluid dynamics, and Xfoil are used to perform these analyses, but each tool has its limitation. In this study, airfoil parameterization, image recognition, and artificial intelligence are combined to overcome these limitations. Image and coordinate data are collected from the UIUC airfoil database. Airfoil parameterization is performed by recognizing images from image data to build a database for deep learning. Trained model can predict the aerodynamic characteristics not only of airfoil images but also of sketches. The mean absolute error of untrained data is 0.0091.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3567-3582
• /
• 2020

Human activities are often affected by weather conditions. Automatic weather recognition is meaningful to traffic alerting, driving assistance, and intelligent traffic. With the boost of deep learning and AI, deep convolutional neural networks (CNN) are utilized to identify weather situations. In this paper, a three-channel convolutional neural network (3C-CNN) model is proposed on the basis of ResNet50.The model extracts global weather features from the whole image through the ResNet50 branch, and extracts the sky and ground features from the top and bottom regions by two CNN5 branches. Then the global features and the local features are merged by the Concat function. Finally, the weather image is classified by Softmax classifier and the identification result is output. In addition, a medium-scale dataset containing 6,185 outdoor weather images named WeatherDataset-6 is established. 3C-CNN is used to train and test both on the Two-class Weather Images and WeatherDataset-6. The experimental results show that 3C-CNN achieves best on both datasets, with the average recognition accuracy up to 94.35% and 95.81% respectively, which is superior to other classic convolutional neural networks such as AlexNet, VGG16, and ResNet50. It is prospected that our method can also work well for images taken at night with further improvement.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.813-826
• /
• 2022

AI-based image processing technologies in various fields have been widely studied. However, the lighter the board, the more difficult it is to reduce the weight of image processing algorithm due to a lot of computation. In this paper, we propose a method using deep learning for object recognition algorithm in lightweight embedded boards. We can determine the area using a deep neural network architecture algorithm that processes semantic segmentation with a relatively small amount of computation. After masking the area, by using more accurate deep learning algorithm we could operate object detection with improved accuracy for efficient neural network (ENet) and You Only Look Once (YOLO) toward executing object recognition in real time for lightweighted embedded boards. This research is expected to be used for autonomous driving applications, which have to be much lighter and cheaper than the existing approaches used for object recognition.

• Proceedings of the IEEK Conference
• /
• 2001.06c
• /
• pp.237-240
• /
• 2001

An image processing and decision making method for the Automatic Surveillance System is proposed. The aim of our Automatic Surveillance System is to detect a moving object and make a decision on whether it is human or not. Various object features such as the ratio of the width and the length of the moving object, the distance dispersion between the principal axis and the object contour, the eigenvectors, the symmetric axes, and the areas if the segmented region are used in this paper. These features are not the unique and decisive characteristics for representing human Also, due to the outdoor image property, the object feature information is unavoidably vague and inaccurate. In order to make an efficient decision from the information, we use a fuzzy rules base system ai an approximate reasoning method. The fuzzy rules, combining various object features, are able to describe the conditions for making an intelligent decision. The fuzzy rule base system is initially constructed by heuristic approach and then, trained and tasted with input/output data Experimental result are shown, demonstrating the validity of our system.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.453-458
• /
• 2024

Optical Character Recognition is the technology that recognizes text in images and converts them into digital format. Deep learning-based OCR is being used in many industries with large quantities of recorded data due to its high recognition performance. To improve medical services, deep learning-based OCR was actively introduced by the medical industry. In this paper, we discussed trends in OCR engines and medical OCR and provided a roadmap for development of medical OCR. By using natural language processing on detected text data, current medical OCR has improved its recognition performance. However, there are limits to the recognition performance, especially for non-standard handwriting and modified text. To develop advanced medical OCR, databaseization of medical data, image pre-processing, and natural language processing are necessary.

