• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.1
• /
• pp.51-58
• /
• 2005

we can set laser patterns with 3D information from vision camera after projected to object with laser stripes. They are very useful for 3-Dimensional informations. We researched the laser patterns of human body projected by stripes and found out three featuring patterns and made database of patterns using Fourier descriptors to recognize the patterns of bodies. The HMM method and Fourier descriptors to recognize human body were experimented. We found out HMM method can recognize human body in more efficient rate than the other.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.207-212
• /
• 2008

최근 공장 자동화가 보편화됨에 따라 무인 운반설비의 자동화 시스템 개발의 한 부분으로써 Stereo Vision 장치를 이용하여 입력된 영상의 에지(Edge)를 추출하고, 추출된 에지를 이용하여 물체의 위치적 특징을 찾고 무인크레인이 이동해야할 위치좌표를 전달한다. 본 연구에서는 실제 산업현장에 가장 보편적인 형상인 판재와 원통을 기준으로 CCD 카메라 2대를 이용하여 물체의 형상을 인식하고, 그 물체의 중심점을 찾는 알고리즘을 제안하였다. 우선 에지를 추출하고 사용자의 선택에 따라 추출된 에지의 특징을 판별하여 판재와 원통을 구분하여 원하는 물체의 위치정보를 찾아낸다. 본 연구는 무인 운반설비의 자동화 시스템 개발에 도움이 될 것으로 기대된다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.2
• /
• pp.112-123
• /
• 1990

This paper presents a vertex-detecting of Hanguel patterns using nested contour shape. Inputed binary character patterns are transformed by distance transformation method and make a new file of transferred data by analysis of charactersitcs. A new vertex-detecting algorithm for recognizing Hanguel patterns using the two data files is proposed. This algorithm is able to reduce the projecting parts of Hanguel pattern, separate the connecting parts between different strokes, set the code number by transformed value of coorked features. It makes the output of results in order to apply the Hanguel recognition.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.198-200
• /
• 2010

구조적 조명 기법은 그레이코드 패턴광을 물체에 투영시켜 정확하게 3차원 형상 정보를 복원 할 수 있는 방법이다. 그러나 물체에 투영되는 그레이코드 패턴광이 카메라에 정확하게 인식 되어야 보다 정밀하게 3차원 좌표를 추정할 수 있다. 즉, 주변광의 밝기가 패턴광의 밝기에 비해 무시할 수 없을 정도로 밝은 경우 카메라가 물체와 투영된 패턴을 정확히 인식하기 어렵다. 본 논문에서는 구조적 조명 기법이 주변의 밝기에 따라 제한적인 문제점을 해결하기 위해 High Dynamic Range Imaging (HDRI) 알고리즘을 적용시켜 보다 넓은 동적 범위의 밝기 영역에서 3차원 형상을 정확하게 복원하는 방법을 제안한다. 실험결과 HDRI를 이용하여 복원하였을 경우 그렇지 않은 경우에 비해 복원 정밀도가 크게 개선되는 것을 확인할 수 있다.

• Journal of Korea Multimedia Society
• /
• v.11 no.11
• /
• pp.1501-1514
• /
• 2008

The face shape extracted by the depth values has different appearance as the most important facial information. The face images decomposed into frequency subband are signified personal features in detail. In this paper, we develop a method for recognizing the range face images by multiple frequency domains for each depth image using the modified fuzzy c-mean algorithm. For the proposed approach, the first step tries to find the nose tip that has a protrusion shape on the face from the extracted face area. And the second step takes into consideration of the orientated frontal posture to normalize. Multiple contour line areas which have a different shape for each person are extracted by the depth threshold values from the reference point, nose tip. And then, the frequency component extracted from the wavelet subband can be adopted as feature information for the authentication problems. The third step of approach concerns the application of eigenface to reduce the dimension. And the linear discriminant analysis (LDA) method to improve the classification ability between the similar features is adapted. In the last step, the individual classifiers using the modified fuzzy c-mean method based on the K-NN to initialize the membership degree is explained for extracted coefficient at each resolution level. In the experimental results, using the depth threshold value 60 (DT60) showed the highest recognition rate among the extracted regions, and the proposed classification method achieved 98.3% recognition rate, incase of fuzzy cluster.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.04a
• /
• pp.287-292
• /
• 2004

In this study, we made a comparative study of backpropagation neural network and probabilistic neural network and bayesian classifier and perceptron as shape recognition algorithm of welding flaws. For this purpose, variables are applied the same to four algorithms. Here, feature variable is composed of time domain signal itself and frequency domain signal itself, Through this process, we confirmed advantages/disadvantages of four algorithms and identified application methods of few algorithms.

