• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.338-340
• /
• 2000

자동차 번호판 인식 시스템은 영상획득, 번호판 영역 추출, 추출된 번호판 영역의 전처리, 문자부분 영역화, 문자인식 등의 5가지 핵심부분으로 구성된다. 그 중에서도 번호판 영역 추출, 추출된 영역의 전처리, 문자부분 영역화의 정확성은 전체 시스템 인식률에 지대한 영향을 줄 수 있는 부분으로써 그 정확성이 요구된다. 이에 본 논문에서는 컴퓨터 비젼 분야 중의 하나인 영상처리 기법을 사용하여 명암의 변화에도 문자를 잘 추출할 수 있는 Dynamic Adaptive Threshold 방법을 사용하여 추출된 번호판 영역을 이진화하고, 정확하게 문자 부분을 영역화하기 위한 방법으로 누적분포와 번호판 문자배열 특성을 이용한 방법을 제안한다. 그리고 추출되어진 문자는 ART2 신경망을 이용하여 인식한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.7
• /
• pp.1551-1556
• /
• 2010

In this paper, we propose a new inspection method that applies fuzzy reasoning method considering the difference of brightness and intensity of illumination by bend together. In the preprocessing phase, we compensate the degree of semiconductor images with bilinear interpolation and moment-rotation. Then we use fuzzy reasoning method with the difference of brightness from error region by pattern matching and the difference of intensity of illumination from bends. Then the result is difuzzified and applied to the final inspection process. In experiment which uses 30 real world semiconductors with strait shots and side shots, the proposed method successfully discard the false positive identified by conventional brightness comparison only method without any loss of misidentification.

• 보존과학연구
• /
• s.23
• /
• pp.59-75
• /
• 2002

In this study human bones and teeth, excavated from the Myeongam-risite in Asan, Chungcheongnam-do Province, have been analysed by nuclear DNA typing and mitochondrial DNA sequencing methods. Twenty-one samples of long bones and twenty-seven samples of teeth from twenty-one individuals were collected and analysed. Among these thirteenteeth were successfully subjected to nuclear DNA extraction, quantification, and PCR(Polymerase Chain Reaction) amplification. Silver STR III (D16S539, D7S820, D13S317) multiplex PCR method was used in this study for a short tandem repeat (STR) analysis. Mitochondrial DNAs of tooth samples were also amplified and sequenced by a DNA sequencer. These analyses show that a sample from Burial no. 29 and one from Burial no. 38(right) possessed the same maternal inheritance. This may suggest that the Myeongam-ri cemetery was used by a kin group for a relatively long period of time.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.911-921
• /
• 2004

Accurate minutiae extraction from input fingerprint images is one of the critical modules in robust automatic fingerprint identification system. However, the performance of a minutiae extraction is heavily dependent on the quality of the input fingerprint images. If the preprocessing is performed according to the fingerprint image characteristics in the image enhancement step, the system performance will be more robust. In this paper, we propose a knowledge-based preprocessing method, which extracts S features (the mean and variance of gray values, block directional difference, orientation change level, and ridge-valley thickness ratio) from the fingerprint images and analyzes image quality with Ward's clustering algorithm, and enhances the images with respect to oily/neutral/dry characteristics. Experimental results using NIST DB 4 and Inha University DB show that clustering algorithm distinguishes the image Quality characteristics well. In addition, the performance of the proposed method is assessed using quality index and block directional difference. The results indicate that the proposed method improves both the quality index and block directional difference.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.667-673
• /
• 2009

This paper presents an efficient facial expression recognition method by measuring the histogram distance based on preprocessing. The preprocessing that uses both centroid shift and histogram equalization is applied to improve the recognition performance, The distance measurement is also applied to estimate the similarity between the facial expressions. The centroid shift based on the first moment balance technique is applied not only to obtain the robust recognition with respect to position or size variations but also to reduce the distance measurement load by excluding the background in the recognition. Histogram equalization is used for robustly recognizing the poor contrast of the images due to light intensity. The proposed method has been applied for recognizing 72 facial expression images(4 persons * 18 scenes) of 320*243 pixels. Three distances such as city-block, Euclidean, and ordinal are used as a similarity measure between histograms. The experimental results show that the proposed method has superior recognition performances compared with the method without preprocessing. The ordinal distance shows superior recognition performances over city-block and Euclidean distances, respectively.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.419-421
• /
• 1999

