• Proceedings of the KAIS Fall Conference
• /
• 2011.05a
• /
• pp.247-250
• /
• 2011

컴퓨터의 대중화와 각종 디지털 기기의 보급 및 네트워크의 발달로 거의 모든 정보가 디지털화되어 처리 및 저장되고 있는 추세이다. 하지만 이러한 편리한 측면에도 불구하고 개인 신상 정보 유출 및 피싱, 해킹 등으로 인해 아이디/비밀번호와 같은 기존 방식으로는 강화되고 있는 보안에 대한 요구를 충족시킬 수 없는 것이 현실이다. 홍채 인식은 최근들어 출입통제, 정보보안 등의 분야에 많이 활용되고 있다. 홍채 특징 추출 시 크기, 조명, 회전에 무관한 홍채 특징을 추출하는 것이 바람직하다. 홍채크기 및 조명 문제는 전처리를 통해 쉽게 해결할 수 있지만 회전에 무관한 홍채 특징 추출은 여전히 문제가 된다. 본 논문에서는 회전 보정으로 인한 인식률 및 속도 저하를 개선하기 위해 Zernike 모멘트를 통한 홍채특징 추출방법을 제안하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.838-840
• /
• 2005

얼굴인식 기술은 타 생체 인식 기술에 비해 경제성과 사용자 편리성이 높은 이유로 최근 몇 년간 영상 이해 분야의 가장 성공적인 응용의 하나로 주목받고 있다. 그러나 얼굴인식은 타 생체인식에 비해 정확도가 떨어지는 문제가 있으며 이것은 배경, 조명 또는 포즈등과 같은 요인으로 인해 얼굴인식을 위한 전처리 작업인 얼굴영역 검출이 어렵기 때문이다. 본 논문에서는 얼굴영역 검출을 하기 위해서 나타나는 문제점들인 배경, 조명등의 환경적인 요인을 8x8 블록영상과 블록들의 연결성을 이용하여 제거한 후 얼굴만을 검출한다. 제안된 알고리즘은 복잡한 배경 및 원거리에서 촬영된 입력영상에서도 매우 안정적으로 적용됨을 실험을 통해 확인하였다.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.310-311
• /
• 2007

다중패턴 홀로그램을 위한 자동 검사 시스템을 제안한다. 시스템 하드웨어는 조명계, 카메라 그리고 영상처리부로 구성된다. UV LED를 사용하는 다양한 조명은 다른 위치에 놓여 각 위치에서의 이미지 패턴을 획득한다. 시스템 소프트웨어는 전처리, 패턴 생성, 패턴매칭으로 구성된다. 획득한 입력 홀로그램 영상은 패턴매칭 알고리즘에 의해 표준 패턴과 비교한다. 입력 홀로그램의 위치 오차 보정을 위해, 다른 위치에서의 홀로그램 표준 패턴은 온라인상에서 생성되어야만 한다. 본 논문은 표준 패턴의 생성을 위해 CGH(Computer Generated Hologram)방법에 근거한 주파수 변환을 적용한다. 한국지폐의 홀로그램을 위한 실험 결과는 제안한 시스템의 유용성을 증명한다.

• 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.

• Journal of KIISE
• /
• v.44 no.3
• /
• pp.295-305
• /
• 2017

Facial appearance is greatly influenced by illumination conditions, and therefore illumination variation is one of the factors that degrades performance of face recognition systems. In this paper, we propose a robust method for face representation under varying illumination conditions, combining non-alpha Weberface (non-alpha WF) and histogram equalization. We propose a two-step method: (1) for a given face image, non-alpha WF, which is not applied a parameter for adjusting the intensity difference between neighboring pixels in WF, is computed; (2) histogram equalization is performed to non-alpha WF, to make a uniform histogram distribution globally and to enhance the contrast. $(2D)^2PCA$ is applied to extract low-dimensional discriminating features from the preprocessed face image. Experimental results on the extended Yale B face database and the CMU PIE face database show that the proposed method yielded better recognition rates than several illumination processing methods as well as the conventional WF, achieving average recognition rates of 93.31% and 97.25%, respectively.

