• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2108-2111
• /
• 2003

This paper introduces a new local feature extraction method and image matching method for the localization and classification of targets. Proposed method is based on the block-by-block projection associated with directional pattern of blocks. Each pattern has its own eigen-vertors called as CEBs(Classified Eigen-Blocks). Also proposed block-based image matching method is robust to translation and occlusion. Performance of proposed feature extraction and matching method is verified by the face localization and FLIR-vehicle-image classification test.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.2 no.4
• /
• pp.37-44
• /
• 2009

Stroke patients are the most in the cause of death among Koreans. Therefore, an accurate diagnosis of stroke is very important. But, it is the only way to diagnose strokes that the doctors see the MRI image and detect the pathological pattern. In this paper, we proposed the new method to detect the pathological pattern of a suspected stroke. We used the quasibi-symmetry of the MRI brain image in our new method. we detected pathological pattern applied the proposed method, and show the result.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.3
• /
• pp.168-173
• /
• 2011

In this paper, an optical image hiding technique using real-valued decoding key is proposed. In the embedding process, a each zero-padded original image placed in a quadrants on an input plane is multiplied by a statistically independent random phase pattern and is Fourier transformed. An encoded image is obtained by taking the real-valued data from the Fourier transformed image. And then a phase-encoded pattern, used as a hidden image and a decoding key, is generated by the use of multiple phase wrapping from the encoded images. A transmitted image is made from the linear superposition of the weighted hidden images and a cover image. In reconstruction process, the mirror reconstructed images can be obtained at two quadrants by the inverse-Fourier transform of the product of the transmitted image and the decoding key. Computer simulation and optical experiment are demonstrated in order to confirm the proposed technique.

• The Korean Fashion and Textile Research Journal
• /
• v.13 no.2
• /
• pp.147-154
• /
• 2011

The purpose of this study was to investigate the clothing image according to coloration, tone, and interval of checked pattern in color contrast. The experimental materials developed for this study were a set of stimulus and response scales. The stimuli were 24 color pictures, in which coloration(RB: Red+Blue, YP: Yellow+Purple), tone(light, dull, dark), and interval(0.5 cm, 1.5 cm, 3.5 cm, 5.5 cm) were manipulated. The 7-point scale was used for evaluation of clothing image. Data were obtained from 240 female college students living in Seoul, Gwangju, Jinju, and Masan on May 2010. For data analysis, ANOVA and Duncan-test were used by using SPSS program. Results of this study were as follows.; Clothing image according to coloration, tone, and interval of checked pattern consisted of five dimensions of attractiveness, freshness, appeal, modesty, and activity. Coloration showed an independent effect on attractiveness and appeal. Tone showed an independent effect on freshness, appeal, and modesty. Interval showed an independent effect on freshness. Also, interaction effects of coloration and tone on appeal were found. Interaction effects of coloration and interval on modesty were found.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.12 no.3
• /
• pp.133-143
• /
• 2010

The purpose of this study was to investigate the clothing image according to gender, coloration of chromatic and achromatic color, and interval of checked pattern. The experimental materials developed for this study were a set of stimulus and response scales. The stimuli were 16 color pictures, in which the gender(male, female), interval(0.5cm, 1.5cm, 3.5cm, 5.5cm), and coloration(WR: white+red, WY: white+yellow, WB: white+Blue, WP: white+purple) were manipulated. The 7-point scale was used for evaluation of clothing image. Data were obtained from 192 male college students and 192 female college students living in Seoul, Gwangju, Daegu, Jinju, and Changwon on March 2010. For data analysis, ANOVA and Duncan-test were used by using SPSS program. Results of this study were as follows.; Clothing image according to coloration of chromatic and achromatic color, and interval of checked pattern consisted of six dimensions of attractiveness, appeal, activity, freshness, modesty, and cuteness. Gender showed an independent effect on attractiveness, appeal, activity, freshness, and cuteness. Interval showed an independent effect on attractiveness. Coloration showed an independent effect on appeal, activity, freshness, modesty, and cuteness. Also, interaction effects of gender and coloration on freshness and cuteness were found.

