• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.195-199
• /
• 2008

We present an approach to detect real plane for line base recognition and pose estimation Given 3D line segments, we set up reference plane for each line pair and measure the normal distance from the end point to the reference plane. And then, normal distances are measured between remains of line endpoints and reference plane to decide whether these lines are coplanar with respect to the reference plane. After we conduct this coplanarity test, we initiate visibility test using z-buffer value to prune out ambiguous planes from reference planes. We applied this algorithm to real images, and the results are found useful for evidence fusion and probabilistic verification to assist the line based recognition as well as 3D pose estimation.

• Journal of Multimedia Information System
• /
• v.6 no.3
• /
• pp.119-124
• /
• 2019

In this paper, a method of detecting vehicle plates through depth pictures is proposed. A vehicle plate can be recognized by detecting the plane areas. First, plane factors of each square block are calculated. After that, the same plane areas are grouped by comparing the neighboring blocks to whether they are similar planes. Width and height for the detected plane area are obtained. If the height and width are matched to an actual vehicle plate, the area is recognized as a vehicle plate. Simulations results show that the recognition rates for the proposed method are about 87.8%.

• Journal of Korea Multimedia Society
• /
• v.15 no.4
• /
• pp.417-424
• /
• 2012

In this paper, we propose an automatic system that recognizes dynamic human gestures activity, including Arabic numbers from 0 to 9. We assume the gesture trajectory is almost in a plane that called principal gesture plane, then the Least Squares Method is used to estimate the plane and project the 3-D trajectory model onto the principal. An improved FNN model combined with HMM is proposed for dynamic gesture recognition, which combines ability of HMM model for temporal data modeling with that of fuzzy neural network. The proposed algorithm shows that satisfactory performance and high recognition rate.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.12C
• /
• pp.984-994
• /
• 2010

Pose variation is a critical problem in face recognition. Three-dimensional(3D) face recognition techniques have been proposed, as 3D data contains depth information that may allow problems of pose variation to be handled more effectively than with 2D face recognition methods. This paper proposes a pose-normalized 3D face modeling method that translates and rotates any pose angle to a frontal pose using a plane fitting method by Singular Value Decomposition(SVD). First, we reconstruct 3D face data with stereo vision method. Second, nose peak point is estimated by depth information and then the angle of pose is estimated by a facial plane fitting algorithm using four facial features. Next, using the estimated pose angle, the 3D face is translated and rotated to a frontal pose. To demonstrate the effectiveness of the proposed method, we designed 2D and 3D face recognition experiments. The experimental results show that the performance of the normalized 3D face recognition method is superior to that of an un-normalized 3D face recognition method for overcoming the problems of pose variation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.307-313
• /
• 2012

This paper proposes a hand-eye laser range finder (LRF) based welding plane recognition method for autonomous robotic welding. The robot welding is the process of joining a metal piece and the welding plane along the welding path predefined by the shape of the metal piece. Thus, for successful robotic welding, the position and direction of the welding plane should be exactly detected. If the detected position and direction of the plane is not accurate, the autonomous robotic welding should fail. For precise recognition of the welding plane, a line on the plane is detected by the LRF. For obtaining the line on the plane, the Hough transform is applied to the obtained data from the LRF. Since the Hough transform is based on the voting method, the sensor noise can be reduced. Two lines on the plane are obtained before and after rotation of the robot joint, and then the direction of the plane is calculated by the cross product of two direction vectors of two lines. For verifying the feasibility of the proposed method, the simulation with the robot simulator, RoboticsLab developed by Simlab Co. Ltd., is carried out.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.869-870
• /
• 2008

Illumination variation is the most significant factor affecting face recognition rate. In this paper, we propose adaptive smoothing based on combined most significant bit (CMSB) - plane and local entropy for robust face recognition in varying illumination. Illumination normalization is achieved based on Retinex method. The proposed method has been evaluated based on the CMU PIE database by using Principle Component Analysis (PCA).

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10a
• /
• pp.428-432
• /
• 1988

In this study, some issues on 3- dimentional object recognition and pose determination are discussed. The method employs a laser projector which projects a cyliderical light beam on the object plane where it produces a bright ring pattern. The picture is then taken by a T.V camera. The ring pattern is mathmetically the ellipse of which the geometrical parameters have the 3-dimentional feature of the object plane. This paper gives the mathematical aspects of 3-dimentional recognition method and shows experimentally the variations of ellipse parameters as the spatial deviation of the plane object.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.8
• /
• pp.1659-1665
• /
• 2009

In this paper, we propose an implementation method of 3D image correlator using integral imaging technique. In the proposed method, elemental images of the reference and signal 3D objects are recorded by lenslet arrays and then reference and signal output plane images with high resolution are optically reconstructed on the output plane by displaying these elemental images into a display panel. Through cross-correlations between the reconstructed reference and the single plane images, 3D object recognition is performed. The proposed method can provide a precise 3D object recognition by using the high-resolution output plane images compared with the previous methods and implement all-optical structure for real-time 3D object recognition system. To show the feasibility of the proposed method, optical experiments are carried out and the results are presented.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.388-393
• /
• 1992

An infrared range finder using a self-mixing laser diode (SM-LD), which has been proposed and developed by the Authors, can measure not only a range of a moving target but its velocity simultaneously. In this paper, described is that the precise mode-hop pulse train can be obtained by employing a new signal processing circuit even when the backscattered light returning into the SM-LD is much more weaker. As a result, the distance to a tilted square sheet made from aluminium or white paper, which is placed 10 cm through 60 cm from the SM-LD, is measured with accuracy of a few percent even when the tilting angle is less than 75 degrees or 85 degrees, respectively. And in this paper, described is the range-image recognition of a plane object under the condition of standstill. The output laser beam is scanned by scanning two plane mirrors-equipped with each stepping motor. And we succeeded in the acquisition of the range-image of a plane object in a few tens of seconds. Furthermore, described is a feasibility study about the range-image recognition of a slowly moving plane object.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1287-1292
• /
• 2005

This paper presents an effective pattern classification model by designing an artificial neural network based pattern classifiers for face recognition. First, a RGB image inputted from a frame grabber is converted into a HSV image which is similar to the human beings' vision system. Then, the coarse facial region is extracted using the hue(H) and saturation(S) components except intensity(V) component which is sensitive to the environmental illumination. Next, the fine facial region extraction process is performed by matching with the edge and gray based templates. To make a light-invariant and qualified facial image, histogram equalization and intensity compensation processing using illumination plane are performed. The finally extracted and enhanced facial images are used for training the pattern classification models. The proposed H-ART2 model which has the hierarchical ART2 layers and F-LVQ model which is optimized by fuzzy membership make it possible to classify facial patterns by optimizing relations of clusters and searching clustered reference patterns effectively. Experimental results show that the proposed face recognition system is as good as the SVM model which is famous for face recognition field in recognition rate and even better in classification speed. Moreover high recognition rate could be acquired by combining the proposed neural classification models.