• Journal of Periodontal and Implant Science
• /
• v.31 no.3
• /
• pp.501-511
• /
• 2001

Several indices have been developed that use bleeding and color changes as indicators of early gingival pathology. In the presence of gingivitis, vascular proliferation and reduction of keratinization owing to increase redness in gingiva. Descriptions of healthy gingiva are numerous, ranging from pale pink and coral pink to deep red and violet. This terms are not objective. Because of perception of color depends on a lot of factors such as light source, object, observer and so on. It is difficult to make an objective expression. Therefore the using of mechanical equipment is recommended to exclude these variables and observer's vias. The purpose of this study was to evaluate gingival color change after scaling & subgingival root planing. The other purpose of this study was to research the correlation of pocket depth, P.B.I. score and gingival color change. After photo-taking and storaging the image of gingival color into a computer, color change was examine with an image analysis program. Results were as follow; 1. Color of healed gingiva after scaling & subgingival root planing was significantly differ from color of inflamed gingiva(p<0.01). 2. Color of healed gingiva after scaling was similar to color of healed gingiva after subgingival root planing(p<0.05). 3. There was statistically significant correlation between color change of red component and pocket depth after scaling & subgingival root planing(p<0.01). 4. There was no correlation between color change of green, blue component and pocket depth after scaling & subgingival root planing(p<0.01). 5. There was statistically significant correlation between between color change of red component and P.B.I. score after scaling & subgingival root planing(p<0.01). 6. There was no correlation between color changes of green, blue component and P.B.I. score after scaling & subgingival root planing(p<0.01). 7. Increase of pocket depth and P.B.I. score were significantly correlated to the amount of color change(p<0.01). 8. P.B.I. score had a higher correlation with color change than pocket depth(p<0.01).

• International Journal of Contents
• /
• v.9 no.3
• /
• pp.9-14
• /
• 2013

In this paper, we will examine single face tracking algorithms with scaling function in a mobile device. Face detection and tracking either in PC or mobile device with scaling function is an unsolved problem. Standard single face tracking method with particle filter has a problem in tracking the objects where the object can move closer or farther from the camera. Therefore, we create an algorithm which can work in a mobile device and perform a scaling function. The key idea of our proposed method is to extract the average of skin color in face detection, then we compare the skin color distribution between the detected face and the tracking face. This method works well if the face position is located in front of the camera. However, this method will not work if the camera moves closer from the initial point of detection. Apart from our weakness of algorithm, we can improve the accuracy of tracking.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.1
• /
• pp.213-224
• /
• 2010

In this paper, we propose an algorithm both geometric correction using a grid point image and radiometric adaptive projection that dependent upon the luminance of the input image and that of the background. This method projects and captures the grid point image then calculates the geometrically corrected position by difference between the two images. Next, to compensate color, a corrected image is calculated by the ratio divided luminance of an input image by luminance of arbitrary surface. In addition, we found the scaling factor which controls the contrast to avoid clipping error. At this time, the scaling factor is dependent on mean image lightness when background is determined. Experimental results show that the proposed method achieves good performance and is able to reduce the perceived color clipping and artifacts, better approximating the projection on a white screen.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2000.06a
• /
• pp.54-61
• /
• 2000

A method and results of classification of 4 types metallic wear debris were presented by using their color features. The color image of wear debris was used (or the initial data, and the color properties of the debris were specified by HSI color model. Particle was characterized by a set of statistical features derived from the distribution of HSI color model components. The initial feature set was optimized by a principal component analysis, and multidimensional scaling procedure was used for the definition of classification plane. It was found that five features, which include mean values of H and S, median S, skewness of distribution of S and I, allow to distinguish copper based alloys, red and dark iron oxides and steel particles. In this work, a method of probabilistic decision-making of class label assignment was proposed, which was based on the analysis of debris-coordinates distribution in the classification plane. The obtained results demonstrated a good availability for the automated wear particle analysis.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.4
• /
• pp.124-130
• /
• 1996

A compensation method of color error resulting from dynamic range transformation of color image is propsoed. The color error is measured using the CIE L a b uniform color space, and the color image is compensated to minimize it. The color error is significant in the dark region of image, which is caused by the lunimance scaling factor is relatively large in that case. In the proposed method, we weight the luminance scaling factor corresponding to luminnce to minimize the error. Because the weighting factor depends on luminace distribution of image, a decisio method of weighting factor using histogram is also proposed.