• Journal of the Korean Society of Costume
• /
• v.60 no.6
• /
• pp.37-47
• /
• 2010

The purpose of this study was to investigate the effect of perceiver's gender, interval and color of checked pattern on clothing image. The experimental materials developed for this study were a set of stimulus and response scales. The stimuli were 16 color pictures, in which the perceiver's gender, interval(0.5cm, 1.5cm, 3.5cm, 5.5cm), and color(red, yellow, blue, purple) were manipulated. The 7-point scale was used for evaluation of clothing image. Data were obtained from 192 male college students and 192 female college students living in Seoul, Gwangju, Jinju, and Masan on December 2009. For data analysis, ANOVA and Duncan-test were used by using SPSS program. Results of this study were as follows.; Clothing image according to interval and color of checked pattern consisted of five dimensions of attractiveness, appeal, warmness, modesty, and freshness. Perceiver's gender showed an independent effect on appeal, modesty, and freshness. Interval showed an independent effect on appeal, warmness, modesty, and freshness. Also, interaction effects of Perceiver's gender and interval on appeal and freshness were found. Interaction effects of Perceiver's gender and color on appeal were found.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.35 no.8
• /
• pp.867-876
• /
• 2011

This study investigates the image of casual shirts according to color combination, tone, and interval of checked pattern in tone-in-tone coloration. The experimental materials developed for this study were a set of stimulus and response scales. The stimuli were 24 color pictures, in which color combination (RY: Red+Yellow, BP: Blue+Purple), tone (light, dull, dark), and interval (0.5cm, 1.5cm, 3.5cm, and 5.5cm) were manipulated. The 7-point scale was used for evaluation of image. Data were obtained from 240 female college students living in Seoul, Gwangju, Jinju, and Changwon in April 2010. For data analysis, ANOVA and Duncan-test were used by using SPSS program. The results of this study are as follows. Image according to color combination, tone, and interval of checked pattern consisted of five dimensions of attractiveness, youth- activity, appeal, modesty, and freshness. The cover combination showed an independent effect on freshness. Tone showed an independent effect on attractiveness, youth-activity, appeal, and modesty. Interval showed an independent effect on appeal, modesty, and freshness. Interaction effects of color combination and tone on youth-activity and appeal were found. In addition, interaction effects of tone and interval on attractiveness, youth-activity, and freshness were also found.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.6
• /
• pp.1253-1272
• /
• 2010

In this paper, we propose a new affine shape adaptation scheme for the affine invariant feature detector, in which the convergence stability is still an opening problem. This paper examines the relation between the integration scale matrix of next iteration and the current second moment matrix and finds that the convergence stability of the method can be improved by adjusting the relation between the two matrices instead of keeping them always proportional as proposed by previous methods. By estimating and updating the shape of the integration kernel and differentiation kernel in each iteration based on the anisotropy of the current second moment matrix, we propose a coarse-to-fine affine shape adaptation scheme which is able to adjust the pace of convergence and enable the process to converge smoothly. The feature matching experiments demonstrate that the proposed approach obtains an improvement in convergence ratio and repeatability compared with the current schemes with relatively fixed integration kernel.

• Korean Journal of Human Ecology
• /
• v.16 no.2
• /
• pp.407-419
• /
• 2007

The purpose of this study was to identify the effect of four clothing cues dot pattern size and ground field of color area ratio on dress's wearer image. The experimental materials developed for this study are a set of stimuli and response scales(The 7-point semantic). The stimuli were 30 color pictures manipulated with the combination of dot pattern size, dot pattern on background of color area ratio and neutral dress's using computer simulation. The subjects were 180 female undergraduates living students in Gyeong-nam. The result of this study are as follows: Image factor of the stimulus was composed of 5 different components (visibility, gracefulness, attractiveness, cuteness, womanly). Especially, Neutral color combination independently influenced the every components. In regarding the effect of interaction between each variable, the combination of dot pattern on background of color area ratio, dot pattern size on the combination had cuteness, womanly.

• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.283-290
• /
• 2005

The mismatched allocation of watermarking position due to parallel translation, rotation, and scaling distortion is a problem that requires an answer in watermarking. In this paper, we propose a watermarking method robust enough to hold against geometrical distorting using restoration pattern matching. The proposed method defines restoration pattern, then inserts the pattern to a watermark embedded image for distribution. Geometrical distortion is verified by comparing restoration pattern extracted from distributed image and the original restoration pattern inserted to the image. If geometrical distortion is found, inverse transformation is equally performed to synchronize the watermark insertion and extraction position. To evaluate the performance of the proposed method, experiments in translation, rotation, and scaling attack are performed.