• Journal of KIISE
• /
• v.43 no.11
• /
• pp.1298-1306
• /
• 2016

Backlight has a major factor in power consumption of TFT-LCDs which are most popular in portable devices. There have been a lot of attempts to achieve power savings by backlight dimming. At the same time, the researches have shown image compensation due to decreased brightness of a displayed image. However, existing image compensation methods such as histogram equalization have some limits in completely satisfying the human visual system (HVS)-awareness. This paper proposes an enhanced dimming technique to obtain both power saving and HVS-awareness by combining pixel compensation and histogram specification for TFT-LCDs. This method executes a search algorithm and an automation algorithm employing simplified calculations for fast image processing. Experimental results showed that the proposed method achieved significant improvement in visual satisfaction per power saving over existing backlight dimming.

• Journal of KIISE
• /
• v.42 no.1
• /
• pp.93-96
• /
• 2015

The SIFT method is well-known for robustness against various image transformations, and is widely used for image retrieval and matching. The SIFT method extracts keypoints using scale space analysis, which is different from conventional keypoint detection methods that depend only on the image space. The SIFT method has also been extended to use higher-order scale space derivatives for increasing the number of keypoints detected. Such detection of additional keypoints detected was shown to provide performance gain in image retrieval experiments. Herein, a sigma based normalization method for keypoint detection is introduced using higher-order scale space derivatives.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1177-1183
• /
• 2018

Recent developments in machine learning have attracted a lot of attention for techniques such as machine learning and deep learning that implement artificial intelligence. In this paper, binary malicious code using deep learning based R-CNN is imaged and the feature is extracted from the image to classify the family. In this paper, two steps are used in deep learning to image malicious code using CNN. And classify the characteristics of the family of malicious codes using R-CNN. Generate malicious code as an image, extract features, classify the family, and automatically classify the evolution of malicious code. The detection rate of the proposed method is 93.4% and the accuracy is 98.6%. In addition, the CNN processing speed for image processing of malicious code is 23.3 ms, and the R-CNN processing speed is 4ms to classify one sample.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.7
• /
• pp.129-136
• /
• 2019

In this study, the magnetic flux leakage technique was applied to diagnose steel plate damage, imaging technique was applied through those signals. Steel plate specimens with different thicknesses were prepared for the imaging the magnetic flux leakage signal, and 6 different depths of damage were artificially processed at the same locations on each specimen. The sensor head consist hall sensor and magnetization yoke was fabricated to magnetize the steel plate specimen and measure the magnetic flux leakage signal. In order to remove the noise and increase the resolution of the image in the signal collected from the hall sensor, various of signal processing was performed. P-P value was analyzed for each channel to analyze the magnetic flux leakage signals measured from each damaged part. Based on the above processed signals and analysis, it was converted into heatmap image. Through this, it was possible to identify the damage on the steel plate at glance by imaging magnetic flux leakage signal.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.6
• /
• pp.161-165
• /
• 2007

The process of selecting a small number of representative colors from an image of higher color resolution is called color image quantization. In a color quantization process, it is vet important to determine what colors should be preserve and the others not. In our study, by the idea of an image can be divided into interesting area and uninteresting area, we propose a color quantization method that preserves more colors in the interesting area of an image. We evaluated correctness of extracting interesting area and compared the quality of our method with the others.

• Journal of Korea Multimedia Society
• /
• v.12 no.10
• /
• pp.1418-1426
• /
• 2009

There has been a lot of interest in an effective method for background subtraction in an effort to separate foreground objects from a predefined background image. Promising results on background subtraction using statistical methods have recently been reported are robust enough to operate in dynamic environments, but generally require very large computational resources and still have difficulty in obtaining clear segmentation of objects. We use a simple running-average method to model a gradually changing background, instead of using a complicated statistical technique. We employ a single global threshold vector, optimized by a genetic algorithm, instead of pixel-by-pixel thresholds. A new fitness function is defined and trained to evaluate segmentation result. The system has been implemented on a PC with a webcam, and experimental results on real images show that the new method outperforms an existing method based on a mixture of Gaussian.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.153-156
• /
• 1998

