• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.112-115
• /
• 2022

The process of deep learning usually needs to deal with massive data which has greatly limited the development of deep learning technologies today. Convolutional Neural Network (CNN) structure is often used to solve image classification problems. However, a large number of images may be required in order to train an image in CNN, which is a heavy burden for existing computer systems to handle. If the image data can be compressed under the premise that the computer hardware system remains unchanged, it is possible to train more datasets in deep learning. However, image compression usually adopts the form of lossy compression, which will lose part of the image information. If the lost information is key information, it may affect learning performance. In this paper, we will analyze the effect of image compression on deep learning performance on CNN-based cat and dog classification. Through the experiment results, we conclude that the compression of images does not have a significant impact on the accuracy of deep learning.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.825-828
• /
• 2022

In this paper, we propose an efficient image size selection method for video-based point cloud compression. The current MPEG video-based point cloud compression reference encoding process configures a threshold on the size of images while converting point cloud data into images. Because the converted image is compressed and restored by the legacy video codec, the size of the image is one of the main components in influencing the compression efficiency. If the image size can be made smaller than the image size determined by the threshold, compression efficiency can be improved. Here, we studied how to improve the compression efficiency by selecting the best-fit image size generated during video-based point cloud compression. Experimental results show that the proposed method can reduce the encoding time by 6 percent without loss of coding performance compared to the test model 15.0 version of video-based point cloud encoder.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.4
• /
• pp.333-337
• /
• 2002

A content-based image retrieval method using color, texture, and shape features is proposed in this paper. A region segmentation technique using PIM(Picture Information Measure) entropy is used for similarity indexing. For segmentation, a color image is first transformed to a gray image and it is divided into n$\times$n non-overlapping blocks. Entropy using PIM is obtained from each block. Adequate variance to perform good segmentation of images in the database is obtained heuristically. As variance increases up to some bound, objects within the image can be easily segmented from the background. Therefore, variance is a good indication for adequate image segmentation. For high variance image, the image is segmented into two regions-high and low entropy regions. In high entropy region, hue-saturation-intensity and canny edge histograms are used for image similarity calculation. For image having lower variance is well represented by global texture information. Experiments show that the proposed method displayed similar images at the average of 4th rank for top-10 retrieval case.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.3E
• /
• pp.26-29
• /
• 1999

In this paper, we propose a new voice coding using only the features of the face image such as mouth height(H), width(W), rate(R=W/H), area(S), and ellipse's feature(P). It provides high security and is not affected by acoustic noise because we use only the features of face image for speech. In the proposed algorithm, the mean recognition rate for the vowels approximately rises between 70% and 96% after many tests.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2009.10a
• /
• pp.103-105
• /
• 2009

A Study on the Replace Broadcasting Image Lighting fixture of LED so electrical charges, eye many of be dazzling, very hot of tungsten halogen light fixture take a photograph studio image in low space studio

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.41.5-41
• /
• 2002

This paper presents a feature extraction algorithm for vision-based micromanipulation. In order to guarantee of the accurate micromanipulation, most of micromanipulation systems use vision sensor. Vision data from an optical microscope or high magnification lens have vast information, however, characteristics of micro image such as emphasized contour, texture, and noise are make it difficult to apply macro image processing algorithms to micro image. Grasping points extraction is very important task in micromanipulation because inaccurate grasping points can cause breakdown of micro gripper or miss of micro objects. To solve those problems and extract grasping points for micromanipulation...

• Proceedings of the Korea Society of Costume Conference
• /
• 2003.10a
• /
• pp.57-57
• /
• 2003

Present avartar market is expanding with rapid development of the internet and its contents. Therefore, apparel industry is experimenting PPL by providing their products with avartar. Objectives of this study are to investigate about the avartar's fashion products efficiency on casual garment advertisements to study about the effect of avartar's clothing image provided by apparel industry and investigate about the effect of avartar's fashion product on apparel advertisement for fundamental data on the avartar's fashion marketing.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2002.08a
• /
• pp.153-156
• /
• 2002

We have developed a pixel structure for reflective color TFT-LCD which can display 27-color in still-image. The proposed pixel can display 3 gray scale in still image; white, black and median gray. This paper shows the concept and the driving method of the proposed pixel. Finally this paper compares power consumption and area with the Toshiba's DMOG technology.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2002.08a
• /
• pp.285-288
• /
• 2002

We propose the use of synchronously moving micro-optics (lenslet arrays) for image pickup and display in three-dimensional integral imaging to overcome the upper resolution limit imposed by the Nyquist sampling theorem. With the proposed technique, we present an all-optical three-dimensional integral imaging projector. An optically addressed spatial light modulator is used, which potentially provides better image resolution than the conventional CCD and liquid crystal display pair. We present experimental results using a liquid crystal light valve.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2002.05a
• /
• pp.1093-1096
• /
• 2002

In this paper, a new semi-automated cyber character generating method is presented. Local edge detection tools extract face contour from graphic image files. Some graphic manipulation process detailed touch to obtain neat face contour. This method shortens the making process dramatically while maintaining the good quality similar to real face image. Some of the processed images are illustrated for clear explanation.