• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.347-349
• /
• 1999

본 논문에서는 대규모 영상 데이터베이스로부터 모양 영상에 대한 검색을 빠르고 효율적으로 수행하기 위해 해싱기법을 변형한 색인구조와 검색방법을 제안한다. 제안된 색인 구조는 이진 모양 영상(binary shape image)의 불변 모멘트 집합(invariant moments set)을 특징 벡터로 사용하여 다차원으로 구성된다. 이 색인 구조를 기반으로 제안된 해싱을 변형한 검색방법은 기존의 방법들에 비해 검색공간을 줄임으로써 검색속도를 높인다. 본 논문에서 제안한 색인구조와 검색방법을 1000개의 이진 모양 영상들에 적용해 본 결과 검색공간이 전체 공간의 10% 미만으로 줄어드는 효과가 있었다.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.579-582
• /
• 1999

In this paper, we propose a human face detection algorithm using adaptive skin color model and neural networks. To attain robustness in the changes of illumination and variability of human skin color, we perform a color segmentation of input image by thresholding adaptively in modified hue-saturation color space (TSV). In order to distinguish faces from other segmented objects, we calculate invariant moments for each face candidate and use the multilayer perceptron neural network of backpropagation algorithm. The simulation results show superior performance for a variety of poses and relatively complex backgrounds, when compared to other existing algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10b
• /
• pp.155-160
• /
• 1987

In this paper, the model reduction method of the linear time invariant continuous systems is proposed. The denominator of reduced order model is determined by the eigenvalue selected considering the error of the power series that exists between original system and reduced order system at each time moments. And the numerator of model is founded by the time moment matching method. The method suggested is compared with other various methods in examples.

• Proceedings of the KIEE Conference
• /
• 1987.07a
• /
• pp.86-89
• /
• 1987

In this paper, feature vectors composed of 6 features of Fourier spectrum of 2-D image at each projection angle and 7 features of invariant moments are defined. The feature are extracted by optical Fourier transformer and Radon transformer. After extracting the feature, the input pattern is recognized using the squared Mahalanobis distance.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.04a
• /
• pp.225-230
• /
• 2004

A cold ＆ hot rolling coil production line of iron nill consists of a kind of coherent automatic process, but an automatic labelling process still had technical difficulties in the automation of its process. The reason for difficulties in building an automatic process is that quantitative data for each rolled coil from every shipping is not easy to receive from the previous process. it is not possible to apply for a general and simple purpose robot that is actually worked through a taught position to the process because the size and direction of the coi1 has differed on every shipping. From these reasons. we introduce a robot vision system to accept an expected variable situation and to ensure the stability and flexibility of the process. This paper examines a study applied for similar cases and finds the position and direction of relied coil using the moment invariant algorithm proposed by Hu. In addition. the camera calibration and position error compensation algorithm is applied by the analysis of the relationship of transition in a space coordinate system. The construction of a robot vision system proposed by this paper is a more intellectual system than that of the automatic labelling system. which is already used to the Daihen steel nill of NEW JAPAN steel mill co. Ltd in Japan, and shows a better independent operation in the field of production.

• Journal of Korea Society of Industrial Information Systems
• /
• v.6 no.2
• /
• pp.16-22
• /
• 2001

In this paper we mose a new scheme for recognition of deformed letters by extracting feature vectors based on Gibbs distributions which are well suited for representing the spatial continuity. The extracted feature vectors are comprised of 2-D conditional moments which are invariant under translation, rotation, and scale of an image. The Algorithm for pattern recognition of deformed letters contains two parts: the extraction of feature vector and the recognition process. (i) We extract feature vector which consists of an improved 2-D conditional moments on the basis of estimated conditional Gibbs distribution for an image. (ii) In the recognition phase, the minimization of the discrimination cost function for a deformed letters determines the corresponding template pattern. In order to evaluate the performance of the proposed scheme, recognition experiments with a generated document was conducted. on Workstation. Experiment results reveal that the proposed scheme has high recognition rate over 96%.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.2
• /
• pp.1-6
• /
• 1999

We propose a new algorithm for pattern classification by extracting feature vectors based on Gibbs distributions which are well suited for representing the characteristic of an images. The extracted feature vectors are comprised of 2-D moments which are invariant under translation rotation, and scale of the image less sensitive to noise. This implementation contains two puts: feature extraction and pattern classification First of all, we extract feature vector which consists of an improved 2-D moments on the basis of estimated Gibbs distribution Next, in the classification phase the minimization of the discrimination cost function for a specific pattern determines the corresponding template pattern. In order to evaluate the performance of the proposed scheme, classification experiments with training document sets of characters have been carried out on SUN ULTRA 10 Workstation Experiment results reveal that the proposed scheme had high classification rate over 98%.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.10 no.4
• /
• pp.78-84
• /
• 1996

In this study, 3-D object recognition and restoration independent of the object translation for automotive kind recognition in parking administration system using an ultrasonic sensor array, neural networks and invariant moments are presented. Using invariant moment vectors of the acquired data 16$\times$8 pixels, 3-D objects could be classified by SCL (Simple Competitive Learning) neural networks. Modified SCL neural networks using the 16$\times$8 low resolution image was used for object restoration of 32$\times$32 high resolution image. Invariant moment vectors kept constant independent of the object translation. The recognition rates for the training and the testing data were 98[%] and 95[%], respectively. The experimental results have shown that ultrasonic sensor array with the neural networks could be applied for the detection of the automobiles and classification of the automotive kind.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.11a
• /
• pp.273-276
• /
• 2009

본 논문에서는 Dynamic Space Time Warping(DSTW) 알고리즘을 이용하여 손동작을 다양한 배경에서도 정확하게 인식할 수 있는 방법을 제안한다. DSTW 알고리즘을 이용한 기존의 손동작 인식 방법은 질의영상의 매 프레임 마다 검출된 다수의 손 후보영역을 사용하여 모델영상과 시간 축 상으로 비교하는 방법이다. 그러나 기존의 DSTW 알고리즘을 이용한 손동작 인식 방법은 손을 포함하지 않은 후보영역들(배경, 팔꿈치 등)에 의해 오인식될 수 있는 경로를 생성하며, 그 결과로 사용자가 의도하지 않은 손동작으로 인식될 수 있다. 이러한 단점을 해결하기 위해서, 본 논문에서는 손 후보영역의 불변 모멘트를 이용하여 질감 정보를 추출한 후 후보영역들 사이의 유사도를 비교하였다. 제안한 방법은 유사도를 모델과 질의의 매칭비용에 가중치로 적용하였고, 다양한 실험 결과 제안한 방법이 기존의 방법에 비해 사용자의 손동작을 정확하게 인식하는 것을 확인하였다.

• ETRI Journal
• /
• v.34 no.4
• /
• pp.572-582
• /
• 2012

The discrete Gaussian-Hermite moment (DGHM) is a global feature representation method that can be applied to square images. We propose a modified DGHM (MDGHM) method and an MDGHM-based scale-invariant feature transform (MDGHM-SIFT) descriptor. In the MDGHM, we devise a movable mask to represent the local features of a non-square image. The complete set of non-square image features are then represented by the summation of all MDGHMs. We also propose to apply an accumulated MDGHM using multi-order derivatives to obtain distinguishable feature information in the third stage of the SIFT. Finally, we calculate an MDGHM-based magnitude and an MDGHM-based orientation using the accumulated MDGHM. We carry out experiments using the proposed method with six kinds of deformations. The results show that the proposed method can be applied to non-square images without any image truncation and that it significantly outperforms the matching accuracy of other SIFT algorithms.