• The Journal of the Korea Contents Association
• /
• v.4 no.1
• /
• pp.18-23
• /
• 2004

In this paper, we propose a new visual feature extraction method for content-based image retrieval(CBIR) based on wavelet transform which has both spatial-frequency characteristic and multi-resolution characteristic. We extract visual features for each frequency band in wavelet transformation and use them to CBIR. The lowest frequency band involves spacial information of original image. We extract L feature vectors using fuzzy homogeneity in the wavelet domain, which consider both the wavelet coefficients and the spacial information of each coefficient. Also, we extract 3 feature vectors wing the energy values of high frequency bands, and store those to image database. As a query, we retrieve the most similar image from image database according to the 10 largest homograms(normalized fuzzy homogeneity vectors) and 3 energy values. Simulation results show that the proposed method has good accuracy in image retrieval using 90 texture images.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.3
• /
• pp.27-34
• /
• 2011

In this paper, the novel approach for image contrast enhancement is introduced. The method is based on the unsharp mask and directional information of images. Since the unsharp mask techniques give better visual quality than the conventional sharpening mask, there are much works on image enhancement using unsharp masks. The proposed algorithm decomposes the image to several blocks and extracts directional information using DCT. From the geometric properties of the block, each block is labeled as appropriate type and processed by adaptive unsharp mask. The masking process is skipped at the flat area to reduce the noise artifact, but at the texture and edge area, the adaptive unsharp mask is applied to enhance the image contrast based on the edge direction. Experiments show that the proposed algorithm produces the contrast enhanced images with superior visual quality, suppressing the noise effects and enhancing edge at the same time.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.8 no.5
• /
• pp.10-18
• /
• 2005

The research was carried out to define the morphological and growth characteristics of Poa pratensis L.(Kentucky bluegrass) 'Sewon' in native to Korea. Poa pratensis 'Sewon' was collected at the terrace land on the river in Guiman-ri, Cheongcheon-myeon, Goesan-gun, Chungcheongbuk-do on May 5, 1995. The collected Poa pratensis 'Sewon' was grown under non-mowing naturally growing condition. The morphological characteristics of Poa pratensis 'Sewon' are as follows. : The height of plant was 21.6cm but was increased to 33cm at the flowering time. The height of first node from the base was 5.0cm and the length and width of leaf were 9.6cm and 4.1cm, respectively. The length of inflorecences was 37.8cm and the length of a spike was 7.3cm. Based on these morphological characteristics, Poa pratensis 'Sewon' was defined to dwarf~medium and coarse texture type Kennturky bluegrass. 1 to 9 scale of visual quality, visual color and visual density were measured. Poa pratensis 'Sewon' showed best turf qualities among native Kentucky bluegrasses. In spring and fall growing season, Poa pratensis 'Sewon' were measured to be excellent performances for turf qulities similar to foreign excellent quality cultivars such as Midnight, Nuglade and Brilliant Kentucky bluegrasses. But turf quality of Poa pratensis 'Sewon' decreased by plant disease according to temperature increase in summe compared to foreign excellent quality cultivars. So, Poa pratensis 'Sewon' should be improved of disease tolerent quality by incessant breeding work in order to compete foreign excellent quality cultivars.

• Journal of Convergence for Information Technology
• /
• v.11 no.5
• /
• pp.267-275
• /
• 2021

Skin condition is an important concern in beauty aspect. This study considered a rough skin condition analysis method that beauty industry workers can do through visual observation or skin condition images taken with smartphones. First, studies that combine subjective and objective evaluations were selected among degree papers and academic papers searched by keywords related to 'skin condition' in the Research Information Sharing Service(RISS). Among them, papers that derive correlations with visually verifiable factors were selected. Next, the relationship between factors that match subjective skin condition and objective skin measurement results and factors that can be visually identified on the skin surface was investigated. According to the study, the most suitable factor for matching subjective and objective evaluations was 'oil volume', which is significantly related to 'pore', 'skin texture' and 'erythema', which can be visually checked on the skin surface. It is believed that a rough skin condition analysis will be possible using this.

