• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.49-53
• /
• 2006

본 논문에서는 복잡한 배경을 가진 영상에서 손 영역을 안정적으로 검출, 손 형상을 인식하여 그림 맞추기 응용 프로그램을 제어하는 시스템에 대해 기술한다. 피부색의 컬러 정보를 이용하여 손 영역만을 추출한 후 핑거 팁 템플릿매칭을 사용하여 손가락 끝점을 찾아낸다. 또한 손 영역의 에지 방향성 히스토그램을 구하여 얻어진 정보를 바탕으로 주성분 분석법을 사용하여 손 형상을 인식한다. 최종적으로 인식된 손 형상 정보와 손가락 끝점 추적을 이용한 명령어 실행으로 그림 맞추기 응용 프로그램을 제어 한다. 본 논문에서 제안한 알고리즘으로 그림 맞추기 응용 프로그램 제어에 적용한 결과 안정적인 실험 결과를 얻을 수 있었고, HCI 분야에서 다양하게 활용될 수 있음을 확인하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.9
• /
• pp.2013-2018
• /
• 2011

Coronary angioplasty and coronary artery bypass graft, both are for the treatment of myocardial infarction widely used methods. For these procedures, there are especially difficulties in stenosis of blood vessels to diagnose accurately. To remedy this problem, by several researchers by using edge detection to detect stenosis of blood vessels has been studying. However, the results of using these methods vary defend on the vascular structure and the quality of the image. In this study, to improve these problems, the new algorithm is proposed. The proposed algorithm consists of methods to detect bifurcation of blood vessels and its ending point by using multi sampling, threshold and fuzzy algorithm. To evaluate the performance of the proposed algorithm, angiography was used for the different results of the blood vessels of the proposed algorithm, and the result was effective in detecting bifurcation of blood vessels and its ending point.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.3
• /
• pp.85-90
• /
• 2014

In this paper, we propose a virtual violin implementation using the detection of bowing and finger dropping position from the estimated finger tip and finger board information with the 3D image data from a Kinect. Violin finger board pattern and depth information are extracted from the color image and depth image to detect the touch event on the violin finger board and to identify the touched position. Final decision of activated musical alphabet is carried out with the finger drop position and bowing information. Our virtual violin uses PC MIDI to output synthesized violin sound. The experimental results showed that the proposed method can detect finger drop position and bowing detection with high accuracy. Virtual violin can be utilized for the easy and convenient interface for a beginner to learn playing violin with the PC-based learning software.

• The KIPS Transactions:PartB
• /
• v.16B no.4
• /
• pp.299-308
• /
• 2009

AAM(Active Appearance Model) is an algorithm to extract face feature points with statistical models of shape and texture information based on PCA(Principal Component Analysis). This method is widely used for face recognition, face modeling and expression recognition. However, the detection performance of AAM algorithm is sensitive to initial value and the AAM method has the problem that detection error is increased when an input image is quite different from training data. Especially, the algorithm shows high accuracy in case of closed lips but the detection error is increased in case of opened lips and deformed lips according to the facial expression of user. To solve these problems, we propose the improved AAM algorithm using lip feature points which is extracted based on a new lip detection algorithm. In this paper, we select a searching region based on the face feature points which are detected by AAM algorithm. And lip corner points are extracted by using Canny edge detection and histogram projection method in the selected searching region. Then, lip region is accurately detected by combining color and edge information of lip in the searching region which is adjusted based on the position of the detected lip corners. Based on that, the accuracy and processing speed of lip detection are improved. Experimental results showed that the RMS(Root Mean Square) error of the proposed method was reduced as much as 4.21 pixels compared to that only using AAM algorithm.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.242-245
• /
• 1998

음성인식 시스템의 입력인 음성은 실제의 음성부분 외에도 주변잡음을 포함한 기침 소리, 문닫는 소리, 책장 넘기는 소리등과 같은 사용자에 의해서 발생될 수 있는 다양한 종류의 비음성을 포함할 수 있다. 특히 에너지가 큰 비음성을 포함하는 경우 기존의 끝점검출 알고리듬만으로는 음성부분만의 정확한 검출이 어렵게 되고 이는 음성인식 시스템의 성능을 저하시키는 주요 원인이 된다. 본 논문에서는 음성 발생시 일어날 수 있는 비음성들에 대해서 조사하고 이러한 비음성이 포함될 때 음성부분만의 정확한 검출을 가능하게 하는 알고리듬을 제시하였다. 사용된 파라미터로는 자기상관법에 의해 얻어지는 피치정보와 웨이브렛 영역에서의 에너지로써 비교적 낮은 신호대 잡음비에서도 음성부 검출을 가능하게 하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.6B
• /
• pp.746-751
• /
• 2001

