• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.448-450
• /
• 2012

본 논문에서는 Kinect 방식의 RGB-D 영상센서를 사용하여, 깊이(Depth) 영상으로부터 3차원 객체의 기하정보를 표현하는 표면 정규 벡터(Surface Normal Vector)를 추출하고, 그 결과를 영상화하는 방법을 제안하며, 제안된 방법으로 생성된 영상으로부터 깊이 영상의 특징점 및 특징 기술자를 추출하여 3차원 객체 인식 성능을 향상시키는 방법을 제안한다. 또한 생성된 RGB-D 특징 기술자들을 객체 단위로 구분 가능한 코드북(CodeBook) 학습을 통한 인식방법을 제안하여 객체의 인식 성능을 높이는 방법을 제안한다. 제안하는 RGB-D 기반의 특징 추출 및 학습 방법은 텍스쳐 유무, 카메라 회전 및 이동 변화 등의 환경변화에 강건함을 실험적으로 증명하였으며, 이 방법은 Kinect 방식의 RGB-D 영상을 사용하는 3차원 객체/공간 인식 및 추적, 혹은 이를 응용하는 증강현실 시스템에 적용하여 사용될 수 있다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.8
• /
• pp.5280-5287
• /
• 2014

This paper proposes a method in which classes are grouped as a hierarchical tree structure for the effective classification of the Raman spectra. As experimental data, the Raman spectra of 28 chemical compounds were obtained, and pre-treated with noise removal and normalization. The spectra that induced a classification error were grouped into the same class and the hierarchical structure class was composed. Each high and low class was classified using a PCA-MAP method. According to the experimental results, the classification of 100% was achieved with 2.7 features on average when the proposed method was applied. Considering that the same classification rates were achieved with 6 features using the conventional method, the proposed method was found to be much better than the conventional one in terms of the total computational complexity and practical application.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.117-120
• /
• 2017

본 논문은 스테레오 영상을 이용하여 3 차원 영상을 제공하기 위한 과정에서 중요한 변위 지도 생성 과정의 개선을 목적으로 한다. 변위 지도란, 서로 다른 시점의 두 영상 내에 매칭되는 대응점을 찾고 이와 같은 대응점들 간의 차를 통해 상대적 거리정보를 얻은 후, 이를 정규화하여 픽셀 값으로 나타낸 지도이다. 이에 본 논문에서는 변위 지도 생성 시, 물체들 간 대응점 매칭율을 높이기 위해 물체들의 외곽을 보존하여 형태를 뚜렷하게 하는 전처리 과정을 제안한다. 제안하는 방안은 제한 적응 히스토그램 평활화를 통해 물체들의 세부적인 특징들을 부각시키고, 양방향 필터를 통해 외각을 뚜렷하게 하는 전처리 과정을 포함한다. 본 논문에서는 제한 적응 히스토그램 평활화와 양방향 필터의 처리 과정을 분석하고, 실험결과를 통해 제안하는 전처리 과정을 검증하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.623-624
• /
• 2009

본 논문에서는 신경망의 오류 역전파(Backpropagation) 학습 알고리즘을 이용한 얼굴의 정상 비정상을 인식하는 보안 시스템을 제안하였다. 제안된 시스템은 정지영상 및 동영상에서 입력된 얼굴영상을 전처리 단계에서 얼굴영역을 검출하여 $160{\times}160$ 크기의 고정 크기로 확대 및 축소 작업을 거친다. Mosaic 처리와 LaplacianEdge 처리를 거쳐 $40{\times}40$ 크기로 이진화한 정규화 데이터를 Gravity-Center 처리를 한다. 오류 역전파 학습 알고리즘으로 얼굴의 특징을 학습한 후 각종 정상 및 비정상 얼굴 데이터를 이용하여 인식률을 실험 하였다. 실험데이터는 이 분야의 공인 자료인 LFW Face Database[7] 데이터를 사용하였으며, 실험결과는 제안된 방법이 문제 해결에 적합한 접근임을 보여준다.

