• Smart Media Journal
• /
• v.2 no.2
• /
• pp.14-19
• /
• 2013

Recently, due to the increase of the use of scanned images, the text segmentation techniques, which play critical role to optimize the quality of the scanned images, are required to be updated and advanced. In this study, an algorithm has been developed based on the modification of Gaussian mixture model (GMM) by integrating the calculation of Gaussian detection gradient and the estimation of the number clusters. The experimental results show an efficient method for text segmentation in natural scenes such as storefronts, street signs, scanned journals and newspapers at different size, shape or color of texts in condition of lighting changes and complex background. These indicate that our model algorithm and research approach can address various issues, which are still limitations of other senior algorithms and methods.

• Journal of the Korean Society of Costume
• /
• v.55 no.8 s.99
• /
• pp.144-153
• /
• 2005

The purpose of this study is to make a Web Color Data Base for practical design system for domestic fashion industry. The market segmentation was based on the results of the previous studies and the characteristics of fashion consumers. Finally, the 14,121 color samples are collected from the survey of 55 manufacturers of domestic fashion industry and 116 fashion brands of major department stores. These color samples are analyzed by the Munsell's H V/C and CIE L*a*b* value. The representative colors are selected concerning the density in CIE L*a*b* color space and the distance between the color samples. As a result, We suggested 2213 representative colors. Also, this color data was constructed on Web site. The data were sorted by the market, season and color code. In addition, the representative color sample book was made for the prototype of .

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.2
• /
• pp.48-55
• /
• 2008

In this paper we propose a novel method for image retrieval system using image segmentation and salient points. The proposed method consists of four steps. In the first step, images are segmented into several regions by JSEG algorithm. In the second step, for the segmented regions, dominant colors and the corresponding color histogram are constructed. By using dominant colors and color histogram, we identify candidate regions where objects may exist. In the third step, real object regions are detected from candidate regions by SIFT matching. In the final step, we measure the similarity between the query image and DB image by using the color correlogram technique. Color correlogram is computed in the query image and object region of DB image. By experimental results, it has been shown that the proposed method detects multi-object very well and it provides better retrieval performance compared with object-based retrieval systems.

• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1603-1613
• /
• 2017

This paper proposes a method for effectively segmenting the hand region using a widely popular RGB color-based webcam. This performs the empirical preprocessing method four times to remove the noise. First, we use Gaussian smoothing to remove the overall image noise. Next, the RGB image is converted into the HSV and the YCbCr color model, and global fixed binarization is performed based on the statistical value for each color model, and the noise is removed by the bitwise-OR operation. Then, RDP and flood fill algorithms are used to perform contour approximation and inner area fill operations to remove noise. Finally, ROI (hand region) is selected by eliminating noise through morphological operation and determining a threshold value proportional to the image size. This study focuses on the noise reduction and can be used as a base technology of gesture recognition application.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.5
• /
• pp.303-311
• /
• 2003

Since the MPEG-4 visual standard enables content-based functionalities, it is necessary to extract video object from natural video sequences. Segmentation algorithms can largely be classified into automatic segmentation and user-assisted segmentation. In this paper, we propose a user-assisted VOP generation method based on the geometric active contour. Since the geometric active contour, unlike the parametric active contour, employs the level set method to evolve the curve, we can draw the initial curve independent of the shape of the object. In order to generate the edge function from a smoothed image, we propose a vector-valued diffusion process in the LUV color space. We also present a discrete 3-D diffusion model for easy implementation. By combining the curve shrinkage in the vector field space with the curve expansion in the empty vector space, we can make accurate extraction of visual objects from video sequences.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.3
• /
• pp.1-8
• /
• 2022

Recently, Google MedeiaPipe presents a novel approach for neural network-based hair segmentation from a single camera input specifically designed for real-time, mobile application. Though neural network related to hair segmentation is relatively small size, it produces a high-quality hair segmentation mask that is well suited for AR effects such as a realistic hair recoloring. However, it has undesirable segmentation effects according to hair styles or in case of containing noises and holes. In this study, the energy function of the test image is constructed according to the estimated prior distributions of hair location and hair color likelihood function. It is further optimized according to graph cuts algorithm and initial hair region is obtained. Finally, clustering algorithm and image post-processing techniques are applied to the initial hair region so that the final hair region can be segmented precisely. The proposed method is applied to MediaPipe hair segmentation pipeline.