JPEG은 정지 영상의 압축 표준으로 8$\times$8 블록을 기반으로 DCT 변환을 한 후 양자화 및 엔트로피 부호화 과정을 통해 압축이 이루어진다. DCT는 이미지를 공간 영역에서 주파수 영역으로 변환하는 기법으로 대체로 저주파 성분은 저주파 성분끼리, 고주파 성분은 고주파 성분끼리 모아준다. 이러한 형태는 필요 없는 성분들을 쉽게 제거할 수 있어 압축이 효율적으로 이루어지도록 한다. 블록 기반의 압축 기법을 적용할 때 흔히 나타나는 문제점은 블록 기반으로 인해 발생하는 블？킹 현상으로서 이는 양자화로 인한 정보의 손실에서 비롯되며 그 기본이 되는 8$\times$8 블록 단위로 나타난다. 본 연구세어서는 작은 블록 단위를 16$\times$16의 매크로블록으로 확대한 개념을 이용하여 매크로 블록 내의 수직 및 수평 방향으로 1:2단위로 샘플링한 4개의 8$\times$8블록 간의 블록킹 경계로 없애 주도록 하고자 한다. 또한 16$\times$16의 DCT 블록 대신 16$\times$16 블록내의 8$\times$8 블록들을 이용함으로써 표준 기법에서 이용되는 8$\times$8 단위의 양자화 테이블이나 RLE기법 등을 그대로 적용할 수 있다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.25-34
• /
• 2010

Robust face recognition under various illumination environments is difficult to achieve. For robust face recognition with respect to illumination variations, illumination normalization of face images is usually applied as a preprocessing step. Most of previously proposed illumination normalization methods cannot handle cast shadows in face images effectively. In this paper, We propose a new face illumination normalization method based on the illumination-separated face identity texture subspace. Since the face identity texture subspace is constructed so as to be separated from the effects of illumination variations, the projection of face images into the subspace produces a good illumination-normalized face images. Through experiments, it is shown that the proposed face illumination normalization method can effectively eliminate cast shadows as well as attached shadows and achieves a good face illumination normalization.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.12
• /
• pp.2931-2946
• /
• 1997

In multimedia information retrieval applications, content-based image retrieval is essential for retrieving relevant multimedia documents. The purpose of our paper is to provide effective representation and efficient retrieval of images when a pixel-level original image is automatically or manually transformaed into its iconic image containing meaningful graphic descriptions, called icon objects. For this, we first propose new spatial match representationschemes to describe spatial relationships between icon objects accurately by expressing them as rectangles, rather than as points. In order to accelerate image searching, we also design an efficient retrieval method using a two-dimensional signature file organization. Finally, we show from our experiment that the proposed representation schemes achieve better retrieval effectiveness than the 9-DLT (Direction Lower Triangular) scheme.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.11a
• /
• pp.144-145
• /
• 2016

디지털 컨텐츠는 UHD, 3D, 파노라마 영상 등 다양한 형태로 발전되고 있다. 그 중 파노라마 영상은 여러 영상을 정합하여 넓은 시야각을 제공하는 컨텐츠로 전문적인 기술자들을 중심으로 제작되고 있다. 또한 디지털 컨텐츠의 제작자는 전문가에서 일반인으로까지 범위가 확장되었고, 발전된 형태의 컨텐츠를 일반인이 스마트폰 등의 개인 단말로 손쉽게 제작할 수 있도록 해주는 컨텐츠 생성 기술이 발달되고 있다. 이에 본 논문에서는 일반 사용자들이 각각의 스마트폰 단말로 촬영한 여러 동영상들을 하나의 파노라마 영상으로 제작하기위한 기술 중, 각기 다른 스마트폰의 시간축을 이미지 매칭을 통해 하나의 통일된 시간축으로 동기화 시키는 기법에 관하여 연구하였다. 이를 위해, 본 논문에서는 동영상에서 시간정보로 이용하기 위한 오브젝트의 움직임이 포함된 시퀀스를 찾는 방법과 해당 시퀀스를 이용하여 다른 동영상과의 이미지 매칭으로 시간축을 동기화 시키는 방법을 제안한다.