• Journal of Korea Multimedia Society
• /
• v.5 no.2
• /
• pp.158-166
• /
• 2002

In this paper, we proposed a contour shape description method which use the CFR(contour fluctuation ratio) feature. The CFR is the ratio of the line length to the curve length of a contour segment. The line length means the distance of two end points on a contour segment, and the curve length means the sum of distance of all adjacent two points on a contour segment. We should acquire rotation and scale invariant contour segments because each CFR is computed from contour segments. By using the interleaved contour segment of which length is proportion to the entire contour length and which is generated from all the points on contour, we could acquire rotation and scale invariant contour segments. The CFR can describes the local or global feature of contour shape according to the unit length of contour segment. Therefore we describe the shape of objects with the feature vector which represents the distribution of CFRs, and calculate the similarity by comparing the feature vector of corresponding unit length segments. We implemented the proposed method and experimented with rotated and scaled 165 fish images of fifteen types. The experimental result shows that the proposed method is not only invariant to rotation and scale but also superior to NCCH and TRP method in the clustering power.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.6
• /
• pp.183-190
• /
• 2016

This study proposed a more stable robust recognition algorithm which detects faces reliably even in cases where there are changes in lighting and angle of view, as well it satisfies efficiency in calculation and detection performance. The algorithm proposed detects the face area alone after normalization through pre-processing and obtains a feature vector using (PCA). Also, by applying the feature vector obtained for SVM, face areas can be tested. After the testing, using the feature vector is final face recognition performed. The algorithm proposed in this study could increase the stability and accuracy of recognition rates and as a large amount of calculation was not necessary due to the use of two dimensions, real-time recognition was possible.

• Journal of Advanced Navigation Technology
• /
• v.17 no.2
• /
• pp.247-254
• /
• 2013

The task of 3D gesture recognition for controlling equipments is highly challenging due to the propagation of 3D smart TV recently. In this paper, the AdaBoost algorithm is applied to 3D gesture recognition by using Kinect sensor. By tracking time interval trajectory of hand, wrist and arm by Kinect, AdaBoost algorithm is used to train and classify 3D gesture. Experimental results demonstrate that the proposed method can successfully extract trained gestures from continuous hand, wrist and arm motion in real time.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.9C
• /
• pp.930-938
• /
• 2005

We propose a content-based image retrieval(CBIR) method based on an efncient combination of a color feature and multiresolution texture features. As a color feature, a HSV autocorrelograrn is chosen which is blown to measure spatial correlation of colors well. As texture features, BDIP and BVLC moments are chosen which is hewn to measure local intensity variations well and measure local texture smoothness well, respectively. The texture features are obtained in a wavelet pyramid of the luminance component of a color image. The extracted features are combined for efficient similarity computation by the normalization depending on their dimensions and standard deviation vectors. Experimental results show that the proposed method yielded average $8\%\;and\;11\%$ better performance in precision vs. recall than the method using BDIPBVLC moments and the method using color autocorrelograrn, respectively and yielded at least $10\%$ better performance than the methods using wavelet moments, CSD, color histogram. Specially, the proposed method shows an excellent performance over the other methods in image DBs contained images of various resolutions.

• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.4
• /
• pp.47-55
• /
• 2010

In this paper, we proposed a recognition system of smile facial expression for smile treatment training. The proposed system detects face candidate regions by using Haar-like features from camera images. After that, it verifies if the detected face candidate region is a face or non-face by using SVM(Support Vector Machine) classification. For the detected face image, it applies illumination normalization based on histogram matching in order to minimize the effect of illumination change. In the facial expression recognition step, it computes facial feature vector by using PCA(Principal Component Analysis) and recognizes smile expression by using a multilayer perceptron artificial network. The proposed system let the user train smile expression by recognizing the user's smile expression in real-time and displaying the amount of smile expression. Experimental result show that the proposed system improve the correct recognition rate by using face region verification based on SVM and using illumination normalization based on histogram matching.