• Journal of Oral Medicine and Pain
• /
• v.35 no.4
• /
• pp.237-243
• /
• 2010

Acanthosis nigricans usually has the characteristics that involve the development of darker pigmented patches and thickened skin with velvety texture on the body folds, and papillomatosis on lip and intraoral regions including tongue, gingiva, mucosa, palate. Malignant acanthosis nigricans, a type of acanthosis nigricans, occurs most commonly in association with underlying malignancy and characterically appears with three characteristic mucocutaneous lesion : especially of the lips and eyelids, hyperkeratosis of the palms and soles, the sign of Leser-Trelat. In the present report, the patient had typical clinical and histological findings of oral acanthosis nigricans, as well as past medical history associated with malignant gastric adenocarcinoma.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.6
• /
• pp.464-468
• /
• 2009

In this paper we propose an image-based approach, which is different from the traditional flow cytometric method to detect shape of apoptosis cells. This method can overcome the defects of cytometry and give precise recognition of apoptosis cells. In this work K-means clustering was used to do the rough segmentation and an active contour model, called 'snake' was used to do the precise edge detection. And then some features were extracted including physical feature, shape descriptor and texture features of the apoptosis cells. Finally a Mahalanobis distance classifier classifies the segmentation images as apoptosis and non-apoptosis cell.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.39 no.1
• /
• pp.37-45
• /
• 2002

This paper proposes new features for recognizing telltale bulb in a cluster. A typical feature employed in model-based pattern recognition is polygonal approximation points of object. But recognition using these dominant points has many mismatching counts in small model such as telltale bulb. To reduce mismatching counts, proposed features are the circle distribution of object pixel and the ratio of distance from center to boundary in object. This Paper also proposes new decision function using three features. In simulation result, we make a comparison mismatching counts between recognition using dominant points and the new recognition algorithm using three features.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.548-550
• /
• 2005

본 논문에서는 지문 인식을 하는데 있어서 특징점의 정보를 이용하여 지문을 정합하는 방법을 제안 하였다. 지문에는 중심점(core point), 삼각주(delta point), 분기점(bifurcation), 단점(ending point)들이 있는데, 본 논문에서는 먼저 poincare index를 이용하여 중심점을 검출한다. 검출된 중심점을 중심으로 하여 관심영역(ROI : region of interest)을 결정하여 영역내의 특징점들을 검출하여, 각 각 특징별로 분류한 다음 중심점과 특징점들과의 관계를 계산하여 지문 정합에 이용한다. 입력 받은 지문은 개개인 각각 양손 모두 10개의 손가락에서 센서의 누르기 압력을 다르게 하여 2번 입력 받아 사용하였다. 실험 결과 기존의 특징점 기반 알고리즘 보다 더 적은 영역에서 좀 더 정확하고 신뢰할 수 있는 지문 정합을 보여줌을 확인 하였다.

• Proceedings of the KIPE Conference
• /
• 2005.07a
• /
• pp.601-604
• /
• 2005

본 논문에서는 전방향 등극기하를 이용하여 이동로봇의 효과적인 표식대응에 대하여 기술한다. 전방향 영상에서 등극점과 등극선의 특성에 따라 추출된 특징의 영상내 위치를 추정한다. 예측된 특징의 영상위치정보를 통해 효과적인 특징 대응을 하며 본 연구에서는 두영상에서 8개의 대응점을 이용하여 기초행렬 F를 구하고 이것으로 특징의 공간정보를 계산한다. 따라서 기초행렬 F에서 계산된 기초행렬 E로부터 로봇은 자신의 위치와 운동정보(회전, 병진운동)를 알 수 있다. 또한 효과적인 특징대응을 위해 탐색범위를 축소함으로써 계산시간의 단축과 강인한 특징대응을 제시하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.57-66
• /
• 2011