본 논문은 자궁경부암 검사를 위한 전처리 과정인 자궁경부암 세포 영상분할 문제 연구의 결과이다. 자궁경부암 세포 영상은 배경과 세포질 및 세포핵의 구별이 어렵다. 게다가 자궁경부암 검사 시스템은 짧은 시간동안 많은 영상을 처리해야 하기 때문에, 영상의 분석 속도가 빠르고 강력한 영상 분할 기법이 필요하다. 이를 위하여 우리는 thresholding 기법을 연구하였다. 먼저 세포 영상의 각 화소의 명암의 분포를 조사하여 히스토그램을 구하였다. 히스토그램은 0~255 사이에 존재하게 되는데, 0~255의 전 영역에 존재하기 보다는 그 중 일부분에만 존재한다. 우리는 히스토그램이 존재하는 영역을 백분율로 나누고 세포핵 및 세포질이 존재하는 영역의 분포를 구하여 global threshold를 찾았고, 이를 기준으로 각 점을 thresholding 할 때에 주위의 평균값을 보정값으로 두어 local thresholding을 수행하였다. 결과 영상은 핵의 영역을 탐색하기 위한 seed로 사용하기에 적합하다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.466-468
• /
• 2001

의료 영상 처리 기술은 질병의 진단 및 치료를 위한 계획이나 방법을 결정하는데 있어 매우 중요한 역할을 하고 있으며 의료 영상 시스템과 같은 활용 분야에서는 질병이 있는 환자의 자동 진단을 위한 연구도 활발하게 이루어지고 있다. 여기서는 뇌 MR영상에서의 질병을 자동 진단할 수 있는 방법에 관한 연구를 한다. 뇌 MR영상에서의 질병 진단을 위한 단계로서 필수적으로 이루어져야 하는 단계가 비정상 영역의 추출 단계이다. 이 논문에서는 뇌의 질병 진단에 사용할 수 있는 자료를 제공하기 위한 전처리 단계로서 질병이 있는 환자의 뇌 영상에서 비정상적인 영역 추출 방법을 제안한다. 일반적으로 비정상적인 영역의 명암간 분포는 회백질 영역의 분포와 유사하나 두께 차이로서 구분이 가능하다. 여기서는 이 정보를 활용하여 정상인의 뇌영상에 대해서 회백질의 평균 두께 분포를 구하여 테스트로 입력되어지는 영상에서 회백질의 평균 두께 이상의 영역만을 남김으로서 질병이 있는 환자의 뇌 영상에서 비정상적인 영역을 추출할 수 있음을 보인다. 또한 추출되어진 비정상 영역에 대해서 진단에 필요한 인자를 자동으로 측정하였고 뇌경색, 뇌종양 환자를 포함한 63명의 뇌 MR 영상 시리즈에 대해서 실험하여 비교적 정확한 추출결과를 유도할 수 있었음을 확인하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.3
• /
• pp.616-621
• /
• 2005

In this paper. digital watermarking algorithm based on human visual system and transform domain is presented. Firstly, original image is separated into RGB thannels, watermark is embedded into the coefficients of DCT so as to consider a contrast sensitivity and texture degrees. In preprocessing, DCT domain based transform is involved and binary image of visually recognizable patterns is utilized as a watermark. Consequently, experimental results showed that proposed algorithm is robust and imperceptibility such destruction attack as JPEG compression.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.113-117
• /
• 2003

In this paper, have necessity of PACS (Picture Archiving and Communication System) at hospital but hereafter by economical problem PACS apply this to medical treatment image enhancing image quality applying histogram equalization for improvement of light and darkness after reconstruct because make image that pretreatment filtering has wild picture and is processed in wave lets dissolution and wave lets area using weight median filter because could not buy expensive equipment at hospital which introduction is difficulty do inversion and extracted characteristic.

• Journal of Digital Contents Society
• /
• v.5 no.4
• /
• pp.311-315
• /
• 2004

In this paper, we proposed a robust watermarking algorithm based on fuzzy inference and human visual system. In the first, discrete wavelet transform(DWT) is involved to calculate additive energy strength, then we devised fuzzy inference, which was established by computing contrast and texture degree in gray-level image. Watermark is embeded into the coefficients of 3-level DWT so as to consider a spatial effects. Visual recognizable patterns such as binary image were used as a watermark Consequently, experimental results showed that proposed algorithm is robust in JPEC compression.