• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.822-823
• /
• 2014

The usual method of generating an image for a multiview display system requires acquiring a color image and depth information of a reference camera. Then, intermediate images, generated using DIBR method, will be captured at a number of different viewpoints and composed to construct an multiview image. When such intermediate views are generated, several holes would be shown because some hidden parts are shown when the screenshot is taken at different angle. Previous research tried to solve this problem by creating a new hole-filling algorithm or enhancing the depth information. This paper describes a new method of enhancing the intermediate view images by applying the Ball Pivoting algorithm, which constructs meshes from a point cloud. When the new method is applied to the Microsoft's "Ballet" and "Break Dancer" data sets, PSNR comparison shows that about 0.18~1.19 increasement. This paper will explaing the new algorithm and the experiment method and results.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.3
• /
• pp.55-65
• /
• 2019

Although crack on concrete exists from its early formation, crack requires attention as it affects stiffness of structure and can lead demolition of structure as it grows. Detecting cracks on concrete is needed to take action prior to performance degradation of structure, and deep learning can be utilized for it. In this study, transfer learning, one of the deep learning techniques, was used to detect the crack, as the amount of crack's image data was limited. Pre-trained Inception-v3 was applied as a base model for the transfer learning. Web scrapping was utilized to fetch images of concrete wall with or without crack from web. In the recognition of crack, image post-process including changing size or removing color were applied. In the visualization of crack, source images divided into 30px, 50px or 100px size were used as input data, and different numbers of input data per category were applied for each case. With the results of visualized crack image, false positive and false negative errors were examined. Highest accuracy for the recognizing crack was achieved when the source images were adjusted into 224px size under gray-scale. In visualization, the result using 50 data per category under 100px interval size showed the smallest error. With regard to the false positive error, the best result was obtained using 400 data per category, and regarding to the false negative error, the case using 50 data per category showed the best result.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.672-678
• /
• 2020

Ultra-high-speed images that accurately depict the minute movements of objects have become common as low-cost and high-performance cameras that can film at high speeds have emerged. In this paper, the proposed method removes unexpected noise contained in images after input at high speed, and then extracts an area of interest that can represent personal information, such as skin areas, from the image in which noise has been removed. In this paper, noise generated by abnormal electrical signals is removed by applying bilateral filters. A color model created through pre-learning is then used to extract the area of interest that represents the personal information contained within the image. Experimental results show that the introduced algorithms remove noise from high-speed images and then extract the area of interest robustly. The approach presented in this paper is expected to be useful in various applications related to computer vision, such as image preprocessing, noise elimination, tracking and monitoring of target areas, etc.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.5
• /
• pp.45-54
• /
• 2009

In this paper, we propose an adult images detection algorithm using a mean intensity filter and an improved 2D Hough Transform. This paper is composed of three major steps including a training step, a recognition step, and a verification step. The training step generates a mean nipple variance filter that will be used for detecting nipple candidate regions in the recognition step. To make the mean variance filter, we converts an input color image into a gray scale image and normalize it, and make an average intensity filter for nipple areas. The recognition step first extracts edge images and finds connected components, and decides nipple candidate regions by considering the ratio of width and height of a connected component. It then decides final nipple candidates by calculating the similarity between the learned nipple average intensity filter and the nipple candidate areas. Also, it detects breast lines of an input image through the improved 2D Hough transform. The verification step detects breast areas and identifies adult images by considering the relations between nipple candidate regions and locations of breast lines.

• Design Convergence Study
• /
• v.15 no.6
• /
• pp.229-241
• /
• 2016

In generative design computer automatically and quickly generates many alternative design solutions, and the computer algorithms which perform the design tasks are important. The main purpose of this study is to propose a computer algorithm which generates three-dimensional shapes from a two-dimensional digital image such as a photograph or a painting. The base geometry of the final shape is a cylinder or sphere. A surface of the cylinder or sphere is deformed depending on the used image. The proposed algorithm was implemented as a computer program, and the program tested with several famous paintings. The algorithm and results presented in this study implicate the possibilities of the generative design which generates three-dimensional shapes from two-dimensional images. It is necessary to find and measure the values of the generated shape, and it will be a future research to find the relations of emotional and cognitive aspects between the input images and the generated shapes. Those studies are expected to expand the possibilities of generative design.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.463-465
• /
• 2021

Currently, the inspection method printed on food packages and boxes is to sample only a few products and inspect them with human eyes. Such a sampling inspection has the limitation that only a small number of products can be inspected. Therefore, accurate inspection using a camera is required. This paper proposes a deep learning object recognition technology model, which is an artificial intelligence technology, as a method for detecting the defects of expiration date printed on the product packaging. Using the Faster R-CNN (region convolution neural network) model, the color images, converted gray images, and converted binary images of the printed expiration date are trained and then tested, and each detection rates are compared. The detection performance of expiration date printed on the package by the proposed method showed the same detection performance as that of conventional vision-based inspection system.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.26 no.1
• /
• pp.1-16
• /
• 2024

