• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.2
• /
• pp.428-434
• /
• 2015

A new tongue examination model by using color analysis according to the taste division of tongue. The proposed system consists of a tongue image acquisition in a predefined template, taste region segmentation, color distribution analysis and abnormality decision of tongue by color analysis using Hue-Saturation histograms and the part of a mobile application service. We divided 4 basic taste(bitter, sweet, salty and sour) regions and performed color distribution analysis targeting each region under HSI(Hue Saturation Intensity) color model. To minimize the influence of illumination, the histograms of H and S components only except U are utilized. Using the analyzed results, the abnormality is discriminated by the criteria of the histogram range of normal tongues. Finally, a self tongue diagnosis system which can be used anytime and anywhere on mobile environment.

• Korean Journal of Remote Sensing
• /
• v.22 no.2
• /
• pp.123-129
• /
• 2006

High-resolution aerial color image offers great possibilities for geometric and semantic information for spatial data generation. However, shadow casts by buildings and trees in high-density urban areas obscure much of the information in the image giving rise to potentially inaccurate classification and inexact feature extraction. Though many researches have been implemented for solving shadow casts, few studies have been carried out about the extraction of features hindered by shadows from aerial color images in urban areas. This paper presents a asphalt road boundary extraction technique that combines information from aerial color image and LIDAR (LIght Detection And Ranging) data. The following steps have been performed to remove shadow effects and to extract road boundary from the image. First, the shadow regions of the aerial color image are precisely located using LEAR DSM (Digital Surface Model) and solar positions. Second, shadow regions assumed as road are corrected by shadow path reconstruction algorithms. After that, asphalt road boundary extraction is implemented by segmentation and edge detection. Finally, asphalt road boundary lines are extracted as vector data by vectorization technique. The experimental results showed that this approach was effective and great potential advantages.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.390-397
• /
• 2021

As digital twin technology is applied to various industrial fields, technologies to effectively process large amounts of data are required. In this paper, we discuss a customized service method for fast search and effective delivery of large-scale data for underground facility for public utilities management. The proposed schemes are divided into two ways: a fast search data generation method and a customized information service segmentation method to efficiently search and abbreviate vast amounts of data. In the high-speed search data generation, we discuss the configuration of the synchronization process for the time series analysis of the sensors collected in the underground facility and the additional information method according to the data reduction. In the user-customized service method, we define the types of users in normal and disaster situations, and discuss how to service them accordingly. Through this study, it is expected to be able to develop a systematic data generation and service model for the management of underground utilities that can effectively search and receive large-scale data in a disaster situation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.6
• /
• pp.645-651
• /
• 2019

At a time when large amounts of data are being poured out, there are many changes in software architecture or data storage patterns because of the nature of the data being written, rather more read-intensive than writing. Accordingly, in this paper, the query model of Command Query Responsibility Segmentation (CQRS) pattern separating the responsibilities of commands and queries is used to implement an efficient high-capacity data lookup system in users' requirements. This paper uses the 2018 temperature, humidity and precipitation data of the Korea Meteorological Administration Open API to store about 2.3 billion data suitable for RDBMS (PostgreSQL) and NoSQL (MongoDB). It also compares and analyzes the performance of systems with CQRS pattern applied from the perspective of the web server (Web Server) implemented and systems without CQRS pattern, the storage structure performance of each database, and the performance corresponding to the data processing characteristics.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.4
• /
• pp.95-105
• /
• 2021

Road surface damage detection is essential for a comfortable driving environment and the prevention of safety accidents. Road management institutes are using automated technology-based inspection equipment and systems. As one of these automation technologies, a sensor to detect road surface damage plays an important role. For this purpose, several studies on sensors using deep learning have been conducted in recent years. Road images and label images are needed to develop such deep learning algorithms. On the other hand, considerable time and labor will be needed to secure label images. In this paper, the adversarial learning method, one of the semi-supervised learning techniques, was proposed to solve this problem. For its implementation, a lightweight deep neural network model was trained using 5,327 road images and 1,327 label images. After experimenting with 400 road images, a model with a mean intersection over a union of 80.54% and an F1 score of 77.85% was developed. Through this, a technology that can improve recognition performance by adding only road images was developed to learning without label images and is expected to be used as a technology for road surface management in the future.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.2_1
• /
• pp.177-184
• /
• 2022

