• Journal of Information Processing Systems
• /
• 제16권2호
• /
• pp.343-359
• /
• 2020

In this paper, a new algorithm is proposed for three-dimensional (3D) shape recognition using local features of model views and its sparse representation. The algorithm starts with the normalization of 3D models and the extraction of 2D views from uniformly distributed viewpoints. Consequently, the 2D views are stacked over each other to from view cubes. The algorithm employs the descriptors of 3D local features in the view cubes after applying Gabor filters in various directions as the initial features for 3D shape recognition. In the training stage, we store some 3D local features to build the prototype dictionary of local features. To extract an intermediate feature vector, we measure the similarity between the local descriptors of a shape model and the local features of the prototype dictionary. We represent the intermediate feature vectors of 3D models in the sparse domain to obtain the final descriptors of the models. Finally, support vector machine classifiers are used to recognize the 3D models. Experimental results using the Princeton Shape Benchmark database showed the average recognition rate of 89.7% using 20 views. We compared the proposed approach with state-of-the-art approaches and the results showed the effectiveness of the proposed algorithm.

• 한국정보통신학회논문지
• /
• 제6권5호
• /
• pp.783-788
• /
• 2002

최근 통신 시스템의 연구와 발전 방향은 목소리의 음성 정보와 말하는 얼굴 영상의 화상 정보를 함께 적용하므로서 음성 정보만을 제공하는 경우보다 높은 인식율을 제공한다. 따라서 본 연구는 청각장애자들의 언어 대체수단 중 하나인 구화(speechreading)에서 가장 시각적 변별력이 논은 입모양 인식을 일반 퍼스널 컴퓨터상에서 구현하고자 한다. 본 논문은 기존의 방법과 달리 말하는 영상 시퀀스에서 입모양 인식을 행하기 위해 3차원 모델을 사용하여 입의 벌어진 정도, 턱의 움직임, 입술의 돌출과 같은 3차원 특징 정보를 제공하였다. 이와 같은 특징 정보를 얻기 위해 3차원 형살 모델을 입력 동영상에 정합시키고 정합된 3차원 형상모델에서 각 특징점의 변화량을 인식파라미터로 사용하였다. 그리고, 인식단위로 동영상을 분리하는 방법은 3차원 특징점 변화량에서 얻어지는 강도의 기울기에 의하여 이루어지고, 인식은 각각의 3차인 특징벡터를 이산 HMM 인식기의 인식 파라메타로 사용하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 1998년도 추계종합학술대회
• /
• pp.181-185
• /
• 1998

최근 통신 시스템의 연구와 발전 방향은 목소리의 음성 정보와 말하는 얼굴 영상의 화상 정보를 함께 적용하므로서 음성 정보만을 제공하는 경우보다 높은 인식율을 제공한다. 따라서 본 연구는 청각장애자들의 언어 대체수단 중 하나인 구화(speechreading)에서 가장 시각적 변별력이 높은 독순(lipreading)을 PC에서 구현하고자 한다. 간 논문은 기존의 방법과 달리 말하는 영상 시퀀스에서 독순(lipreading)을 행하기 위해 3차원 모델을 사용하여 입의 벌어진 정도, 턱의 움직임, 입술의 돌출과 같은 3차원 특징 정보를 제공하였다. 이와 같은 특징 정보를 얻기 위해 3차원 형상 모델을 입력 동영상에 정합시키고 정합된 3차원모델에서 각 특징점의 변화량을 인식파라미터로 사용하였다. 그리고, 인식 단위로 동영상을 분리하는 방법은 3차원 특징점 변화량에서 얻어지는 강도의 기울기에 의한다. 인식은 다차원(multi-dimensional), 다단계 라벨링 방법을 사용하여 3차원 특징벡터를 입력으로 한 이산 HMM을 사용하였다.

• 사상체질의학회지
• /
• 제19권2호
• /
• pp.30-39
• /
• 2007

1. Objectives The Face is an important standard for the classification of Sasang Constitution. We are developing 3D Automatic Face Recognition Apparatus(3D-AFRA) to analyse the facial characteristics. This apparatus show us 3D image and data of man's face and measure facial figure data. So we should examine the figure restoration error of 3D Automatic Fare Recognition Apparatus(3D-AFRA) in hardware Error Analysis. 2. Methods We scanned Face status by using 3D Automatic Face Recognition Apparatus(3D-AFRA). And also we scanned Face status by using laser scanner(vivid 9i). We compared facial shape data be restored by 3D Automatic Face Recognition Apparatus(3D-AFRA) with facial shape data that be restorated by 3D laser scanner. And we analysed the average error and the maximum error of two data. 3. Results and Conclusions In frontal face, the average error was 0.48mm. and the maximum error was 4.60mm. In whole face, the average error of was 0.99mm. And the maximum error was 6.64mm. In conclusion, We assessed that accuracy of 3D Automatic Face Recognition Apparatus(3D-AFRA) is considerably good.