This study aims to investigate the differences in blue jean styles and the visual images associated with them. To achieve this, literature reviews, case studies, and surveys were conducted. The results are as follows. 1) Based on previous studies, it was found that the design elements influencing the style of blue jeans and their visual images include waistline position, silhouette, details, decorations, and color. Additionally, differences in the preferences and visual evaluations of Korean and Chinese individuals regarding the style of blue jeans were confirmed. 2) Skinny blue jeans are typically characterized by a high waistline and a length that reaches the ankles, featuring a snug fit with stretchy fabric. Straight blue jeans, on the other hand, usually have a natural or high waistline and cover the instep, with a straight silhouette descending from the thigh to the hem. Bell-bottom blue jeans are primarily high-waisted and cover the instep with a silhouette forming a bell shape from the knee to the hem. 3) Korean and Chinese women in their 20s evaluated skinny, straight, and bell-bottom styles of blue jeans as having a 'casual' image. However, they also associated bell-bottom style blue jeans with 'unique' and 'attractive' images. Interestingly, Korean women described skinny-style blue jeans as making someone look 'youthful', while Chinese women perceived them as 'sophisticated', 'making the waist look thicker', and 'unassuming'. As for straight-style blue jeans, Korean women saw them as 'well-fitting', while Chinese women described them as 'making one appear taller', 'desirable', and 'free-spirited'.

• Journal of Internet of Things and Convergence
• /
• v.10 no.2
• /
• pp.51-60
• /
• 2024

Aiming at the problem of low contrast and difficult to recognize video images in low-light environment, we propose an adaptive contrast compensation enhancement algorithm based on human visual perception. First of all, the video image characteristic factors in low-light environment are extracted: AL (average luminance), ABWF (average bandwidth factor), and the mathematical model of human visual CRC(contrast resolution compensation) is established according to the difference of the original image's grayscale/chromaticity level, and the proportion of the three primary colors of the true color is compensated by the integral, respectively. Then, when the degree of compensation is lower than the bright vision precisely distinguishable difference, the compensation threshold is set to linearly compensate the bright vision to the full bandwidth. Finally, the automatic optimization model of the compensation ratio coefficient is established by combining the subjective image quality evaluation and the image characteristic factor. The experimental test results show that the video image adaptive enhancement algorithm has good enhancement effect, good real-time performance, can effectively mine the dark vision information, and can be widely used in different scenes.

• The Journal of Korean Medicine
• /
• v.44 no.4
• /
• pp.136-149
• /
• 2023

Objectives: Facial diagnosis is an important part of clinical diagnosis in traditional East Asian Medicine. In this paper, we proposed a model to quantitatively classify cold sensitivity using a fully automated facial image analysis system. Methods: We investigated cold sensitivity in 452 subjects. Cold sensitivity was determined using a questionnaire and the Cold Pattern Score (CPS) was used for analysis. Subjects with a CPS score below the first quartile (low CPS group) belonged to the cold non-sensitivity group, and subjects with a CPS score above the third quartile (high CPS group) belonged to the cold sensitivity group. After splitting the facial images into train/validation/test sets, the train and validation set were input into a convolutional neural network to learn the model, and then the classification accuracy was calculated for the test set. Results: The classification accuracy of the low CPS group and high CPS group using facial images in all subjects was 76.17%. The classification accuracy by sex was 69.91% for female and 62.86% for male. It is presumed that the deep learning model used facial color or facial shape to classify the low CPS group and the high CPS group, but it is difficult to specifically determine which feature was more important. Conclusions: The experimental results of this study showed that the low CPS group and the high CPS group can be classified with a modest level of accuracy using only facial images. There was a need to develop more advanced models to increase classification accuracy.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.6
• /
• pp.85-96
• /
• 2023

This study proposes a method for forest vegetation monitoring using high-resolution aerial imagery captured by unmanned aerial vehicles(UAV) and deep learning technology. The research site was selected in the forested area of Mountain Dogo, Asan City, Chungcheongnam-do, and the target species for monitoring included Pinus densiflora, Quercus mongolica, and Quercus acutissima. To classify vegetation species at the pixel level in UAV imagery based on characteristics such as leaf shape, size, and color, the study employed the semantic segmentation method using the prominent U-net deep learning model. The research results indicated that it was possible to visually distinguish Pinus densiflora Siebold & Zucc, Quercus mongolica Fisch. ex Ledeb, and Quercus acutissima Carruth in 135 aerial images captured by UAV. Out of these, 104 images were used as training data for the deep learning model, while 31 images were used for inference. The optimization of the deep learning model resulted in an overall average pixel accuracy of 92.60, with mIoU at 0.80 and FIoU at 0.82, demonstrating the successful construction of a reliable deep learning model. This study is significant as a pilot case for the application of UAV and deep learning to monitor and manage representative species among climate-vulnerable vegetation, including Pinus densiflora, Quercus mongolica, and Quercus acutissima. It is expected that in the future, UAV and deep learning models can be applied to a variety of vegetation species to better address forest management.