• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.417-420
• /
• 2006

Detection of faces on still color images with arbitrary backgrounds is attempted in this paper. The newly proposed method is invariant to arbitrary background, number of faces, scale, orientation, skin color, and illumination through the steps of color clustering, cluster scanning, sub-block processing, face area detection, and face verification. The sub-block method makes the proposed method invariant to the size and the number of faces in the image. The proposed method does not need any pre-training steps or a preliminary face database. The proposed method may be applied to areas such as security control, video and photo indexing, and other automatic computer vision-related fields.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.7
• /
• pp.1040-1046
• /
• 2015

This paper introduces GP(Genetic Programming) based color detection model for an object detection of humanoid robot vision. Existing color detection methods have used linear/nonlinear transformation of RGB color-model. However, most of cases have difficulties to classify colors satisfactory because of interference of among color channels and susceptibility for illumination variation. Especially, they are outstanding in degraded images from robot vision. To solve these problems, we propose illumination robust and non-parametric multi-colors detection model using evolution of GP. The proposed method is compared to the existing color-models for various environments in robot vision for real humanoid Nao.

• Korean Journal of Remote Sensing
• /
• v.27 no.2
• /
• pp.75-87
• /
• 2011

This paper presents a method for region-based building extraction from high resolution satellite images(HRSI) using integrated information of spectral and color invariant features without user intervention such as selecting training data sets. The purpose of this study is also to evaluate the effectiveness of the proposed method by applying to IKONOS and QuickBird images. Firstly, the image is segmented by the MSRG method. The vegetation and shadow regions are automatically detected and masked to facilitate the building extraction. Secondly, the region merging is performed for the masked image, which the integrated information of the spectral and color invariant features is used. Finally, the building regions are extracted using the shape feature for the merged regions. The boundaries of the extracted buildings are simplified using the generalization techniques to improve the completeness of the building extraction. The experimental results showed more than 80% accuracy for two study areas and the visually satisfactory results obtained. In conclusion, the proposed method has shown great potential for the building extraction from HRSI.

• Textile Coloration and Finishing
• /
• v.13 no.6
• /
• pp.397-404
• /
• 2001

The accurate representation of the colors of dyed fabric on a color CRT(cathode ray tube) screen is the basis for the automatic process in dyeing industry. In the former study, we had focused on the theoretically color matching method between CIE(International Commission on illumination) and RGB color coordinates, but In this study we tried simulating the colors obtained from fabrics on the color CRT by using experimental method. we obtained the following results. 1. We could simulate all of the color CRT by gamut mapping method, even though some of the KOSCOTE(Korea Standard Color of Textile) colors represented on the color CRT didn't exist in the region of color region 2. We could do conditional matching by CIE system, even though it was hard to do invariant matching the Red, Green, Blue phosphors of the color CRT because of the SPD(Spectral Power Distribution) which had been set up before. 3. We could simulate all the colors obtained from fabrics on the color CRT by matching those two color groups from KOSCOTE fabrics and color CRT using match algorithm and matching programs. 4. If we get over on obstacles by grafting CCM and CCK machines which have been used in educational and industrial areas by matching KOSCOTE with color CRT we will be able to invent color simulation system controled automatically.

• Textile Coloration and Finishing
• /
• v.13 no.6
• /
• pp.39-39
• /
• 2001

The accurate representation of the colors of dyed fabric on a color CRT(cathode ray tube) screen is the basis for the automatic process in dyeing industry. In the former study, we had focused on the theoretically color matching method between CIE(International Commission on Illumination) and RGB color coordinates, but In this study we tried simulating the colors obtained from fabrics on the color CRT by using experimental method. we obtained the following results. 1. We could simulate all of the color CRT by gamut mapping method, even though some of the KOSCOTE(Korea Standard Color of Textile) colors represented on the color CRT didn′t exist in the region of color region. 2. We could do conditional matching by CIE system, even though it was hard to do invariant matching the Red, Green, Blue phosphers of the color CRT because of the SPD(Spectral Power Distribution) which had been set up before. 3. We could simulate all the colors obtained from fabrics on the color CRT by matching those two color groups from KOSCOTE fabrics and color CRT using match algorithm and matching programs. 4. If we get over on obstacles by grafting CCM and CCK machines which have been used in educational and industrial areas by matching KOSCOTE with color CRT we will be able to invent color simulation system controled automatically.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.487-490
• /
• 1999

In this paper we propose an efficient content-based image retrieval method using the color and wavelet based features. The color features are extracted from color histograms of the global image and the wavelet based features are extracted from the invariant moments of the high-pass band image through the spatial-frequency analysis of the wavelet transform. The proposed algorithm, called color and wavelet features based query(CWBQ), is composed of two-step query operations for efficient image retrieval: the coarse level filtering operation and the fine level matching operation. In the first filtering operation, the color histogram feature is used to filter out the dissimilar images quickly from a large image database. The second matching operation applies the wavelet based feature to the retained set of images to retrieve all relevant images successfully. The experimental results show that the proposed algorithm yields more improved retrieval accuracy with computationally efficiency than the previous methods.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.1
• /
• pp.44-49
• /
• 2003

This paper describes a method of estimating miniature train location by color vision for development of an intelligent railway system model. In the teal world, to control trains automatically, GPS(Global Positioning System) is indispensable to determine the location of trains. A color vision system was used for estimating the location of trains in an indoor experiment. Two different rectangular color bars were attached to the top of each train as a means of identifying them. Several trains were detected where they were located on the track by color feature, geometric features and moment invariant, and tracked simultaneously. In the experiment the identity, location and direction of each train were estimated and transferred to the control computer using serial communication. Processing speed of up to 8 frames/sec could be achieved, which was enough speed for the real-time train control.

• Journal of Korea Multimedia Society
• /
• v.6 no.4
• /
• pp.594-600
• /
• 2003

In this paper, we propose a detection method for facial features in color images with various backgrounds and face poses. To begin with, the proposed method extracts face candidacy region from images with various backgrounds, which have skin-tone color and complex objects, via the color and edge information of face. And then, by using the elliptical shape property of face, we correct a rotation, scale, and tilt of face region caused by various poses of head. Finally, we verify the face using features of face and detect facial features. In our experimental results, it is shown that accuracy of detection is high and the proposed method can be used in pose-invariant face recognition system effectively

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.3
• /
• pp.23-34
• /
• 2001

• 한국지형공간정보학회:학술대회논문집
• /
• 2000.12a
• /
• pp.10-17
• /
• 2000