• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.6
• /
• pp.39-45
• /
• 2017

Conventional Color-Based Face Recognition Methods are Sensitive to Illumination Changes, and there are the Possibilities of Forgery and Falsification so that it is Difficult to Apply to Various Industrial Fields. In This Paper, we propose a Face Recognition Method Based on LBP(Local Binary Pattern) using the Depth Images to Solve This Problem. Face Detection Method Using Depth Information and Feature Extraction and Matching Methods for Face Recognition are implemented, the Simulation Results show the Recognition Performance of the Proposed Method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.5
• /
• pp.1098-1103
• /
• 2007

This paper presents an automatic detection and removal method of red eye in a color image. The method detects initial red eye region based on redness and geometric feature, and extracts final red eye region considering local characteristics around the initial red eye region. Red eye fur the foal red eye region is removed by soft based removal method. In the experiments, the proposed method improved the red eye detection and removal results than that of Willamowski and Csurka[1].

• Journal of Korea Multimedia Society
• /
• v.11 no.6
• /
• pp.777-786
• /
• 2008

Human face avatar is important information in nowadays, such as describing real people in virtual world. In this paper, we have presented a face avatar creation and warping algorithm by using face feature analysis method, in order to detect face feature, we utilized local mean method based on facial feature appearance and face geometric information. Then detect facial candidates by using it's character in $YC_bC_r$ color space. Meanwhile, we also defined the rules which are based on face geometric information to limit searching range. For analyzing face feature, we used face feature points to describe their feature, and analyzed geometry relationship of these feature points to create the face avatar. Then we have carried out simulation on PC and embed mobile device such as PDA and mobile phone to evaluate efficiency of the proposed algorithm. From the simulation results, we can confirm that our proposed algorithm will have an outstanding performance and it's execution speed can also be acceptable.

• Korean Journal of Human Ecology
• /
• v.19 no.1
• /
• pp.149-156
• /
• 2010

TV news anchor woman's appearance, voice, expression, and clothing, etc., have an influence on the reliability of the article to be reported. Among these, clothing is the most crucial factor in forming an anchor woman's image, especially the clothing color factor. This study is aimed at providing the basic foundation for anchor woman when they select the clothing color by analyzing the clothing color image on the screen. For this purpose, the KBS and MBC 9 o'clock news desk and SBS 8 o'clock news of the local major news programs were selected. With the collection of 300 pieces of news clips related to anchor woman's clothing from January to December 2008, they were classified into F/W seasons and analyzed by the clothing color. The surveying method of clothing color was to capture the anchor woman's clothing among the news clips, then pick the representing color by applying Adobe Photoshop, and researching the formed $L^*a^*b^*$ value of color chips. The surveyed color was transformed into value of distant cell, H V/C, and the results were analyzed. As a result, it showed that the White system for anchor woman's clothing during the S/S seasons is most frequently picked, followed by the Red system. In F/W seasons, Gray system is the most favored, then White and Red, respectively. It was revealed that the most frequently selected colors for upper-wear by anchor women in the three broadcasting stations was an achromatic color, such as White or Gray, and then the chromatic color, Red. It shows that there is no big difference in season. The Inner-wear color matched the jackets which were also achromatic in color, white and black being the most favored in the S/S seasons, and in the case of chromatic colors, Red was the most favored. In addition to this, identical coloration with jacket, coloration with similar color, or single color as clothing color were no less frequently adopted. During the F/W seasons, identical coloration accounts for 26%, the most popular colored being White and Red. It was found that the coloration with achromatic colors are highly favored in the three major broadcasting stations alike.

