• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 제13회 신호처리 합동 학술대회 논문집
• /
• pp.901-904
• /
• 2000

A direct authentication from gray-scale image, instead of the conventional multi-step preprocessing, is proposed using Gabor filter-based features from the gray-scale fingerprint around core point. The core point is located as a reference point for the translation invariant matching. And its principal symmetry axis is detected for the rotation invariant matching from its neighboring region centered at the core point. And then fingerprint is divided into non-overlapping blocks with respect to the core point and features are directly extracted form the blocked gray level fingerprint using Gabor filter. The proposed fingerprint authentication is based on the Euclidean distance between the corresponding Gabor features of the input and the template fingerprints. Experiments are conducted on 300${\times}$300 fingerprints obtained from a CMOS sensor with 500 dpi resolution, and the proposed method could lower the False Reject Rate(FRR) to 18.2% under False Acceptance Rate(FAR) of 0%.

• 한국의류학회지
• /
• 제22권5호
• /
• pp.597-606
• /
• 1998

The purposes of the study were 1) to evaluate the visual image of colored Korean traditional dress for woman 2) to analyze the colors and, color combinations effect on the image perception using gestalt theory. The research method was a quasi-experimental with a between subjects design. The experimental materials developed for the study were a set of stimuli and a response scale. The stimuli was consisted of 17 drawings of females wearing Korean tradinational dress, by using CAD simulation. A response scale consisted of semantic differential scales. The subjects were 1138 undergraduate students of Taejon city, Chungnam province and Chungbuk province. Their responses to the semantic differential scales were analyzed using factor analysis, one-way ANOVA, Duncan's multiple range test, 1-test. Results were as follows; 1) The image of the stimulus was consisted of the 4 different dimensions.(sociability, evaluation, visibility, attractiveness) 2) Clothing colors had significant effects on image perception of the evaluation dimension, visibility dimension and attractiveness dimension in the mono-color set. The blue showed the most positive image on the evaluation dimension, and the yellow and the gray showed negative image on the same dimension. The yellow showed the most salient image and the gray showed the least salient image on the visibility dimension. The red showed the most attractive image and the green showed the least attractive image on the attractiveness dimension. 3) In hi-color set stimulus, the perceived image was influenced by color combinations. The yellow blouse-the red skirt set showed the most sociable image on the sociability dimension. The blue blouse-the green skirt set showed the most positive image on the evaluation dimension. The yellow blouse-the red skirt set showed the most salient image and the blue blouse-the green skirt set showed the least salient image on the visibility dimension. And the red blouse-the yellow skirt set showed the most attractive image on the attractiveness dimension. On conclusion the visual image of Korean traditional dress wearer was affected by dress colors and color combinations.

• 한국지능시스템학회논문지
• /
• 제11권7호
• /
• pp.569-573
• /
• 2001

An approximate representation of discrete functions {f$_{i,j}\mid$｜i, j=-1, 0, 1, …, N+1}in two variables by a fuzzy system is described. We use the cubic B-splines as fuzzy sets for the input fuzzification and spike functions as the output fuzzy sets. The ordinal number of f$_{i,j}$ in the sorted list is taken to be the out put fuzzy set number in the (i, j) th entry of the fuzzy rule table. We show that the fuzzy system is an exact representation of the cubic spline function s(x, y)=$\sum_{N+1}^{{i,j}=-1}f_{i,j}B_i(x)B_j(y)$ and that the approximation error S(x, y)-f(x, y) is surprisingly O($h^2$) when f(x, y) is three times continuously differentiable. We prove that when f(x, y) is a gray scale image, then the fuzzy system is a smoothed representation of the image and the original image can be recovered exactly from its fuzzy system representation when it is a digitized image.e.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.1811-1814
• /
• 2002

In this paper, we propose an improved contrast control method f9r image improvement of multi-gray scale image. The proposed contrast control method can improve contrast of image by changing gradient of weight as the type of input image. In addition, the proposed method does not require field and frame memory for large amount of computed data. And, the proposed method can be easily applied to the FPD fur real-time processing because of its less hardware complexity than that of the conventional methods. Also it can flexibly control the contrast of input gray level by varying the weight values that control the contrast range. The operation and performance of the proposed controller have been verified using computer simulation.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2003년도 춘계학술발표논문집 (상)
• /
• pp.631-634
• /
• 2003

오늘날 CT나 MR등을 통한 의학 영상 기술과 컴퓨터 성능의 향상으로 인체 내부 장기의 영상을 비교적 용이하게 얻을 수 있으며 얻어진 영상 정보는 컴퓨터로 수치화 되므로 데이터의 조작 및 가공이 용이하다. 그러나, 이렇게 얻어진 의학 영상들은 보통 2 차원적 슬라이스 image 형태로 얻어진다. 일반적으로 슬라이스 사이의 간격은 조사량 등 여러 문제 때문에, 항상 동일한 간격을 유지하고 있지 않은 경우가 많으며 슬라이스 사이 간격이 슬라이스 내의 픽셀 간격보다 큰 경우가 대부분이다. 이러한 image로부터 3 차원적 디스플레이나, 조작, 분석을 하기 위해서는 같은 간격의 image를 얻어야 한다. 이러한 이유로 인하여 보간(Interpolation) 기법이 의학 영상 분야에서 많이 사용된다. 본 논문은 형태-기반 보간 방법을 gray-scale image 에 적용이 가능하도록 확장한 그레이 수준 형태 기반 보간 알고리즘을 구현하였다. 그리하여, 본 논문이 제안한 알고리즘을 슬라이스 간격이 큰 2차원 복부 CT 영상에 적용시켜 다른 보간 법들보다 향상된 결과를 확인할 수 있었다.