• Journal of the Korean Society of Radiology
• /
• v.17 no.6
• /
• pp.881-887
• /
• 2023

This study aims to analyze the development and current trends of AI-based medical imaging devices commercialized in South Korea. As of September 30, 2023, there were a total of 186 AI-based medical devices licensed, certified, and reported to the Korean Ministry of Food and Drug Safety, of which 138 were related to imaging. The study comprehensively examined the yearly approval trends, equipment types, application areas, and key functions from 2018 to 2023. The study found that the number of AI medical devices started from four products in 2018 and grew steadily until 2023, with a sharp increase after 2020. This can be attributed to the interaction between the advancement of AI technology and the increasing demand in the medical field. By equipment, AI medical devices were developed in the order of CT, X-ray, and MR, which reflects the characteristics and clinical importance of the images of each equipment. This study found that the development of AI medical devices for specific areas such as the thorax, cranial nerves, and musculoskeletal system is active, and the main functions are medical image analysis, detection and diagnosis assistance, and image transmission. These results suggest that AI's pattern recognition and data analysis capabilities are playing an important role in the medical imaging field. In addition, this study examined the number of Korean products that have received international certifications, particularly the US FDA and European CE. The results show that many products have been certified by both organizations, indicating that Korean AI medical devices are in line with international standards and are competitive in the global market. By analyzing the impact of AI technology on medical imaging and its potential for development, this study provides important implications for future research and development directions. However, challenges such as regulatory aspects, data quality and accessibility, and clinical validity are also pointed out, requiring continued research and improvement on these issues.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.250-252
• /
• 2022

Recently, with the development of IoT technology and AI, unmanned and automated systems are progressing in various fields, and various application technologies are being studied in systems using algorithms such as object detection, recognition, and tracking. In the case of a system operating based on an image, noise removal is performed as a pre-processing process, and precise noise removal is sometimes required depending on the environment of the system. In this paper, we propose a modified central weight filter algorithm using pixel division of local regions to minimize the blurring that tends to occur in the filtering process and to emphasize the details of the resulting image. In the proposed algorithm, when a pixel of a local area is divided into two areas, the center of the dominant area among the divided areas is set as a criterion for the weight filter algorithm. The resulting image is calculated by convolving the transformed center weight with the pixel value inside the filtering mask.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.420-426
• /
• 2022

Breast cancer is among the cancers that may be healed as the disease diagnosed at early times before it is distributed through all the areas of the body. The Automatic Analysis of Diagnostic Tests (AAT) is an automated assistance for physicians that can deliver reliable findings to analyze the critically endangered diseases. Deep learning, a family of machine learning methods, has grown at an astonishing pace in recent years. It is used to search and render diagnoses in fields from banking to medicine to machine learning. We attempt to create a deep learning algorithm that can reliably diagnose the breast cancer in the mammogram. We want the algorithm to identify it as cancer, or this image is not cancer, allowing use of a full testing dataset of either strong clinical annotations in training data or the cancer status only, in which a few images of either cancers or noncancer were annotated. Even with this technique, the photographs would be annotated with the condition; an optional portion of the annotated image will then act as the mark. The final stage of the suggested system doesn't need any based labels to be accessible during model training. Furthermore, the results of the review process suggest that deep learning approaches have surpassed the extent of the level of state-of-of-the-the-the-art in tumor identification, feature extraction, and classification. in these three ways, the paper explains why learning algorithms were applied: train the network from scratch, transplanting certain deep learning concepts and constraints into a network, and (another way) reducing the amount of parameters in the trained nets, are two functions that help expand the scope of the networks. Researchers in economically developing countries have applied deep learning imaging devices to cancer detection; on the other hand, cancer chances have gone through the roof in Africa. Convolutional Neural Network (CNN) is a sort of deep learning that can aid you with a variety of other activities, such as speech recognition, image recognition, and classification. To accomplish this goal in this article, we will use CNN to categorize and identify breast cancer photographs from the available databases from the US Centers for Disease Control and Prevention.