• KSTLE International Journal
• /
• v.1 no.1
• /
• pp.34-42
• /
• 2000

A method and results of classification of four different metallic wear debris were presented by using their color features. The color image of wear debris was used far the initial data, and the color properties of the debris were specified by HSI color model. Particles were characterized by a set of statistical features derived from the distribution of HSI color model components. The initial feature set was optimized by a principal component analysis, and multidimensional scaling procedure was used fer the definition of a classification plane. It was found that five features, which include mean values of H and S, median S, skewness of distribution of S and I, allow to distinguish copper based alloys, red and dark iron oxides and steel particles. In this work, a method of probabilistic decision-making of class label assignment was proposed, which was based on the analysis of debris-coordinates distribution in the classification plane. The obtained results demonstrated a good availability for the automated wear particle analysis.

• Journal of The Institute of Information and Telecommunication Facilities Engineering
• /
• v.9 no.2
• /
• pp.73-79
• /
• 2010

The most popular technique for image retrieval in a heterogeneous collection of color images is the comparison of images based on their color histogram. The color histogram describes the distribution of colors in the color space of a color image. In the most image retrieval systems, the color histogram is used to compute similarities between the query image and all the images in a database. But, small changes in the resolution, scaling, and illumination may cause important modifications of the color histogram, and so two color images may be considered to be very different from each other even though they have completely related semantics. A new method of color feature representation based on the 3-dimensional RGB color map is proposed to improve the defects of the color histogram. The proposed method is based on the three 2-dimensional projection map evaluated by projecting the RGB color space on the RG, GB, and BR surfaces. The experimental results reveal that the proposed is less sensitive to small changes in the scene and that achieve higher retrieval performances than the traditional color histogram.

• Journal of information and communication convergence engineering
• /
• v.2 no.2
• /
• pp.123-127
• /
• 2004

The most popular technique for image retrieval in a heterogeneous collection of color images is the comparison of images based on their color histogram. The color histogram describes the distribution of colors in the color space of a color image. In the most image retrieval systems, the color histogram is used to compute similarities between the query image and all the images in a database. But, small changes in the resolution, scaling, and illumination may cause important modifications of the color histogram, and so two color images may be considered to be very different from each other even though they have completely related semantics. A new method of color feature representation based on the 3-dimensional RGB color map is proposed to improve the defects of the color histogram. The proposed method is based on the three 2-dimensional projection map evaluated by projecting the RGB color space on the RG, GB, and BR surfaces. The experimental results reveal that the proposed is less sensitive to small changes in the scene and that achieve higher retrieval performances than the traditional color histogram.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.262-264
• /
• 2002

In this paper we focused on the color representation prob1em based on fuzzy set theory. The main factor is the determination or computation of color membership function and color difference formula. The mathematical formula to calculate the color difference should generate a uniform color scaling, and due to this reason we adopted a CIELAB color- space as a fundamental feature space. With the help of the CIELAB color space we created a new color model, referred to fuzzy color model, which can represent the ambiguous characteristics underlying colors. Based on the proposed color difference formula between fuzzy colors, we could obtain the membership computation method of an arbitrary color for a given color family.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.12a
• /
• pp.53-56
• /
• 2000

본 논문에서는 컬러이미지의 스케일링(scaling)을 위해 경사투영방법을 사용하여 기본적인 보간방법, 최소자승근사(least square approximation)의 결과들과 비교하여 보았다. 경사투영방법은 최소의 근사오차(approximation error)를 제공하는 수직투영(orthogonal projection)방법과 유사한 결과를 제공하며 전처리 필터 디자인에 자유성을 부여하고, 좀 더 일반화된 형태의 보간 방법이다. 사용된 방법을 기본적인 보간법들과 비교하여 보았을 때 더 좋은 PSNR의 결과를 얻을 수 있었으며 최소자승근사 방법과 유사한 결과들을 얻을 수가 있었다.