• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1831-1834
• /
• 2003

Due to the increasing of multimedia data quantity, database searching based on image becomes important. For this scheme, MPEG-7 gives a good solution to efficient data searching. MPEG-7 uses Descriptors which are color, texture, and shape to extract features from images. It is obvious that using more than one Descriptor causes more accurate data searching result than using just one. In this paper, selecting a composite of MPEG-7 visual Descriptor using KL-Expansion is proposed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.737-740
• /
• 2004

본 논문에서는 차종 식별을 위해 차량 영상의 질감 특징을 사용하였다. 차량의 질감 특징 정보를 얻기 위한 관심영역으로 라디에이터 그릴 부분을 선택하였다. 추출된 관심영역으로부터 GLCM(Gray Level Co-occurrence Matrix)을 사용하여 질감 특징 값을 추출하였고, 그 특징 값들을 입력으로 취하는 3층의 신경회로망을 구성한 후 역전파 학습 알고리즘을 사용하여 학습을 시켜서 차종 식별을 시도하였다.

• Journal of Korea Multimedia Society
• /
• v.4 no.1
• /
• pp.29-36
• /
• 2001

This paper proposes an efficient image description method for image retrieval using circular scanning pattern. Therefore, we place the origin of the circular scanning pattern on center point of an image and describe spatial color features of the image using the pattern. The features are Circular Dominant Color, Circular Color Texture, and Circular Color Variation Plot. By the method we can describe color and spatial information of the image at a time, efficiently. Therefore, we can reduce the computational expense and memory usage needed to index the image more than the conventional one does.

• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.3
• /
• pp.515-521
• /
• 2020

Deep learning methods have been effectively used to provide great improvement in various research fields such as machine learning, image processing and computer vision. One of the most frequently used deep learning methods in image processing is the convolutional neural networks. Compared to the traditional artificial neural networks, convolutional neural networks do not use the predefined kernels, but instead they learn data specific kernels. This property makes them to be used as feature extractors as well. In this study, we compared the quality of CNN features for traditional texture feature extraction methods. Experimental results demonstrate the superiority of the CNN features. Additionally, the recognition process and result of a pioneering CNN on MNIST database are presented.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.593-596
• /
• 1999

In this paper, we propose an image retrieval system using the MBCM(Modified Borda Count method) in CME(Combining Multiple Experts). It combines color-, shape- and texture-based retrieval sub-systems. CME method can complementarily combine results of each retrieval system, which uses different features. There are some problems when the Borda count method in pattern recognition is applied to image retrieval. Thus, we propose a modified Borda count method to solve these problems. In the experiment, our method reduces false positive errors and produces better results than that of each retrieval module that uses only one feature.

• ETRI Journal
• /
• v.34 no.5
• /
• pp.791-794
• /
• 2012

We propose an efficient framework to realistically render 3D faces with a reduced set of points. First, a robust active appearance model is presented to detect facial features in the projected faces under different illumination conditions. Then, an adaptive simplification of 3D faces is proposed to reduce the number of points, yet preserve the detected facial features. Finally, the point model is rendered directly, without such additional processing as parameterization of skin texture. This fully automatic framework is very effective in rendering massive facial data on mobile devices.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.6-8
• /
• 2007

In this paper, We propose reasoning system for object recognition and space classification using not only visual features but also contextual information. It is necessary to perceive object and classify space in real environments for mobile robot. especially vision based. Several visual features such as texture, SIFT. color are used for object recognition. Because of sensor uncertainty and object occlusion. there are many difficulties in vision-based perception. To show the validities of our reasoning system. experimental results will be illustrated. where object and space are inferred by bi -directional rules even with partial and uncertain information. And the system is combined with top-down and bottom-up approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3842-3855
• /
• 2018

A novel image completion method is proposed that uses the advantage of planar structural information to fill corrupted portions of an image. First, in estimating parameters of the projection plane, the image is divided into several planes, and their planar structural information is analyzed. Second, in calculating the a priori probability of patch and patch offset regularity, this information is converted into a constraint condition to guide the process of filling the hole. Experimental results show that the proposed algorithm is fast and effective, and ensures the structure continuity of the damaged region and smoothness of the texture.

• Proceedings of the KIEE Conference
• /
• 1987.11a
• /
• pp.311-315
• /
• 1987

This paper describes the automatic visual inspect ion system of fabric defects based on pattern recognition techniques. To extract features for detection of fabric defects, four different techniques such as SGLDM. GCM, decorrelation method, and Laws' texture measure were investigated. From results of computer simulation, it has been found that GCM and decorrelation techniques provide good features. By employing a simple statistical pattern recognition technique, theaccuracy of classification of defect and nondefect was more than 90%. Some experimental results arm also presented.

• Journal of International Society for Simulation Surgery
• /
• v.2 no.1
• /
• pp.7-9
• /
• 2015

Purpose In the many face-related application such as head pose estimation, 3D face modeling, facial appearance manipulation, the robust and fast facial feature extraction is necessary. We present the facial feature extraction method based on shape regression and feature selection for real-time facial feature extraction. Materials and Methods The facial features are initialized by statistical shape model and then the shape of facial features are deformed iteratively according to the texture pattern which is selected on the feature pool. Results We obtain fast and robust facial feature extraction result with error less than 4% and processing time less than 12 ms. The alignment error is measured by average of ratio of pixel difference to inter-ocular distance. Conclusion The accuracy and processing time of the method is enough to apply facial feature based application and can be used on the face beautification or 3D face modeling.