• The KIPS Transactions:PartB
• /
• v.13B no.7 s.110
• /
• pp.689-698
• /
• 2006

Pattern recognition is the study of how machines can observe the environment, learn to distinguish patterns of interest from their background, and make sound and reasonable decisions about the categories of the patterns. Color image consists of various color patterns. And most pattern recognition methods use the information of color which has been trained and extract the feature of the color. This thesis extracts adaptively specific color feature from images with several limited colors. Because the number of the color patterns is limited, the distribution of the color in the image is similar. But, when there are some noises and distortions in the image, its distribution can be various. Therefore we cannot extract specific color regions in the standard image that is well expressed in special color patterns to extract, and special color regions of the image to test. We suggest new method to reduce the error of recognition by extracting the specific color feature adaptively for images with the low distortion, and six test images with some degree of noises and distortion. We consequently found that proposed method shouws more accurate results than those of statistical pattern recognition.

• Journal of Biosystems Engineering
• /
• v.35 no.2
• /
• pp.138-145
• /
• 2010

An on-line algorithm that discriminates brown rice kernels on their echelon feeder using color image processing is presented for quality inspection. A rapid color image segmentation algorithm based on Bayesian clustering method was developed by means of the look-up table which was made from the significant clusters selected by experts. A robust estimation method was presented to improve the stability of color clusters. Discriminant analysis of color distributions was employed to distinguish nine types of brown rice kernels. Discrimination accuracies of the on-line discrimination algorithm were ranged from 72% to 85% for the sound, cracked, green-transparent and green-opaque, greater than 93% for colored, red, and unhulled, about 92% for white-opaque and 67% for chalky, respectively.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.651-654
• /
• 2000

본 논문에서는 칼라 영역으로 확장된 블록단위 영상분할 알고리듬을 제안한다. 즉, 기존의 휘도 성분을 기반으로 한 블록단위 알고리듬을 HSV 칼라 성분을 기반으로 하는 칼라 영상분할로 확장한다. 기존의 수학적 형태학(mathematical morphology)에 기반한 영상분할기법이나 블록단위 영상분할 기법들이 밝기 정보만을 활용했던 것에 대해 제안된 블록단위 영상분할 기법은 밝기뿐만이 아니라 칼라 성분도 고려하여 영상분할의 정확도를 향상시켰다. 실험의 결과 휘도 성분만을 고려한 영상분할 결과 보다 칼라 성분을 사용한 영상분할의 결과가 더 정확함을 알 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.532-534
• /
• 1998

본 논문에서는 칼라공간상의 거리와 이웃정보를 이용한 클러스터링을 통한 칼라영상 분할 방법을 제안한다. 영상의 픽셀들을 이웃관계를 유지하여 칼라공간으로 매핑한다. 칼라공간상에서 이웃하는 픽셀들을 클러스터링하여 영상의 세그먼트들을 찾는다. 클러스터링 방법으로서 인력을 모방하는 클러스터링(gravitational clustering)을 사용하였다. 이 방법으로 클러스터의 중심값과 클러스터 수를 미리 정해주지 않아도 자동적으로 결정할 수 있는 장점이 있다. gravitational 클러스터링에서 찾은 클러스터 수를 가지고 다른 클러스터링 방법에 입력으로 주어 결과를 비교해 본다. 본 논문에서는 이웃관계를 따라 클러스터링하는 것이 정확한 경계선을 찾는데 효과적임을 보여준다.