In this paper, it is proposed for algorithm to detect human efficiently using a edge symmetry and gradient directional characteristics in realtime by the feature extraction in a single input image. Proposed algorithm is composed of three stages, preprocessing, region partition of human candidates, verification of candidate regions. Here, preprocessing stage is strong the image regardless of the intensity and brightness of surrounding environment, also detects a contour with characteristics of human as considering the shape features size and the condition of human for characteristic of human. And stage for region partition of human candidates has separated the region with edge symmetry for human and size in the detected contour, also divided 1st candidates region with applying the adaboost algorithm. Finally, the candidate region verification stage makes excellent the performance for the false detection by verifying the candidate region using feature vector of a gradient for divided local area and classifier. The results of the simulations, which is applying the proposed algorithm, the processing speed of the proposed algorithms is improved approximately 1.7 times, also, the FNR(False Negative Rate) is confirmed to be better 3% than the conventional algorithm which is a single structure algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.11
• /
• pp.31-38
• /
• 2013

Feature normalization as a pre-processing step has been widely used in classification problems to reduce the effect of different scale in each feature dimension and error as a result. Most of the existing methods, however, assume some distribution function on feature distribution. Even worse, existing methods do not use the labels of data points and, as a result, do not guarantee the optimality of the normalization results in classification. In this paper, proposed is a supervised rank normalization which combines rank normalization and a supervised learning technique. The proposed method does not assume any feature distribution like rank normalization and uses class labels of nearest neighbors in classification to reduce error. SVM, in particular, tries to draw a decision boundary in the middle of class overlapping zone, the reduction of data density in that area helps SVM to find a decision boundary reducing generalized error. All the things mentioned above can be verified through experimental results.

• Cartoon and Animation Studies
• /
• s.11
• /
• pp.87-104
• /
• 2007

This paper proposes to analyze artistic characteristic based on the line expression of , Te Wei's Chinese water-ink animation. We considered the transitions of Chinese water-ink animation through Shang-hai Animation Film Studio's works which induced the dominant improvement in Chinese animations and other major animation industries internationally with the theoretical explanations about particular understanding of line concept and formative characteristics. We not only considered line expression of , aesthetic and idea etc. which are the central point of this paper but also researched the artistic possibilities through the effects of Chinese water ink and line and the relationship of animation.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.3
• /
• pp.182-187
• /
• 2003

In this thesis, we propose the algorithm to improve the performance of speaker verification that is mapping feature parameters by using RBF neural network. There is a big difference between wire vector region and wireless one which comes from the same speaker. For wire/wireless speakers model production, speaker verification system should distinguish the wire/wireless channel that based on speech recognition system. And the feature vector of untrained channel models is mapped to the feature vector(LPC Cepstrum) of trained channel model by using RBF neural network. As a simulation result, the proposed algorithm makes 0.6%∼10.5% performance improvement compared to conventional method such as cepstral mean subtraction.

• Journal of KIISE:Software and Applications
• /
• v.28 no.8
• /
• pp.570-581
• /
• 2001

본 논문에서는 윤곽선(edge) 기반의 형태 정보와 웨이브렛 변환(wavelet transform)에 의한 방향(direction) 정보를 사요하는데 2단계 상표 영상 검색 시스템을 제안한다. 1 단계에서는 후보 상표 영상을 추출하기 위해 영상의 전반적인 정보로 원 상표 영상(original trademark image)을 웨이브렛 변환하여 얻은 X, Y 방향 고주파(high frequency) 성분으로부터 구한 방향 정보와 영상의 윤곽선에 대해 모멘트를 구하는 향상된 불변 모멘트(improved invariant moment)를 이용한다. 2단계에서는 후부 영상들에 대해 영상의 세부 정보인 윤곽선 각도(edge angle)와 윤곽선 반지름(edge radius) 정보를 추출하여 유사도 측정 알고리즘을 통해 결과 영상을 산출하게 된다. 본 상표 영상 검색 시스템은 문자 색인으로는 색인이 용이 하지 않은 기하학적도형 상표 영상만을 사용하였다. 본 시스템에서는 색상과는 상관없는 특징인 형태 정보와 방향 정보만을 이용하므로 같은 색상 구성을 가진 유사 영상뿐만 아니라, 유사하지만 바탕이 반전된 영상이나 색상이 다른 유사 영상에 대해서도 바르게 검색할 수 있으며, 각 특징을 일반화해줌으로 이동.회전.크기 변화에도 불변하는 견고성을 가진다. 또한 효율적인 검색을 위해 2단계의 구조를 사용하였으며, 각 단계마다 계산량을 줄여 검색 시간을 감소시키도록 설계되었다.