일반적으로 음향 반향 제거기에서 적응필터의 안정성을 보장하기 위해서 동시통화 검출기(DTD)를 사용하여 원단화자 신호와 근단화자 신호의 존재 여부에 따라 적응필터 계수의 적응 여부를 결정한다. 본 논문에서는 두 개의 상호상관계수를 이용하여 계산량과 메모리 소자수 면에서 효율적인 동시통화 검출 알고리즘을 제안하였다. 제안된 알고리즘은 마이크로폰의 입력신호와 추정된 반향 신호간의 상호상관계수, 그리고 마이크로폰의 입력신호와 오차신호간의 상호상관계수를 이용하여, 주행 상황과 같이 심한 잡음 환경에서도 동시통화 구간의 시작점과 끝점 검출에 강인한 특성을 갖는다. 또한, 기존의 상호상관도를 이용하는 방법에 비하여 적은 양의 계산과 메모리를 필요로 하여 저가의 고정소수점 DSP를 이용한 실시간 구현에 적합하다. 성능 평가를 위하여 차내 핸즈프리 통신 환경에서 얻은 실측 데이터를 사용하여 기존의 방법과 비교하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.431-438
• /
• 2020

In this paper, the method to extract lip contour by multiple threshold is proposed. Spyridonos et. el. proposed a method to extract lip contour. First step is get Q image from transform of RGB into YIQ. Second step is to find lip corner points by change point detection and split Q image into upper and lower part by corner points. The candidate lip contour can be obtained by apply threshold to Q image. From the candidate contour, feature variance is calculated and the contour with maximum variance is adopted as final contour. The feature variance 'D' is based on the absolute difference near the contour points. The conventional method has 3 problems. The first one is related to lip corner point. Calculation of variance depends on much skin pixels and therefore the accuracy decreases and have effect on the split for Q image. Second, there is no analysis for color systems except YIQ. YIQ is a good however, other color systems such as HVS, CIELUV, YCrCb would be considered. Final problem is related to selection of optimal contour. In selection process, they used maximum of average feature variance for the pixels near the contour points. The maximum of variance causes reduction of extracted contour compared to ground contours. To solve the first problem, the proposed method excludes some of skin pixels and got 30% performance increase. For the second problem, HSV, CIELUV, YCrCb coordinate systems are tested and found there is no relation between the conventional method and dependency to color systems. For the final problem, maximum of total sum for the feature variance is adopted rather than the maximum of average feature variance and got 46% performance increase. By combine all the solutions, the proposed method gives 2 times in accuracy and stability than conventional method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.377-379
• /
• 2000

대화체 음성의 인식을 위해서는 음성 파형에 관한 음향학적인 연구뿐만 아니라 인식하려는 언어자체에 대한 언어학적인 연구를 필요로 한다. 본 논문에서는 숫자음의 언어학적인 요소를 고려하고, 포만트 주파수를 숫자음 검출과 숫자음 인식에 적용하는 방식을 제안한다. 시스템의 입력은 특정 질의에 대한 응답으로 대화체 문장이며, 끝점 추출 기술을 이용하여 고립단어로 분류한 후, 숫자음만을 검출해 내고, 검출된 숫자음을 인식하기 위해 포만트 주파수를 이용한다. 한국어 연결 숫자음 인식은 한국어 숫자음이 단음절로 구성된다는 점과 발음상의 조음효과 등으로 한계를 가지고 있다. 본 논문에서는 숫자음과 발성에 필요한 음소들을 추출하고, 숫자들을 모음에 따라 6개의 그룹으로 분류하여 인식의 범위를 좁히고, 포만트 주파수 정보와 음소 HMM 모델에 의한 두 단계에 걸친 인식을 수행함으로써 연결 숫자음 인식에 대한 성능을 향상시킨다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1984.12a
• /
• pp.66-69
• /
• 1984

This paper is a study on the Endpoint Detection for Korean Speech Recognition. In speech signal process, analysis parameter was classification from Zero Crossing Rate(Z.C.R), Log Energy(L.E), Energy in the predictive error(Ep) and fundamental Korean Speech digits, /영/-/구/ are selected as date for the Recognition of Speech. The main goal of this paper is to develop techniques and system for Speech input ot machine. In order to detect the Endpoint, this paper makes choice of Log Energy(L.E) from various parameters analysis, and the Log Energy is very effective parameter in classifying speech and nonspeech segments. The error rate of 1.43% result from the analysis.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2216-2219
• /
• 2003

Accurate speech region detection and automatic syllable segmentation is important part of speech recognition system. In automatic speech recognition system, they are needed for the purpose of accurate recognition and less computational complexity, In this paper, we Propose improved syllable segmentation method using ramp edge detection method and residual signal Peak energy. These methods were used to ensure accuracy and robustness for endpoint detection and syllable segmentation system. They have almost invariant response to various background noise levels. As experimental results, we obtained the rate of 90.7％ accuracy in syllable segmentation in a condition of accurate endpoint detection environments.