• 지구물리
• /
• 제7권4호
• /
• pp.247-253
• /
• 2004

3차원 형상화를 통한 분석이 많은 분야에서 연구 및 적용되고 있다. 3차원 형상화는 사진영상의 중첩에서 (3차원)레이저 스캐닝(laser scanning)으로 발전을 하여 가고 있으며, 각 방법이 각기 그 자체로서 발전을 해가고 있는 추세이다. 본 연구에서는 물체에 대한 데이터베이스를 구축하여 대상 이미지에 대하여 기하학적 패턴 매칭(patter matching)을 기반으로 한 인지(인식) 알고리즘을 도입하여 3차원 형상화를 통한 지질 및 지반조사를 위한 기초 기술로 활용하고자 하였다. 물체의 외형적인 성질에 기반하며 특별한 광원없이 물체를 인지할 수 있는 3차원 형상화 알고리즘은 지질 및 지반조사 분야 외에서도 많은 도움이 될 것이다.

• 제어로봇시스템학회논문지
• /
• 제19권11호
• /
• pp.960-967
• /
• 2013

Shape recognition of solder ball bumps in a BGA (Ball Grid Array) is an important issue in flip chip bonding technology. In particular, the semiconductor industry has required faster and more accurate inspection of micron-size solder bumps in flip chip bonding as the density of balls has increased dramatically. The difficulty of this issue comes from specular reflection on the metal ball. Shape recognition of a metal ball is a very realproblem for computer vision systems. Specular reflection of the metal ball appears, disappears, or changes its image abruptly due to tiny movementson behalf of the viewer. This paper presents a practical shape recognition method for three dimensional (3-D) inspection of a BGA using a 5-step ring illumination device. When the ring light illuminates the balls, distinctive specularity images of the balls, which are referred to as "iso-slope contours" in this paper, are shown. By using a mathematical reflectance model, we can drive the 3-D shape information of the ball in aquantitative manner. The experimental results show the usefulness of the method for industrial application in terms of time and accuracy.

• 사상체질의학회지
• /
• 제18권2호
• /
• pp.41-49
• /
• 2006

1. Objectives The Face is an important standard for the classification of Sasang Contitutions. We are developing 3D Face Automatic Recognition Apparatus to analyse the facial characteristics. So We should examine a shape demobilization error of 3D Face Automatic Recognition Apparatus. 2. Methods We compared facial shape data be demobilized by 3D Face Automatic Recognition Apparatus with facial shape data that be demobilized by 3D laser scanner. The subject was two korean men. And We analysed the average error and the maximum error of two data. In this process, We used one datum point(the peak of nose) and two datum line(vertical section and horizontal section). 3. Results and Conclusions In each this comparison, the average error of vertical section was 1.962574mm and 2.703814mm. and the maximum error of vertical section was 16.968249mm and 18.61464mm. the average error of horizontal section was 4.173203mm and 21.487479mm. and the maximum error of horizontal section was 3.571210mm and 17.13255mm. Also We complemented this apparatus a little and We reexamined a shape demobilization error of 3D Face Automatic Recognition Apparatus again. Accuracy of a shape demobilization was improved a little. From now on We complement accuracy of a shape demobilization in 3D Face Recognition Apparatus.

• 로봇학회논문지
• /
• 제4권3호
• /
• pp.185-191
• /
• 2009

This paper presents a new shape-based algorithm using affine category shape model for object category recognition and model learning. Affine category shape model is a graph of interconnected nodes whose geometric interactions are modeled using pairwise potentials. In its learning phase, it can efficiently handle large pose variations of objects in training images by estimating 2-D homography transformation between the model and the training images. Since the pairwise potentials are defined on only relative geometric relationship betweenfeatures, the proposed matching algorithm is translation and in-plane rotation invariant and robust to affine transformation. We apply spectral matching algorithm to find feature correspondences, which are then used as initial correspondences for RANSAC algorithm. The 2-D homography transformation and the inlier correspondences which are consistent with this estimate can be efficiently estimated through RANSAC, and new correspondences also can be detected by using the estimated 2-D homography transformation. Experimental results on object category database show that the proposed algorithm is robust to pose variation of objects and provides good recognition performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권1호
• /
• pp.228-246
• /
• 2011

A 3D model based approach for a face representation and recognition algorithm has been investigated as a robust solution for pose and illumination variation. Since a generative 3D face model consists of a large number of vertices, a 3D model based face recognition system is generally inefficient in computation time and complexity. In this paper, we propose a novel 3D face representation algorithm based on a pixel to vertex map (PVM) to optimize the number of vertices. We explore shape and texture coefficient vectors of the 3D model by fitting it to an input face using inverse compositional image alignment (ICIA) to evaluate face recognition performance. Experimental results show that the proposed face representation and recognition algorithm is efficient in computation time while maintaining reasonable accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3924-3940
• /
• 2020

Dynamic hand gesture recognition(d-HGR) plays an important role in human-computer interaction(HCI) system. With the growth of hand-pose estimation as well as 3D depth sensors, depth, and the hand-skeleton dataset is proposed to bring much research in depth and 3D hand skeleton approaches. However, it is still a challenging problem due to the low resolution, higher complexity, and self-occlusion. In this paper, we propose a hand-shape feature extraction(HSFE) network to produce robust hand-shapes. We build a hand-shape model, and hand-skeleton based on LSTM to exploit the temporal information from hand-shape and motion changes. Fusion between two models brings the best accuracy in dynamic hand gesture (DHG) dataset.