• Korean Journal of Agricultural Science
• /
• v.15 no.1
• /
• pp.69-75
• /
• 1988

This experiment was carried out for the analysis of the ability of callus formation and differentiation in the eight Korean local varieties of adzuki beans (Phaseolus angularis). KLA 102 has the highest ability on the formation of callus (all tissues have 90 % over). Morphological heterogeneity (color and shape) of callus was well reflected to the cell constitution and cell meristematic activities. Meristemoid tissues and rooting were derived from only creamish-white color and soft region of callus.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.8
• /
• pp.3806-3825
• /
• 2016

This paper brings out a neoteric frame of reference for visual semantic based 3d video search and retrieval applications. Newfangled 3D retrieval application spotlight on shape analysis like object matching, classification and retrieval not only sticking up entirely with video retrieval. In this ambit, we delve into 3D-CBVR (Content Based Video Retrieval) concept for the first time. For this purpose we intent to hitch on BOVW and Mapreduce in 3D framework. Here, we tried to coalesce shape, color and texture for feature extraction. For this purpose, we have used combination of geometric & topological features for shape and 3D co-occurrence matrix for color and texture. After thriving extraction of local descriptors, TB-PCT (Threshold Based- Predictive Clustering Tree) algorithm is used to generate visual codebook. Further, matching is performed using soft weighting scheme with L₂ distance function. As a final step, retrieved results are ranked according to the Index value and produce results .In order to handle prodigious amount of data and Efficacious retrieval, we have incorporated HDFS in our Intellection. Using 3D video dataset, we fiture the performance of our proposed system which can pan out that the proposed work gives meticulous result and also reduce the time intricacy.

• Journal of Korea Multimedia Society
• /
• v.18 no.9
• /
• pp.1008-1018
• /
• 2015

In this paper, we propose a method that constructs a saliency map in which important regions are accurately specified and the colors of the regions are less influenced by the similar surrounding colors. Our method utilizes LBP(Local Binary Pattern) histogram information to compare and analyze texture information of surrounding regions in order to reduce the effect of color information. We extract the saliency of stereoscopic images by integrating a 2D saliency map with depth information of stereoscopic images. We then measure the distance between two different sizes of the LBP histograms that are generated from pixels. The distance we measure is texture difference between the surrounding regions. We then assign a saliency value according to the distance in LBP histogram. To evaluate our experimental results, we measure the F-measure compared to ground-truth by thresholding a saliency map at 0.8. The average F-Measure is 0.65 and our experimental results show improved performance in comparison with existing other saliency map extraction methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.11
• /
• pp.928-937
• /
• 2013

This paper presents a novel contrast enhancement method based on singular value decomposition and image pyramid. The proposed method consists mainly of four steps. The proposed algorithm firstly decomposes image into band-pass images, including basis image and detail images, to improve both the global contrast and the local detail. In the global contrast process, singular value decomposition is used for contrast enhancement; the local detail scheme uses weighting factors. In the final image composition process, the proposed algorithm combines color and luminance components in order to preserve the color consistency. Experimental results show that the proposed algorithm improves contrast performance and enhances detail compared to conventional methods.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.368-373
• /
• 2007

In recent year s there have been increasing interests in real-time object tracking with image information. This dissertation presents a real-time object tracking method through the object recognition based on neural networks that have robust characteristics under various illuminations. This dissertation proposes a global search and a local search method to track the object in real-time. The global search recognizes a target object among the candidate objects through the entire image search, and the local search recognizes and track only the target object through the block search. This dissertation uses the object color and feature information to achieve fast object recognition. The experiment result shows the usefulness of the proposed method is verified.

• Journal of Korean Institute of Industrial Engineers
• /
• v.26 no.4
• /
• pp.363-375
• /
• 2000

In this paper we propose a content-based image retrieval method that can search large image databases efficiently by color, texture, and shape content. Quantized RGB histograms and the dominant triple (hue, saturation, and value), which are extracted from quantized HSV joint histogram in the local image region, are used for representing global/local color information in the image. Entropy and maximum entry from co-occurrence matrices are used for texture information and edge angle histogram is used for representing shape information. Relevance feedback approach, which has coupled proposed features, is used for obtaining better retrieval accuracy. Simulation results illustrate the above method provides 77.5 percent precision rate without relevance feedback and increased precision rate using relevance feedback for overall queries. We also present a new indexing method that supports fast retrieval in large image databases. Tree structures constructed by k-means algorithm, along with the idea of triangle inequality, eliminate candidate images for similarity calculation between query image and each database image. We find that the proposed method reduces calculation up to average 92.9 percent of the images from direct comparison.