• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.903-906
• /
• 2001

본 논문에서는 조명의 변화에 의해 컬러 영상의 컬러 성분이 달라지더라도 영상 내 컬러간의 편차값을 나타내는 공분산 행렬(covariance matrix)의 고유벡터(eigenvector)와 영상 내 화소들의 컬러 성분과의 상관관계는 거의 변화하지 않는 특징을 이용한 조명 변화에 강인한 영상 검색 방법을 제안한다. 제안된 방법은 영상에서 컬러 성분들의 공분산 행렬과 공분산 행렬의 고유치(eigenvalue), 고유벡터를 계산한 후, 가장 큰 고유치에 관계된 고유벡터로 화소를 투영시키고, 투영된 벡터의 크기 성분으로 영상을 재구성한다. 재구성된 영상으로부터 7개의 불변 모멘트(moment)를 계산하고, 공분산의 가장 큰 고유치를 가중치로 부과하여 특징벡터를 추출한다. 7개의 불변 모멘트로부터 구한 특징벡터는 영상 내 물체의 이동, 영상의 회전, 크기 변화뿐만 아니라, 조명의 변화에 의해 컬러가 변화할 경우에도 유사한 영상을 잘 검색한다. 제안된 방법의 성능 확인을 위하여 5가지 조명에서 얻은 영상 데이터베이스를 이용하여 실험하였으며, 실험 결과 히스토그램 인터섹션에 비해 적은 특징량으로 검색이 가능하면서 조명 변화에도 대응할 수 있는 검색 결과를 얻을 수 있었다.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.951-954
• /
• 1998

This paper describes the implementation of the machine vision system and the method of classifying the objects. Its system described in this paper is consisted of robot, conveyer system, warehouse, and machine vision. This system first recognizes the object on conveyer, and then robot moves it to the warehouse. The position of the object on conveyer is always not constant, because it is not easy to extract the feature of its object and classify it into one of several categories. In this paper, to classify or inspect the pattern of the object, we propose the method of template matching using feature vector such as position invariant moment and mophological operation such as opening and closing. And we indentified an unregistered object using unsuperviser learning method and assigned it to the new pattern. We implemented its system and obtained satisfied results.

• International journal of advanced smart convergence
• /
• v.9 no.3
• /
• pp.85-96
• /
• 2020

It is important to extract salient object image and to solve the invariance problem for image recognition. In this paper we propose a new hybrid algorithm for invariance and improved classification performance in image recognition, whose algorithm is combined by FT(Frequency-tuned Salient Region Detection) algorithm, Guided filter, Zernike moments, and a simple artificial neural network (Multi-layer Perceptron). The conventional FT algorithm is used to extract initial salient object image, the guided filtering to preserve edge details, Zernike moments to solve invariance problem, and a classification to recognize the extracted image. For guided filtering, guided filter is used, and Multi-layer Perceptron which is a simple artificial neural networks is introduced for classification. Experimental results show that this algorithm can achieve a superior performance in the process of extracting salient object image and invariant moment feature. And the results show that the algorithm can also classifies the extracted object image with improved recognition rate.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.135-135
• /
• 2001

In recent years there have been increasing interests in real-time object tracking with image information. Since image information is affected by illumination, this paper presents the real-time object tracking method based on neural networks that have robust characteristics under various illuminations. This paper proposes three steps to track the object and the fast tracking method. In the first step the object color is extracted using neural networks. In the second step we detect the object feature information based on invariant moment. Finally the object is tracked through a shape recognition using neural networks. To achieve the fast tracking performance, we have a global search for entire image and then have tracking the object through local search when the object is recognized.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.2
• /
• pp.69-77
• /
• 1993