• The Journal of the Korea Contents Association
• /
• v.12 no.1
• /
• pp.1-8
• /
• 2012

In this paper, a method of determining the optimal threshold in image binarization for the marker recognition is suggested to resolve the problem that the performances of marker recognition are quite different according to the changes of indoor lighting. The suggested method determines the optimal threshold by considering the average brightness, the standard deviation and the maximum deviation of video image under the various indoor lighting circumstances, such as bright light, dim light, and shadow by unspecified obstacles. In particular, the recognition under the gradation lighting by shadow is improved by applying the weighted value that depends on the brightness of image. The suggested method is experimented to process $720{\times}480$ resolution video images under the various lighting environments, and it shows the fast and high performance, which is suitable for mobile indoor navigation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.821-829
• /
• 2004

A face recognition has been used for verifying and authorizing valid users, but its applications have been restricted according to lighting conditions. In order to minimizing the restricted conditions, this paper proposes a new algorithm of detecting the face from the input image obtained under the irregular lighting condition. First, the proposed algorithm extracts an edge difference image from the input image where a skin color and a face contour are disappeared due to the background color or the lighting direction. In the next step, it extracts a face region using the histogram of the edge difference image and the intensity information. Using the intensity information, the face region is divided into the horizontal regions with feasible facial features. The each of horizontal regions is classified as three groups with the facial features(including eye, nose, and mouth) and the facial features are extracted using empirical properties of the facial features. Only when the facial features satisfy their topological rules, the face region is considered as a face. It has been proved by the experiments that the proposed algorithm can detect faces even when the large portion of face contour is lost due to the inadequate lighting condition or the image background color is similar to the skin color.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.5
• /
• pp.99-106
• /
• 2006

In this paper, implementation of active mufflers using multiple channel adaptive IIR filter is presented. Usually, recursive LMS(RLMS) algorithms for adaptive IIR filters are highly efficient than filtered-X LMS(FXLMS) algorithms, when the order of both algorithms are the same. However, RLMS algorithms usually diverge before the algorithms arenot yet converged. So, the prefilters are presented to improve the stability by pulling the poles of feedback control transfer function in the beginning of active noise control and returning the original poles after the filters converge. The engine noises of diesel engine automobiles and gasoline engine automobiles are analyzed and the mathematical model of an active muffler is derived. Computer simulations and experiments are performed to show the effectiveness of the proposed systems.

• Journal of Broadcast Engineering
• /
• v.11 no.1 s.30
• /
• pp.91-99
• /
• 2006

Pre-processing is one of image processing techniques to enhance image quality or appropriately convert a given image into another form for a specific purpose. An 8 bit depth map obtained by a depth camera usually contains a lot of noisy components caused by the characteristics of depth camera and edges are also more distorted by the quality of a source object and illumination condition comparing with edges in RGB texture image. To reduce this distortion, we use noise removing filters, but they are only able to reduce noise components, so that distorted edges of depth map can not be properly recovered. In this paper, we propose an algorithm that can reduce noise components and also enhance the quality of edges of depth map by using edges in RGB texture. Consequently, we can reduce errors in multi-view stereo image synthesis process.

• Journal of KIISE:Software and Applications
• /
• v.30 no.7_8
• /
• pp.773-779
• /
• 2003

Locating exact position of facial components is a key preprocessing for realizing highly accurate and reliable face recognition schemes. In this paper, we propose a simple but powerful method for detecting isolated facial components such as eyebrows, eyes, and a mouth, which are horizontally oriented and have relatively dark gray levels. The method is based on the shape-resolving locally optimum thresholding that may guarantee isolated detection of each component. We show that pure facial regions can be determined by grouping facial features satisfying simple geometric constraints on unique facial structure. In the test for over 1000 images in the AR -face database, pure facial regions were detected correctly for each face image without wearing glasses. Very few errors occurred in the face images wearing glasses with a thick frame because of the occluded eyebrow -pairs. The proposed scheme may be best suited for the later stage of classification using either the mappings or a template matching, because of its capability of handling rotational and translational variations.