• 한국정보통신학회논문지
• /
• 제8권3호
• /
• pp.708-713
• /
• 2004

그레이 스케일 이미지를 이용한 차량 감지 방법은 주차장에서 빈 공간으로 진입하는 차량의 안내나 기타 유사한 목적들을 위해 제안되고 있다. 본 논문은 그레이레벨 이미지를 이용하여 주차여부를 확인하고, 주차공간을 분석하는 방법을 제안한다. 실험결과로써 각기 2일 동안 새벽부터 해질녘까지 야외 주차장을 이용하여 획득한 129개의 영상을 이용하여 실험한 결과 98.7％의 성공률을 나타내었다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권6호
• /
• pp.792-798
• /
• 2004

본 논문에서는 웨이퍼 영상에서 다이 위치를 인식하기 위한 새로운 코너점 검출 방법을 제안한다. 웨이퍼 다이 위치 인식은 WSCSP(Wafer Scale Chip Scale Packaging)기술에 필수적인 과정으로서 웨이퍼 윗면의 다이 패턴을 얼마나 정확히 인식하느냐에 따라서 후 공정의 정확도가 결정된다. 본 논문에서는 정확한 다이 위치를 인식하기 위하여 계층적 명암 영상 코너 검출 방법을 제안한다. 새로운 코너 검출자는 코너 영역을 마스크 크기에 따라서 동심원으로 나누어 각각의 동심원에서의 코너성과 방향성을 구하여 정확한 코너점을 검출하도록 하였다. 또한 계층적 구조를 가지고 처리하여 기존의 명암 영상코너 검출자 보다 더 빠른 처리 속도를 얻을 수 있도록 하였다.

• Journal of Information Display
• /
• 제2권2호
• /
• pp.13-21
• /
• 2001

We propose a universal image processor for a-Si TFT LCD of UXGA class that can display the full screen on the LCD panel with low resolution of video sources such as NTSC, VGA, SVGA, XGA, and SXGA by using the proposed interpolation filter. In addition, we propose a real-time contrast controller for image improvement of multi-gray scale image. The operation of the proposed methods has been verified using Synopsys VHDL and computer simulation. Results show that the proposed methods might be suitable for a UXGA LCD controller for real-time image improvement.

• 전자공학회논문지
• /
• 제51권9호
• /
• pp.75-81
• /
• 2014

적분영상은 입력영상의 픽셀 값을 기준좌표부터 순차적으로 누적하여 만든 영상으로, Haar-like features와 같은 네모난 박스 모양의 필터 연산을 효율적으로 처리하기 위하여 사용된다. 그러나 적분영상은 입력영상보다 3배 이상 많은 메모리를 소모하기 때문에, 메모리 자원이 제한적인 하드웨어 설계 환경에서는 사용이 어렵다. 본 논문에서는 효율적인 메모리 사용을 위한 적분영상 하드웨어 설계 방법을 제안한다. 해당 방법은 적분영상 이외에 세로적분영상과 가로적분영상을 생성하고, 입력영상을 재사용 하는 방법을 사용한다. 그리고 박스 필터의 크기에 따라 modulo 연산을 적용하여 적분영상의 데이터 크기를 줄이는 방법을 함께 적용하였다. 적분 영상 데이터를 읽기 위해 나누어진 영상 데이터를 다시 덧셈해야하는 연산 오버헤드가 발생하지만, 4개의 데이터를 단순히 더하는 연산이므로 병렬처리가 가능한 하드웨어 환경에서는 큰 영향을 미치지 않는다. Xilinx사의 Virtex5-LX330T를 대상으로 실험한 결과 $640{\times}480$ 크기의 8bit gray-scale 입력영상에서 최대 $32{\times}32$ 크기의 필터사용을 기준으로 50%의 적분영상 메모리를 감소시킬 수 있다.

• Journal of Information Processing Systems
• /
• 제16권6호
• /
• pp.1424-1436
• /
• 2020

Although huge progress has been made in current image segmentation work, there are still no efficient segmentation strategies for tree image which is taken from natural environment and contains complex background. To improve those problems, we propose a method for tree image segmentation combining adaptive mean shifting with image abstraction. Our approach perform better than others because it focuses mainly on the background of image and characteristics of the tree itself. First, we abstract the original tree image using bilateral filtering and image pyramid from multiple perspectives, which can reduce the influence of the background and tree canopy gaps on clustering. Spatial location and gray scale features are obtained by step detection and the insertion rule method, respectively. Bandwidths calculated by spatial location and gray scale features are then used to determine the size of the Gaussian kernel function and in the mean shift clustering. Furthermore, the flood fill method is employed to fill the results of clustering and highlight the region of interest. To prove the effectiveness of tree image abstractions on image clustering, we compared different abstraction levels and achieved the optimal clustering results. For our algorithm, the average segmentation accuracy (SA), over-segmentation rate (OR), and under-segmentation rate (UR) of the crown are 91.21%, 3.54%, and 9.85%, respectively. The average values of the trunk are 92.78%, 8.16%, and 7.93%, respectively. Comparing the results of our method experimentally with other popular tree image segmentation methods, our segmentation method get rid of human interaction and shows higher SA. Meanwhile, this work shows a promising application prospect on visual reconstruction and factors measurement of tree.