• 대한전자공학회논문지
• /
• 제27권5호
• /
• pp.757-766
• /
• 1990

In this paper a new knowledge based vision system using orientation information on each surface of the 3-dimensional object is discussed. The measurement of the orientation information is performed by photometric stereo method. And then the obtained orientations are segmented using Gaussian curvature and mean curvature. A hierarchical knowledge base which is based on the characteristics, shape, area and length of the surface is built up, and then the knowledge based system infers by the condition interprete system (CIS). As the results, an easier and more accurate 3-D object recognition system is implemented, because it uses the characteristics and shapes as units of the surface in the recognition process.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2000년도 춘계학술대회 논문집
• /
• pp.753-756
• /
• 2000

The accumulated know-how and trial-and-error procedures are known as the best ways to determine blank shape and dimensions. One of the most important steps to determine the blank shape and dimensions in deep drawing process is to calculate the surface area of the product. In general, the surface area of products is calculated by mathematical or 3-D modeling methods. A blank design system is constructed for elliptical deep drawing products to recognize the geometry of the product in the long side and short side by drafting in another two layers on AutoCAD software. This system consists of input geometry recognition module, 3-D modeling module and blank design module, respectively. Blank dimension of three types is determined by the same area, which was acquired in 3-D modeling module. The suitability of this system is verified by applying to a real deep drawing product.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권8호
• /
• pp.3136-3150
• /
• 2015

A vision-based 3D tracking of articulated human hand is one of the major issues in the applications of human computer interactions and understanding the control of robot hand. This paper presents an improved approach for tracking and recovering the 3D position and orientation of a human hand using the Kinect sensor. The basic idea of the proposed method is to solve an optimization problem that minimizes the discrepancy in 3D shape between an actual hand observed by Kinect and a hypothesized 3D hand model. Since each of the 3D hand pose has 23 degrees of freedom, the hand articulation tracking needs computational excessive burden in minimizing the 3D shape discrepancy between an observed hand and a 3D hand model. For this, we first created a 3D hand model which represents the hand with 17 different parts. Secondly, Random Forest classifier was trained on the synthetic depth images generated by animating the developed 3D hand model, which was then used for Haar-like feature-based classification rather than performing per-pixel classification. Classification results were used for estimating the joint positions for the hand skeleton. Through the experiment, we were able to prove that the proposed method showed improvement rates in hand part recognition and a performance of 20-30 fps. The results confirmed its practical use in classifying hand area and successfully tracked and recovered the 3D hand pose in a real time fashion.

• 한국멀티미디어학회논문지
• /
• 제25권3호
• /
• pp.546-557
• /
• 2022

Recently, the demand to interpret image data with artificial intelligence in various fields is rapidly increasing. Object recognition and detection techniques using deep learning are mainly used, and video integration analysis to determine unstructured object recognition is a particularly important problem. In the case of natural disasters or social disasters, there is a limit to the object recognition structure alone because it has an unstructured shape. In this paper, we propose intelligent video integration analysis system that can recognize unstructured objects based on video turning point and object detection. We also introduce a method to apply and evaluate object recognition using virtual augmented images from 2D to 3D through GAN.

• 한국인터넷방송통신학회논문지
• /
• 제11권3호
• /
• pp.75-81
• /
• 2011

단백질 분자는 포켓 위치에서 유사한 형상을 갖는 다른 분자와 결합되며, 포켓은 단백질 분자의 형상을 묘사하기 위한 참조 점으로 사용될 수 있다. Harris 검출기는 2 차원이나 3차원 객체의 특징 점을 검출하기 위해 널리 사용된다. 특징 점들은 데이터의 변화율이 높은 영역과 포켓 영역에서 발견된다. 일반적으로 포켓 영역은 함몰된 형태로 존재하기 때문에 이 영역에는 다른 영역에 비해 다수의 특징 점들이 존재한다. 특징 점들을 포함하는 voxel cube를 연속적으로 분할함으로써 포켓 영역을 발견할 수 있었고, 포켓 영역의 중심 좌표와 특징 점들 간의 Euclidean 거리를 계산한 후 이들을 크기순으로 정렬 하였다. 정렬된 거리에 대한 그래프는 단백질 분자의 형상과 특징 점들의 분포에 대한 정보를 제공하므로 단백질 분자를 형상별로 분리 할 수 있었다. 본 연구에서는 인위적인 잡음을 단백질 분자에 추가하여 형상이 왜곡된 분자를 얻었고, 왜곡된 분자에 대해서도 95 % 이상의 정확 도로 형상을 인식 할 수 있었다. 정확한 단백질 분자의 형상 인식은 분자들 간의 결합특성을 예측할 수 있는 중요한 정보를 제공한다.

