• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.598-608
• /
• 2020

In this paper, we propose a color correction technique for images acquired through a multi-view camera system for acquiring a 3D model. It is assumed that the 3D volume is captured indoors, and the position and intensity of the light is constant over time. 8 multi-view cameras are used, and converging toward the center of the space, so even if the lighting is constant, the intensity and angle of light entering each camera may be different. Therefore, a color optimization function is applied to a color correction chart taken from all cameras, and a color conversion matrix defining a relationship between the obtained 8 images is calculated. Using this, the images of all cameras are corrected based on the standard color correction chart. This paper proposed a color correction method to minimize the color difference between cameras when acquiring an image using 8 cameras of 3D objects, and experimentally proved that the color difference between images is reduced when it is restored to a 3D image.

• Journal of KIISE:Computing Practices and Letters
• /
• v.5 no.5
• /
• pp.628-638
• /
• 1999

In this paper, we presents a method of retrieving 24 bpp RGB images based on color-spatial features. For each image, it is subdivided into regions by using similarity of color after converting RGB color space to CIE L*u*v* color space that is perceptually uniform. Our segmentation algorithm constrains the size of region because a small region is discardable and a large region is difficult to extract spatial feature. For each region, averaging color and center of region are extracted to construct color-spatial features. During the image retrieval process, the color and spatial features of query are compared with those of the database images using our similarity measure to determine the set of candidate images to be retrieved. We implement a content-based color image retrieval system using the proposed method. The system is able to retrieve images by user graphic or example image query. Experimental results show that Recall/Precision is 0.80/0.84.

• 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

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.9C
• /
• pp.949-954
• /
• 2005

From the 90's, the image information retrieval methods have been on progress. As good examples of the methods, Conventional histogram method and merged-color histogram method were introduced. Dey could get good result in image retrieval. However, Conventional histogram method has disadvantages if the histogram is shifted as a result of intensity change. Merged-color histogram, also, causes more process so, it needs more time to retrieve images. In this paper, we propose an improved new method using Adaptive Color Histogram(ACH) in image retrieval. The proposed method has been tested and verified through a number of simulations using hundreds of images in a database. The simulation results have quickly yielded the highly accurate candidate images in comparison to other retrieval methods. We show that ACH's can give superior results to color histograms for image retrieval.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1677-1683
• /
• 2006

Color image segmentation is useful for fast retrieval in large image database. For that purpose, new image segmentation technique based on the probability of pixel distribution in the image is proposed. Color image is first divided into R, G, and B channel images. Then, pixel distribution from each of channel image is extracted to select to which it is similar among the well known probabilistic distribution function-Weibull, Exponential, Beta, Gamma, Normal, and Uniform. We use sum of least square error to measure of the quality how well an image is fitted to distribution. That P.d.f has minimum score in relation to sum of square error is chosen. Next, each image is quantized into 4 gray levels by applying thresholds to the c.d.f of the selected distribution of each channel. Finally, three quantized images are combined into one color image to obtain final segmentation result. To show the validity of the proposed method, experiments on some images are performed.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.684-688
• /
• 2009

In this paper, it proposes the technique to restore from a binary image in the color image. The color image is composed of three element images of red, green and blue. Therefore, the color image is first divided into a red, green, and blue element, and the Inverse Halftoning[2]$\sim$[4] is processed to each element images. Finally, each element images is collectively displayed. In that case, the Kalman filter was applied to the Inverse Halftoning for the restoration accuracy improvement of the image. As a result, it was possible to restore it in the color image as well as the time of a monochrome image. Moreover, the result that the restoration accuracy had improved even when which combining with the technique by using the Kalman filter for the Inverse Halftoning so far came out.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.795-796
• /
• 2006

Recently, blocking harmful contents such as adult images has been widely researched. However, most of adult image blocking methods use flush color model without shape information. In this paper, we present a new adult image blocking methods based on shape and color information. In the first step, the shape is considered. In the second step, adult images are detected using skin color model. Considering both shape and color, the detection rate can be increased. We evaluate adult image detection performance using sample images.

• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.25-27
• /
• 2009

This paper presents the stereoscopic conversion of flame images. The stereoscopic conversion is a technology that generates left and right images from a monoscopic image. Even though many conversion methods have been introduced and commercialized so far, the processing of flame images is relatively few. Such conventional methods are effectively used either real-time or off-line. However, the application of such schemes to special-effect images such as flame is hard to be applied. The proposed method is designed to convert a flame image into a stereoscopic image. Depth map of flame regions are produced based on the analysis of color models of flames. Experimental results tested on diverse flame image sets validates the effectiveness of the proposed method.

• Journal of Semiconductor Engineering
• /
• v.2 no.1
• /
• pp.125-129
• /
• 2021

As the interest of deep learning, techniques to control the color of images in image processing field are evolving together. However, there is no clear standard for color, and it is not easy to find a way to represent only the color itself like the color-palette. In this paper, we propose a novel color palette extraction system by chroma fine-tuning with reinforcement learning. It helps to recognize the color combination to represent an input image. First, we use RGBY images to create feature maps by transferring the backbone network with well-trained model-weight which is verified at super resolution convolutional neural networks. Second, feature maps are trained to 3 fully connected layers for the color-palette generation with a generative adversarial network (GAN). Third, we use the reinforcement learning method which only changes chroma information of the GAN-output by slightly moving each Y component of YCbCr color gamut of pixel values up and down. The proposed method outperforms existing color palette extraction methods as given the accuracy of 0.9140.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.504-507
• /
• 2009

Color chart area is automatically extracted in image that captured a crop such as fruits with the color chart, and an approximation formula is obtained for the change in feature value of the color indexes. Comparison is made with the color value of the crop area, and the growing degree is assessed according to the correlation. Using a compact PC equipped with the program, image of fruits is captured, and the output value obtained by the system is compared to the rating by expert. In the automatic recognition of the color chart out of doors, the complete color indexes is correctly acquired in 22 of 29 images. And indoors, they are correctly acquired in all of 34 images. In the color value judgment of the Japanese pear, indoors, 32 of 34 images is within 1.0 of the judgment error (compared the value read off by experts), the average error is about 0.5. These results indicate a practicable value.