The automatic defect sorting function of machinery parts is being introduced to the automation of the manufacturing process. In the final stage of automation of the manufacturing process, it is necessary to apply computer vision rather than human visual judgment to determine whether there is a defect. In this paper, we introduce a deep learning method to improve the classification performance of typical mechanical parts, such as welding parts, galvanized round plugs, and electro galvanized nuts, based on the results of experiments. In the case of poor welding, the method to further increase the depth of layer of the basic deep learning model was effective, and in the case of a circular plug, the surrounding data outside the defective target area affected it, so it could be solved through an appropriate pre-processing technique. Finally, in the case of a nut plated with zinc, since it receives data from multiple cameras due to its three-dimensional structure, it is greatly affected by lighting and has a problem in that it also affects the background image. To solve this problem, methods such as two-dimensional connectivity were applied in the object segmentation preprocessing process. Although the experiments suggested that the proposed methods are effective, most of the provided good/defective images data sets are relatively small, which may cause a learning balance problem of the deep learning model, so we plan to secure more data in the future.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.111-118
• /
• 2022

In computer vision research, the two-dimensional human pose is a very extensive research direction, especially in pose tracking and behavior recognition, which has very important research significance. The acquisition of human pose targets, which is essentially the study of how to accurately identify human targets from pictures, is of great research significance and has been a hot research topic of great interest in recent years. Human pose recognition is used in artificial intelligence on the one hand and in daily life on the other. The excellent effect of pose recognition is mainly determined by the success rate and the accuracy of the recognition process, so it reflects the importance of human pose recognition in terms of recognition rate. In this human body gesture recognition, the human body is divided into 17 key points for labeling. Not only that but also the key points are segmented to ensure the accuracy of the labeling information. In the recognition design, use the comprehensive data set MS COCO for deep learning to design a neural network model to train a large number of samples, from simple step-by-step to efficient training, so that a good accuracy rate can be obtained.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.237-250
• /
• 2022

Structural health monitoring (SHM) plays an important role in ensuring the safety and functionality of critical civil infrastructure. In recent years, numerous researchers have conducted studies to develop computer vision and machine learning techniques for SHM purposes, offering the potential to reduce the laborious nature and improve the effectiveness of field inspections. However, high-quality vision data from various types of damaged structures is relatively difficult to obtain, because of the rare occurrence of damaged structures. The lack of data is particularly acute for fatigue crack in steel bridge girder. As a result, the lack of data for training purposes is one of the main issues that hinders wider application of these powerful techniques for SHM. To address this problem, the use of synthetic data is proposed in this article to augment real-world datasets used for training neural networks that can identify fatigue cracks in steel structures. First, random textures representing the surface of steel structures with fatigue cracks are created and mapped onto a 3D graphics model. Subsequently, this model is used to generate synthetic images for various lighting conditions and camera angles. A fully convolutional network is then trained for two cases: (1) using only real-word data, and (2) using both synthetic and real-word data. By employing synthetic data augmentation in the training process, the crack identification performance of the neural network for the test dataset is seen to improve from 35% to 40% and 49% to 62% for intersection over union (IoU) and precision, respectively, demonstrating the efficacy of the proposed approach.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.21-32
• /
• 2022

Image labeling must be preceded in order to perform object detection, and this task is considered a significant burden in building a deep learning model. Tens of thousands of images need to be trained for building a deep learning model, and human labelers have many limitations in labeling these images manually. In order to overcome these difficulties, this study proposes a method to perform object detection without significant performance degradation, even though labeling some images rather than the entire image. Specifically, in this study, low-resolution oriental painting images are converted into high-quality images using a super-resolution algorithm, and the effect of SSIM and PSNR derived in this process on the mAP of object detection is analyzed. We expect that the results of this study can contribute significantly to constructing deep learning models such as image classification, object detection, and image segmentation that require efficient image labeling.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.83-92
• /
• 2009

In this paper, an extended snake algorithm using color variance energy is proposed for segmenting an interest object in color image. General snake algorithm makes use of energy in image to segment images into a interesting area and background. There are many kinds of energy that can be used by the snake algorithm. The efficiency of the snake algorithm is depend on what kind of energy is used. A general snake algorithm based on active contour model uses the intensity value as an image energy that can be implemented and analyzed easily. But it is sensitive to noises because the image gradient uses a differential operator to get its image energy. And it is difficult for the general snake algorithm to be applied on the complex image background. Therefore, the proposed snake algorithm efficiently segment an interest object on the color image by adding a color variance of the segmented area to the image energy. This paper executed various experiments to segment an interest object on color images with simple or complex background for verifying the performance of the proposed extended snake algorithm. It shows improved accuracy performance about 12.42 %.