적응 퍼지 시스템을 이용한 칼라패턴 감성 평가 모델에 관한 연구

엄경배 한국지능시스템학회 1999 한국지능시스템학회논문지 Vol.9 No.5

In the paper. we propose an evaluation model based the adaptive fuzzy systems, which can transform the physical features of a color pattern to the emotional features. The model is motivated by the Soen's psychological experiments, in which he found the physical features such as average hue, saturation, intensity and the dynamic components of the color patterns affects to the emotional features represented by a pair of adjective words having the opposite meanings. Our proposed model consists of two adaptive fuzzy rule-bases and the y-model, a l i r ~ r ys et operator, to fuze the evaluation values produced by them. The model shows con~parablep erformances to the neural network for the approximation of the nonlinear transforms, and it has the advantage to obtain the linbwistic interpretation from the trained results. We believe the evaluated results of a color pattern can be used to the emotion-based color image retrievals.

퍼지 클러스터 필터와 가중화 된 벡터 $\alpha$-trimmed 평균 필터를 이용한 칼라 영상처리

엄경배,이준환 한국통신학회 1999 한국통신학회논문지 Vol.24 No.9

Color images are often corrupted by the noise due to noisy sensors or channel transmission errors. Some filters such as vector media and vector $\alpha$-trimmed mean filter have bee used for color noise removal. In this paper, We propose the fuzzy cluster filters based on the possibilistic c-means clustering, because the possibilistic c-means clustering can get robust memberships in noisy environments. Also, we propose weighted vector $\alpha$-trimmed mean filter to improve the conventional vector $\alpha$-trimmed mean filter. In this filter, the central data are more weighted than the outlying data. In this paper, we implemented the color noise generator to evaluate the performance of the proposed filters in the color noise environments. The NCD measure and visual measure by human observer are used for evaluation the performance of the proposed filters. In the experiment, proposed fuzzy cluster filters in the sense of NCD measure gave the best performance over conventional filters in the mixed noise. Simulation results showed that proposed weighted vector $\alpha$-trimmed mean filters better than the conventional vector $\alpha$-trimmed mean filter in any kinds of noise.

Interactive emotion-based color image retrieval

엄경배,박중수,Eum Kyoung-Bae,Park Joong-Soo Korea Computer Institute Society 2006 컴퓨터産業敎育學會論文誌 Vol.7 No.1

Variable contents are extracted and used to improve the correctness of the retrieval in the content-based in age retrieval. This way use the physical feature for the retrieval. In this way of retrieval, the user has to know the basic physical features and spatial relationship of target images that he wants to retrieve. There are some restriction to reflect the user's intend. We need the retrieval system that reflect the user's intend. In this paper, we propose an emotion-based retrieval system. It is different from past emotion based image retrieval in point of view that it uses relevance feedback to estimate the users intend and it is easily combined with past content-based image retrieval system. The features and similarity measures are adopted from MPEG-7 color descriptors which are proper retrieval of large multimedia databases. We use wallpaper images for the experiment. The result shows that the system get successful result.

신경망을 이용한 칼라 입력장치의 칼라 보정

엄경배,안창선 한국정보교육학회 1999 정보교육학회논문지 Vol.3 No.1

형태학적 형태 분해 방법을 이용한 물체 인식에 관한 연구

嚴景培,金準哲,李俊煥 全北大學校 1994 論文集 Vol.37 No.-

Mathematical morphology based on the set theory has been applied to various areas in image processing. In this paper, we propose a new method for object recognition based on morphological shape decomposition. The first step of our method decomposes a binary shape into a union of simple binary shapes, and then a new tree structure is constructed which can represent simple binary shapes of objects. Finally, we obtain the feature informations from the tree structures and calculate matching scores using efficient matching measure. The experimental results of the proposed method show the good recognition rate.