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.759-768
• /
• 2005

This paper describes an algorithm that can recognize gestures constructing subspace gesture symbols with hybrid feature information. The previous popular methods based on geometric feature and appearance have resulted in ambiguous output in case of recognizing between similar gesture because they use just the Position information of the hands, feet or bodily shape features. However, our proposed method can classify not only recognition of motion but also similar gestures by the partial feature information presenting which parts of body move and the global feature information including 2-dimensional bodily motion. And this method which is a simple and robust recognition algorithm can be applied in various application such surveillance system and intelligent interface systems.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.512-514
• /
• 1999

효율적인 물체인식을 위해서는 물체의 형상특징을 직선적으로 기술할 수 있는 체적소 기반 물체 표현 방법이 필요하다. 본 논문에서는 몇 개의 계수를 가지고 3차원 정보를 효율적으로 표현할 수 있는 superquadric을 이용하여 기본적인 3차원 물체를 모델링 한다. 그리고 보다 복잡하고 정교한 물체의 표현을 위해서 변형된 superquadric을 함께 이용한다. 이렇게 만들어진 개개의 3차원 모델에 z-buffer 알고리즘을 적용하여 하나의 완전한 3차원 물체로 표현하는 방법을 제시하고 실험을 통해 그 유용성을 입증하였다.

• Journal of Korea Multimedia Society
• /
• v.13 no.7
• /
• pp.1000-1015
• /
• 2010

In this paper, we propose a novel algorithm for hand gesture recognition. The hand detection method is based on human skin color, and we use the boundary energy information to locate the hand region accurately, then the moment method will be employed to locate the hand palm center. Hand gesture recognition can be separated into 2 step: firstly, the hand posture recognition: we employ the parallel NNs to deal with problem of hand posture recognition, pattern of a hand posture can be extracted by utilize the fitting ellipses method, which separates the detected hand region by 12 ellipses and calculates the white pixels rate in ellipse line. the pattern will be input to the NNs with 12 input nodes, the NNs contains 4 output nodes, each output node out a value within 0~1, the posture is then represented by composed of the 4 output codes. Secondly, the hand gesture tracking and recognition: we employed the Kalman filter to predict the position information of gesture to create the position sequence, distance relationship between positions will be used to confirm the gesture. The simulation have been performed on Windows XP to evaluate the efficiency of the algorithm, for recognizing the hand posture, we used 300 training images to train the recognizing machine and used 200 images to test the machine, the correct number is up to 194. And for testing the hand tracking recognition part, we make 1200 times gesture (each gesture 400 times), the total correct number is 1002 times. These results shows that the proposed gesture recognition algorithm can achieve an endurable job for detecting the hand and its' gesture.

• Journal of Biosystems Engineering
• /
• v.21 no.3
• /
• pp.325-335
• /
• 1996

Visual features are crucial for monitoring the growth state, indexing the drying performance, and grading the quality of oak mushrooms. A computer vision system with neural net information processing technique was utilized to quantize quality factors of a dried oak mushrooms distributed over the cap and gill sides. In this paper, visual feature extraction algorithm were integrated with the neural net processing to deal with various fuzzy patterns of mushroom shapes and to compensate the fault sensitiveness of the crisp criteria and heuristic rules derived from the image processing results. The proposed algorithm improved the segmentation of the skin features of each side, the identification of cap and gill surfaces, the identification of stipe states and removal of the stipe, etc. And the visual characteristics of dried oak mushrooms were analyzed and primary visual features essential to tile quality evaluation were extracted and quantized. In this study, black and white gray images were captured and used for the algorithm development.