Automatic image recognition system is essential for a better man-to machine interaction. Because of the noise and deformation due to the sensor operation, it is not simple to build an image recognition system even for the fixed images. In this paper neural network which has been reported to be adequate for pattern recognition task is applied to the fixed and variational(rotation, size, position variation for the fixed image)recognition with a hope that the problems of conventional pattern recognition techniques are overcome. At fixed image recognition system. ART model is trained with face images obtained by camera. When recognizing an matching score. In the test when wigilance level 0.6 - 0.8 the system has achievel 100% correct face recognition rate. In the variational image recognition system, 65 invariant moment features sets are taken from thirteen persons. 39 data are taken to train multi-layer perceptron and other 26 data used for testing. The result shows 92.5% recognition rate.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.36 no.4
• /
• pp.280-286
• /
• 1987

A new method is presented for obtaining redced-order model for time-invariant systems. This method does not require the calculation of the reciprocal transformation, the alpha table, the beta-table and the alpha-beta expansion which should be calculated in Routh approximation method, hence it is computationally very attractive better than Routh approximation method, furthemore the stability of the reduced-order model is guaranted if the original system is stable. This method starts with the continued fraction espansion of auxiliary denominator polynomial give for the denominator polynomial of the reduced-order model. The coefficients of the numerator polynomial are then obtained by equating moment of the original and the reduced-order medel.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2010.07a
• /
• pp.509-510
• /
• 2010

본 논문에서는 마우스 제어를 위한 불변 모멘트 기반의 손 인식 알고리즘을 제안한다. 이를 위하여 배경영상과 입력영상의 차이를 구하고, RGB 컬러모델을 HSV 컬러모델로 변환하여 피부색상과 유사한 영역을 얻었다. 이 둘 사이의 교집합을 통하여 손 영역을 추출하고 모폴로지 연산을 통해 잡음을 제거한 다음 불변 모멘트를 이용하여 손 영역을 인식하였다. 제안된 방법은 손의 이동, 크기 변화, 회전에 무관하게 손을 인식할 수 있다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.1
• /
• pp.44-49
• /
• 2003

This paper describes a method of estimating miniature train location by color vision for development of an intelligent railway system model. In the teal world, to control trains automatically, GPS(Global Positioning System) is indispensable to determine the location of trains. A color vision system was used for estimating the location of trains in an indoor experiment. Two different rectangular color bars were attached to the top of each train as a means of identifying them. Several trains were detected where they were located on the track by color feature, geometric features and moment invariant, and tracked simultaneously. In the experiment the identity, location and direction of each train were estimated and transferred to the control computer using serial communication. Processing speed of up to 8 frames/sec could be achieved, which was enough speed for the real-time train control.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.1
• /
• pp.28-32
• /
• 2001

인간의 손동작 인식은 오랫동안 언어로서의 역할을 해왔던 통신수단의 한 방법이다. 현대의 사회가 정보화 사회로 진행됨에 따라 보다 빠르고 정확한 의사소통 및 정보의 전달을 필요로 하는 가운데 사람과 컴퓨터간의 상호 연결 혹은 사람의 의사 표현에 있어 기존의 장치들이 가지는 단점을 보안하며 이 부분에 사람의 두 손으로 표현되는 자유로운 몸짓을 이용하려는 연구가 최근에 많이 진행되고 있는 추세이다. 본 논문에선 2차원 입력 영상으로부터 동적인 손동작의 사용 없이 손의 특징을 이용한 새로운 인식 알고리즘을 제안하고, 보다 높은 인식률과 실 시간적 처리를 위해 Radial Basis Function Network 및 부가적인 특징점을 통한 손동작의 인식을 구현하였다. 또한 인식된 손동작의 의미를 바탕으로 인식률 및 손동작 표현의 의미성에 대한 정확도를 판별하기 위해 로봇의 제어에 적용한 실험을 수행하였다.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2358-2361
• /
• 2001

In recent years there have been increasing interests in real-time object tracking with image information. Since image information is affected by illumination, this paper presents the real-time object tracking method based on neural networks which have robust characteristics under various illuminations. This paper proposes three steps to track the object and the fast tracking method. In the first step the object color is extracted using neural networks. In the second step we detect the object feature information based on invariant moment. Finally the object is tracked through a shape recognition using neural networks. To achieve the fast tracking performance, this paper first has a global search of entire image and tracks the object through local search when the object is recognized.