• The Journal of the Korea Contents Association
• /
• v.6 no.12
• /
• pp.21-28
• /
• 2006

In a face detection system based on template matching, histogram equalization or log transform is applied to an input image for the intensity normalization and the image improvement. It is known that they are noneffective in improving an image with intensity distortion by illumination variation. In this paper, we propose an efficient image improvement method using a simple regression analysis combined with a bilateral symmetry average for images with intensity distortion by illumination variation. Experimental results show that our method delivers the detection performance better than previous methods and also remarkably reduces the number of face candidates.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.153-156
• /
• 2001

본 논문에서는 하이브리드 패턴 벡터를 이용하여 차량 번호를 실시간으로 인식하는 알고리즘을 제안하였다. 차량 입력 영상에서 전처리 과정을 거쳐 번호판의 수평 및 수직 명암값 빈도수 변화를 이용해 번호판 영역을 추출하고 하이브리드 패턴을 적용해 더 정확한 번호판 문자 및 숫자를 인식하는 알고리즘을 제안하였다. 제안한 알고리즘의 번호판 추출 과정에서는 번호판 영역의 문자와 배경이 뚜렷하게 구별되는 특성 및 번호 판 영역의 상대적인 크기의 특성과 수평 및 수직 빈도 수를 추하여 입력된 차량영상에서 번호판 영역을 추출한다. 또한 번호판 영역에서 잡음 제거와 세선화(Thinning)를 적용해 문자 및 숫자를 하이브리드 패턴 벡터를 적용하여 문자의 크기, 문자와 문자 사이의 밀집도의 특성, 이동에 무관한 특성을 이용해 차량 번호를 인식하는 알고리즘을 제안하였다. 제안한 방법들을 적용한 결과 기존의 원형 패턴 벡터 보다 훨씬 계산 속도가 빠르며, 차량 번호판의 크기에 관계없이 잡음에 영향을 받지 않고 차량 번호를 실시간으로 처리할 수 있는 가능성을 제시하였고, 번호판 영역이 불규칙한 조명 상태에서도 더 정확한 차량 번호를 인식 할 수 있는 알고리즘을 본 논문에서 제안하였다.

• Journal of Game and Entertainment
• /
• v.2 no.2
• /
• pp.45-50
• /
• 2006

In a face detection system based on template matching, histogram equalization or log transform is applied to an input image for the intensity normalization and the image improvement. It is known that they are noneffective in improving an image with intensity distortion by illumination variation. In this paper, we propose an efficient image improvement method called as a bilateral symmetry average for images with intensity distortion by illumination variation. Experimental results show that our method delivers the detection performance better than previous methods and also remarkably reduces the number of face candidates.

• Korean Journal of Optics and Photonics
• /
• v.10 no.5
• /
• pp.379-385
• /
• 1999

The characteristics of image quality of a color CRT (cathode ray tube) monitor are studied by changing the contrast and brightness levels. The resolution is assessed by SQRI (square root integral) measured at 9 different combinations of the contrast and brightness levels. The chromaticity coordinates and luminances of red-green-blue channels as a function of the digital value are measured at these combinations and the relationships among the constant-channel chromaticity, color gamut, maximum luminance of a white point with the channel independence are analyzed. From the results, the optimized combination of levels is obtained.

• Proceedings of the KHMA Conference
• /
• 2000.10a
• /
• pp.1-22
• /
• 2000

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.11C
• /
• pp.1140-1151
• /
• 2003

This paper proposes a face recognition method based on modified Otsu's binarization and Hu moment. Proposed method is robust to brightness, contrast, scale, rotation, and translation changes. As the proposed modified Otsu's binarization computes other thresholds from conventional Otsu's binarization, namely we create two binary images, we can extract higher dimensional feature vector. Here the feature vector has properties of robustness to brightness and contrast changes because the proposed method is based on Otsu's binarization. And our face recognition system is robust to scale, rotation, and translation changes because of using Hu moment. In the perspective of brightness, contrast, scale, rotation, and translation changes, experimental results with Olivetti Research Laboratory (ORL) database and the AR database showed that average recognition rates of conventional well-known principal component analysis (PCA) are 93.2% and 81.4%, respectively. Meanwhile, the proposed method for the same databases has superior performance of the average recognition rates of 93.2% and 81.4%, respectively.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.489-492
• /
• 2005

In this paper, we present a system for robust face detection based on wavelet transform using the standard models of image distortion. In the previous works, it was known to be difficult to treat a distorting of image information such as noises and light of the images obtained by a still camera and a movie camera. we analyze the high frequence information by using wavelet transform. This information is used for testing the image distortion and constructing the standard models of image distortion. The experimental results show that our extracting method based on standard models of image distortion is very effective.

• Cartoon and Animation Studies
• /
• s.15
• /
• pp.73-88
• /
• 2009

Light is a basic force that functions in all the formative arts. Light (brightness) is an important subject of study in that it contains the force to control emotion and has much influence upon the shaping of a visual image and a feeling. If an artist systematizes the characteristics of brightness and creates an image, he or she can acquire a useful tool of expression. Because light is a powerful medium of expression of a visual image, a study on the characteristics of brightness for the emotional expression of an image in the contextual relationship with narratives seemingly has a crucial meaning. Emotion is influenced by a visual image very much, and a visual image is inevitably influenced by light. The brightness by light is basically classified into bright, dim, and dark. And the three basic stages of brightness specialize an image according to the setting of scope of maximal and minimal luminosity, and the image is further differentiated by the size of bright portion or dark portion. Since emotion is such a phenomenon as immaterial and psychological, it is difficult to break down it. Furthermore, clarifying the principle of an image in which the shade of light is associated is impossible. However, the width of luminosity and the change of size can give quite a change to a visual image, and the visual image has further influence upon man's emotion too. Although the influence of brightness upon a visual image varies with extents, circumstances, and personal tastes and interests, even the same image clearly changes with the adjustment of brightness.

• Journal of Broadcast Engineering
• /
• v.22 no.5
• /
• pp.608-617
• /
• 2017

Methods of contrast enhancement have problem such as side effect of over-enhancement with non-gaussian histogram distribution, tradeoff enhancement efficiency against brightness preserving. In order to enhance contrast at various histogram distribution, segmentation to region with gaussian distribution and then enhance contrast each region. First, we segment an image into several regions using GMM(Gaussian Mixture Model)fitting by that k-mean clustering and EM(Expectation-Maximization) in $L^*a^*b^*$ color space. As a result region segmentation, we get the region map and probability map. Then we apply local contrast enhancement algorithm that mean shift to minimum overlapping of each region and preserve brightness histogram equalization. Experiment result show that proposed region based contrast enhancement method compare to the conventional method as AMBE(AbsoluteMean Brightness Error) and AE(Average Entropy), brightness is maintained and represented detail information.

• The KIPS Transactions:PartB
• /
• v.16B no.4
• /
• pp.263-270
• /
• 2009

Histogram Equalization (HE) is a very popular technique for enhancing the contrast of an image. HE stretches the dynamic range of an image using the cumulative distribution function of a given input image, therefore improving its contrast. However, HE has a well-known problem : when HE is applied for the contrast enhancement, there is a significant change in brightness. To resolve this problem, we propose An Adaptive Contrast Enhancement Algorithm using Subhistogram Area-Ratioed Histogram Redistribution, a new method that helps reduce excessive contrast enhancement. This proposed algorithm redistributes the dynamic range of an input image using its mean luminance value and the ratio of sub-histogram area. Experimental results show that by this redistribution, the significant change in brightness is reduced effectively and the output image is able to preserve the naturalness of an original image even if it has a poor histogram distribution.