• Journal of Korea Multimedia Society
• /
• v.17 no.9
• /
• pp.1076-1083
• /
• 2014

We propose an emotional facial avatar that portrays the user's facial expressions with an emotional emphasis, while achieving visual and behavioral realism. This is achieved by unifying automatic analysis of facial expressions and animation of realistic 3D faces with details such as facial hair and hairstyles. To augment facial appearance according to the user's emotions, we use emotional templates representing typical emotions in an artistic way, which can be easily combined with the skin texture of the 3D face at runtime. Hence, our interface gives the user vision-based control over facial animation of the emotional avatar, easily changing its moods.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.1173-1176
• /
• 2005

Depending on the characteristics of each 3D-DCT block, images can be classified into three types: images with motion and textures, images with high textures and little motion, images with little textures and little motion. In this paper, we propose an adaptive watermarking method using these characteristics of each 3D-DCT block. and the human visual system. The proposed method classifies patterns of 3D-DCT blocks based on the motion and texture information, and classifies the image type according to the ratio of these patterns. The watermark is inserted proportional to the 3D-DCT coefficients by using pattern adaptive JND, which. makes the proposed watermarking robust by inserting watermarks in as many blocks as possible. Experimental results show that the proposed method achieves better performance in terms of invisibility and robustness than the previous method.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.25 no.3
• /
• pp.537-547
• /
• 2001

The purpose of this study was to develop the measurement of the fashion sensibility. The stimulus were 91 photos selected in fashion magazines and had dominant visual power under detail, color, texture and pattern in the elements of fashion design. The semantic differential scale was constructed bipolar 25 pairs. The obtained data were analyzed by cluster analysis, factor analysis, ANOVA and t-test. The results were as follows; 1. The hierarchical structure was combined a natural and interesting, sensitive and lovely fashion sensibility. 2. The constructing factors of fashion sensibility were found out as aesthetic value, maturity, character and femininity·masculinity.(total variance: 55.7%) 3. Fashion sensibility by elements of fashion design was significantly different regarding all factors. 4. Fashion sensibility by demographic variables sex, age, marriage, education, occupation and expenditure was significantly different regarding partial factors.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.257-259
• /
• 2005

A crop management system was developed using Visual Basic and ArcGIS VBA. The system is operated on ArcGlS 8.3 with Microsoft Access MOB. Landsat +ETM, KOMPSAT-l EOC, ASTER VNIR and IKONOS panchromatic (pan) and multi-spectral (MIS) images were included in the system to understand what kind of agriculture-related information can be extracted for each images. Agriculture related data inventories using crop cover information such as texture and average pixel value of the crop based on cultivation calendar were designed ,and implemented. Three IKONOS images (May 25,2001, December 25,2001, October 23,2003) were loaded in the system to show crop cover characteristics such as rice, pear, grape, red pepper, garlic, and surface water cover of reservoir with field surveys. GIS layers such as DEM (Digital Elevation Model), stream, road, soil, land use and administration boundary were also supplied and can be overlaid with images to enhance the understanding the general agricultural characteristics and identifying the location easily.

• Journal of Korea Multimedia Society
• /
• v.8 no.6
• /
• pp.783-789
• /
• 2005

This paper is proposed a watermarking technique for copyright protection of multimedia contents. We proposed adaptive watermark detection algorithm using stochastic perceptual model and statistical decision method in DMWT(discrete multi wavelet transform) domain. The stochastic perceptual model calculates NVF(noise visibility function) based on statistical characteristic in the DMWT. Watermark detection algorithm used the likelihood ratio depend on Bayes' decision theory by reliable detection measure and Neyman-Pearson criterion. To reduce visual artifact of image, in this paper, adaptively decide the embedding number of watermark based on DMWT, and then the watermark embedding strength differently at edge and texture region and flat region embedded when watermark embedding minimize distortion of image. In experiment results, the proposed statistical decision method based on multiwavelet domain could decide watermark detection.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.193-197
• /
• 2006

본 연구는 감성 공학적 접근법을 사용하여, 벽지의 디자인 요소와 소비자의 감성과의 관계를 정량적으로 규명하는 것을 목표로 한다. 문헌조사, 인터뷰 전문가 의견 등을 종합하여, 총 13개의 주관적 감성 변수(6개의 시각적 변수, 7개의 촉각적 변수) 와 4개의 벽지 디자인 요소(color, texture pattern, embossing depth, gloss)들이 추출되었으며, 최종 목표 감성은 '고급감'으로 정하였다. 9점 척도와 100점 척도으로 구성된 설문지를 통하여, 28개의 샘플 벽지에 대해서 30명의 목표 고객들을 대상으로 감성 평가 실험을 실시하였고, 주성분 회귀 분석, 수량화 이론 등을 이용한 분석을 통하여, 소비자의 감성과 디자인 요소와의 관계를 정량적으로 분석했으며, 고급감을 향상시킬 수 있는 감성 변수 조합과 디자인 요소 조합을 규명하였다.