감성 형용사의 모형에 관한 연구

엄경배,최득수,Eum, Kyoung-Bae,Choi, Deuk-Soo 한국컴퓨터산업학회 2007 컴퓨터産業敎育學會論文誌 Vol.8 No.2

In this reaearch, our goal is to find the representative adjectives which express the sensitivity for wall paper. We want to make a model which can explain the whole by using the representative adjectives. We got the adjectives through the questionnaire survey, field survey, and internet survey. To find the representative adjectives, we used modified factor analysis. The factor analysis used in preceding research can not control the individual difference of sensitivity, because the distribution information of data is concentrated into the mean. So, we used the modified factor analysis to control it. The experimental result showed that the reduced factors could account about 79.5% when the number of factor are three. The individual difference of sensitivity was reflected in some adjectives. This result can be used to make a recommending model for wallpaper.

Possibilistic C-mean 클러스터링과 영역 확장을 이용한 칼라 영상 분할

엄경배,이준환 대한전자공학회 1997 전자공학회논문지SC (System and control) Vol.s34 No.3

Image segmentation is teh important step in image infromation extraction for computer vison sytems. Fuzzy clustering methods have been used extensively in color image segmentation. Most analytic fuzzy clustering approaches are derived from the fuzzy c-means (FCM) algorithm. The FCM algorithm uses th eprobabilistic constraint that the memberships of a data point across classes sum to 1. However, the memberships resulting from the FCM do not always correspond to the intuitive concept of degree of belongingor compatibility. moreover, the FCM algorithm has considerable trouble above under noisy environments in the feature space. Recently, the possibilistic C-mean (PCM) for solving growing for color image segmentation. In the PCM, the membersip values may be interpreted as degrees of possibility of the data points belonging to the classes. So, the problems in the FCM can be solved by the PCM. The clustering results by just PCM are not smoothly bounded, and they often have holes. So, the region growing was used as a postprocessing. In our experiments, we illustrated that the proposed method is reasonable than the FCM in noisy enviironments.

마이크로 컴퓨터와 BD 컴퓨터들간의 컴퓨터네트웍 구현 및 BD 컴퓨터의 설계

엄경배,전병실 전북대학교 공업기술연구소 1986 工學硏究 Vol.17 No.-

The binary decision method can evaluate any switching function in a number of decision steps and decision steps are reduced greatfully by BD comiler. Therefore, a scan time of the BD computer is faster than any other conventional PC using boolean method. However, in this paper computer network system between BD computers and microcomputer is disigned and sftware for data transport is considered.

Sparse-Neighbor 영상 표현 학습에 의한 초해상도

엄경배,최영희,이종찬,Eum, Kyoung-Bae,Choi, Young-Hee,Lee, Jong-Chan 한국정보통신학회 2014 한국정보통신학회논문지 Vol.18 No.12

Among the Example based Super Resolution(SR) techniques, Neighbor embedding(NE) has been inspired by manifold learning method, particularly locally linear embedding. However, the poor generalization of NE decreases the performance of such algorithm. The sizes of local training sets are always too small to improve the performance of NE. We propose the Learning Sparse-Neighbor Image Representation baesd on SVR having an excellent generalization ability to solve this problem. Given a low resolution image, we first use bicubic interpolation to synthesize its high resolution version. We extract the patches from this synthesized image and determine whether each patch corresponds to regions with high or low spatial frequencies. After the weight of each patch is obtained by our method, we used to learn separate SVR models. Finally, we update the pixel values using the previously learned SVRs. Through experimental results, we quantitatively and qualitatively confirm the improved results of the proposed algorithm when comparing with conventional interpolation methods and NE.

Effective face detection and robust face tracking using hybrid filter

엄경배 한국화상학회 2012 한국화상학회지 Vol.18 No.2

In this paper, I present my face detection and tracking method. First, image enhancement is carried out in HSV space especially if the input image is acquired from unconstrained illumination condition. I used a method for image enhancement in HSV space based on the local processing of image. I propose a lighting invariant face detection system based upon the edge and skin tone information of the input color image. The advantage of the proposed face detection is that, it can detect faces with different size, pose, and expression under unconstrained illumination conditions. I combined the Kalman filter with Camshift to enable track recovery after occlusions and to avoid the tracking failures caused by objects and background with similar colors to face. In my tracking method, I particularly focus on face tracking. The size and position of window are obtained after Camshift iteration. Kalman filtering is used to predict the next starting iterative point of Camshift. The experimental results show that my tracking method get the better results than Camshift in occlusion sequences and dynamic backgrounds.