• 한국통신학회논문지
• /
• 제24권8B호
• /
• pp.1500-1505
• /
• 1999

본 논문은 3물체 인식을 위한 깊이정보의 추출을 위해 스테레오 기법의 적용과 기존의 방법론에서 정합횟수에 대한 문제점을 보완하기 위한 물체의 진행 방향 벡터를 이용하는 방법론을 제안한다. 즉, 물체의 진행 방향을 이용하여 진행방향 벡터를 구하고 이를 축으로 회전 이동된 물체를 정합 시킨다. 그리고 Hough변환을 이용하여 얻은 회전 이동에 대응하는 2차원 합성영상을 참조영상으로 설정하고 입력영상과 정합 과정을 수행하였다.

• Journal of Multimedia Information System
• /
• 제6권1호
• /
• pp.15-22
• /
• 2019

There are many ways to perform face recognition. The first step of face recognition is the face detection step. If the face is not found in the first step, the face recognition fails. Face detection research has many difficulties because it can be varied according to face size change, left and right rotation and up and down rotation, side face and front face, facial expression, and light condition. In this study, facial features are extracted and the extracted features are geometrically reconstructed in order to improve face recognition rate in extracted face region. Also, it is aimed to adjust face angle using reconstructed facial feature vector, and to improve recognition rate for each face angle. In the recognition attempt using the result after the geometric reconstruction, both the up and down and the left and right facial angles have improved recognition performance.

• 한국통신학회논문지
• /
• 제21권7호
• /
• pp.1633-1641
• /
• 1996

In this paper we propose a new method for anlayzing the properties of surface reflectance and reconstructing the shape of object using estimated reflectance parameters. We have investigated the hybrid reflectance surface which has specularreflection and diffuse reflection, which can be explained by Torrance-Sparrow model. Sample sphere made on one maerial is used to estimate the reflectance properties by using LMS algorithm. We can make the reference image which consists of surface normal and brightness value using estimated reflectance parameters, and thenarbitrary shape object made of the same material as sample can be reconstructed by matching with reference image. Photometric matching method proposed in this paper is robust because it mateches object image with the reference imageconsidering its neighbor brightness distribution. Also, in this paper plate diffuse illumination is used to remove intensity disparity with simple scheme. It is expected that the proposed algorithm can be applied to 3D recognition, vision inspection system and other fields.

• 한국멀티미디어학회논문지
• /
• 제20권12호
• /
• pp.1890-1900
• /
• 2017

Tangram game consists of seven pieces of polygons such as triangle, square, and parallelogram. Typical methods of image processing for object recognition may suffer from the existence of side thickness and shadow of the puzzle pieces that are dependent on the pose of 3D-shaped puzzle pieces and the direction of light sources. In this paper, we propose an image processing method that recognizes simple convex polygon-shaped objects irrespective of thickness and pose of puzzle objects. Our key algorithm to remove the thick side of piece of puzzle objects is based on morphological operations followed by logical operations with edge image and background image. By using the proposed object recognition method, we are able to implement a stable tangram game applications designed for tablet computers with front camera. As the experimental results, recognition rate is about 86 percent and recognition time is about 1ms on average. It shows the proposed algorithm is fast and accurate to recognize tangram blocks.

• 사상체질의학회지
• /
• 제18권2호
• /
• pp.34-40
• /
• 2006

1. Objectives We are going to develope 3D Face Recognition Apparatus to analyse the facial characteristics of the Sasangin. In the process, we should identify the recognition rate of the three dimensional position using this Apparatus. 2. Methods We took a photograph of calibrator($280{\times}400mm$) with interval of 20mm longitudinal direction of 10 times using 3D Face Recognition Apparatus. In the practice, we obtained 967 point to the exclusion of points deviating from the visual field of dual camera. And we made a comparison between measurement values and three dimensional standard values to calculate the errors. 3. Results and Conclusions In this test, the average error rate of X axis values was 0.019% and the maximum error rate of X axis values was 0.033%, the average error rate of Y axis values was 0.025% and the maximum error rate of Y axis values was 0.044%, the average error rate of Z axis values was 0.158% and the maximum error rate of Z axis values was 0.269%. This results exhibit much improvement upon the average error rate 1% and the maximum error rate 2.242% of the existing 3D Recognition Apparatus. In conclusion, we assessed that this apparatus was adaptable to abstract the facial characteristic point from three dimensional face shape in the mechanical aspects.