• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.8 no.2
• /
• pp.133-138
• /
• 2014

In this paper, a simple but efficient gait recognition method using spatial-temporal silhouette analysis is proposed. For each image sequence, a background subtraction algorithm and a PBAS(pixel based adaptive segmenter) procedure are first used to segment the moving silhouettes of a walking figure. Then, to identify people, the step count and stride length of walking figure is obtained in silhouette images. Experimental results on a CASIA dataset including 124 subjects demonstrate the validity of the proposed method. Also, the proposed system are believed to have a sufficient feasibility for the application to gait recognition.

• Journal of the Semiconductor & Display Technology
• /
• v.9 no.3
• /
• pp.59-63
• /
• 2010

This paper proposes computer visual inspection algorithms for various LCD defects which are found in a manufacturing process. Modular vision processing steps are required in order to detect different types of LCD defects. Those key modules include RGB filtering for pixel defects, gray-scale morphological processing and Hough transform for line defects, and adaptive threshold for spot defects. The proposed algorithms can give users detailed information on the type of defects in the LCD panel, the size of defect, and its location. The machine vision inspection system is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiment results show that the proposed algorithms are quite successful.

• Journal of the Semiconductor & Display Technology
• /
• v.8 no.2
• /
• pp.23-29
• /
• 2009

To increase the data capacity of one-dimensional symbology, 2D barcodes have been proposed a decade ago. In this paper, a new 2D barcode detection algorithm based on Local Binary Pattern is presented. To locate 2D barcode symbols, a texture analysis scheme based on the Local Binary Pattern is adopted, and a gray-scale projection with sub-pixel operation is utilized to separate the symbol precisely from the input image. Finally, the segmented symbol is normalized using the inverse perspective transformation for the decoding process. The proposed method ensures high performances under various lighting/printing conditions and strong perspective deformations. Experiments show that our method is very robust and efficient in detecting the symbol area for the various types of 2D barcodes.

• Journal of the Optical Society of Korea
• /
• v.5 no.2
• /
• pp.43-48
• /
• 2001

A three-dimensional (3D) display system based on computer-generated integral photography (CGIP) is proposed and its feasibility is discussed. Instead of the pickup process in conventional If, the elemental images of imaginary objects are computer-generated. Using these images, we observed autostereoscopic 3D images in full color and full parallax. The lateral and depth resolutions of the integrated images are limited by some factors such as the image position, object thickness, the lens width, and the pixel size of display panel.

• Journal of the Optical Society of Korea
• /
• v.5 no.3
• /
• pp.117-122
• /
• 2001

A three-dimensional (3D) display system based on computer-generated integral photography (CGIP) is proposed and its feasibility is discussed. Instead of the pickup process in conventional IP, the elemental images of imaginary objects are computer-generated. Using these images, we observed autostereoscopic 3D images in full color and full parallax. The lateral and depth resolutions of the integrated images are limited by some factors such as the image position, object thickness, the lens width, and the pixel size of display panel.

• Imaging Science in Dentistry
• /
• v.51 no.3
• /
• pp.323-328
• /
• 2021

Tooth extraction after head and neck radiotherapy exposes patients to an increased risk for osteoradionecrosis of the jaw. This study reports the results of a radiographic analysis of bone neoformation after tooth extraction in a case series of patients who underwent radiation therapy. No patients developed osteoradionecrosis within a follow-up of 1 year. Complete mucosal repair was observed 30 days after surgery, while no sign of bone formation was observed 2 months after the dental extractions. Pixel intensity and fractal dimension image analyses only showed significant bone formation 12 months after the tooth extractions. These surgical procedures must follow a strict protocol that includes antibiotic prophylaxis and therapy and complete wound closure, since bone formation at the alveolar socket occurs at a slower pace in patients who have undergone head and neck radiotherapy.

• International journal of advanced smart convergence
• /
• v.7 no.4
• /
• pp.147-153
• /
• 2018

This study is about the interactive self-portrait which provides the experience of self-consciousness reflection of the viewer to modern people who are easily alienated in rapid social change. We proposed interactive self-portrait is implemented by an interactive mirror that reproduces the appearance of the viewer acquired using a webcam. The interactive mirror, which can directly project its own image, is drawn by searching news articles in real time and using the extracted characters as pixel information in real time. The viewer has the opportunity to experience a new style of active self-expression while watching his/herself composed of news characters that are issues of modern society. The virtual self-portrait designed with news characters can attract viewers' attention by visually expressing the interests of modern people and can act as an incentive to generate positive interaction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2115-2127
• /
• 2021

Although significant progress has been made in synthesizing visually realistic face images by Generative Adversarial Networks (GANs), there still lacks effective approaches to provide fine-grained control over the generation process for semantic facial attribute editing. In this work, we propose a novel cross channel self-attention based generative adversarial network (CCA-GAN), which weights the importance of multiple channels of features and archives pixel-level feature alignment and conversion, to reduce the impact on irrelevant attributes while editing the target attributes. Evaluation results show that CCA-GAN outperforms state-of-the-art models on the CelebA dataset, reducing Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) by 15~28% and 25~100%, respectively. Furthermore, visualization of generated samples confirms the effect of disentanglement of the proposed model.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.7
• /
• pp.58-65
• /
• 2021

Research on general particle image velocimetry (PIV) has been conducted extensively, but studies on granular PIV are relatively insufficient. In addition, the parameters used for analyzing granular PIV need to be optimized. In this study, we analyzed the error of velocity measurements based on the interrogation area (64-192 pixel), frame per second (30-120 FPS), and video resolution [ultrahigh definition (UHD) and high definition (HD)] within the velocity range typically measured in hoppers. The estimated errors of the granular PIV were below 5%, which is generally acceptable. However, considering the data reliability, the flow velocity in the hopper could be measured with less than 5% error at 120 FPS or higher in the HD resolution and 30 FPS or higher in the UHD resolution.

• Annual Conference of KIPS
• /
• 2009.04a
• /
• pp.1194-1197
• /
• 2009

최근 무선인터넷 기술은 급속히 발전하고 있으며 새로운 모바일 미디어를 통하여 일상생활에 직간접적으로 많은 영향을 끼치고 있다. 본 연구에서는 모바일 폰에 의한 촬영으로 이미지의 픽셀(Pixel) 정보를 얻어내고 DB에 저장된 레퍼런스(Reference)이미지와 비교하여 근접 값을 검색하는 알고리즘을 제안한다. 이것은 눈앞에 보이는 사물에 대한 정보에 대하여 소지하고 있는 모바일 폰으로 이미지를 촬영한 후 인터넷 검색을 통해 알 수 있는 가능성을 제시한다. 실제 촬영 이미지에서 한글 문자를 검색한 후 인터넷을 이용해 그에 대한 정보를 검색하는 시스템을 구현 하였다.