• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권7호
• /
• pp.2633-2648
• /
• 2015

The problem of visual words' synonymy and ambiguity always exist in the conventional bag of visual words (BoVW) model based object category methods. Besides, the noisy visual words, so-called "visual stop-words" will degrade the semantic resolution of visual dictionary. In view of this, a novel bag of visual words method based on PLSA and chi-square model for object category is proposed. Firstly, Probabilistic Latent Semantic Analysis (PLSA) is used to analyze the semantic co-occurrence probability of visual words, infer the latent semantic topics in images, and get the latent topic distributions induced by the words. Secondly, the KL divergence is adopt to measure the semantic distance between visual words, which can get semantically related homoionym. Then, adaptive soft-assignment strategy is combined to realize the soft mapping between SIFT features and some homoionym. Finally, the chi-square model is introduced to eliminate the "visual stop-words" and reconstruct the visual vocabulary histograms. Moreover, SVM (Support Vector Machine) is applied to accomplish object classification. Experimental results indicated that the synonymy and ambiguity problems of visual words can be overcome effectively. The distinguish ability of visual semantic resolution as well as the object classification performance are substantially boosted compared with the traditional methods.

• 아동학회지
• /
• 제30권2호
• /
• pp.161-177
• /
• 2009

In this study of the relationship between preschoolers' visual perception and reading Hangul words, the 287 participants showed significant developmental change in visual perception between three to five years of age. The researcher developed the computer-based screening Test of Visual Perception for Reading (TVPR). Factor analysis confirmed three factors of TVPR : perception of number, direction, and form constancy. These factors correlated highly with four factors of motor-reduced visual perception of the Korean Developmental Test of Visual Perception (Moon et al. 2003). All factors of TVPR explained reading real words and pseudo words; direction and form constancy perception predicted reading low frequency letters. These findings confirm that preschoolers' skills in visual perception contribute to the reading of words in Hangul.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권1호
• /
• pp.364-380
• /
• 2016

The most popular approach in object classification is based on the bag of visual-words model, which has several fundamental problems that restricting the performance of this method, such as low time efficiency, the synonym and polysemy of visual words, and the lack of spatial information between visual words. In view of this, an object classification based on weakly supervised E2LSH and saliency map weighting is proposed. Firstly, E2LSH (Exact Euclidean Locality Sensitive Hashing) is employed to generate a group of weakly randomized visual dictionary by clustering SIFT features of the training dataset, and the selecting process of hash functions is effectively supervised inspired by the random forest ideas to reduce the randomcity of E2LSH. Secondly, graph-based visual saliency (GBVS) algorithm is applied to detect the saliency map of different images and weight the visual words according to the saliency prior. Finally, saliency map weighted visual language model is carried out to accomplish object classification. Experimental results datasets of Pascal 2007 and Caltech-256 indicate that the distinguishability of objects is effectively improved and our method is superior to the state-of-the-art object classification methods.

• 반도체디스플레이기술학회지
• /
• 제18권4호
• /
• pp.57-61
• /
• 2019

Nowadays, portable digital cameras such as smart phone cameras are being popularly used for entertainment and visual information recording. Given a database of geo-tagged images, a visual location recognition system can determine the place depicted in a query photo. One of the most common visual location recognition approaches is the bag-of-words method where local image features are clustered into visual words. In this paper, we propose a new bag-of-words-based visual location recognition algorithm using time-series streetview database. The proposed algorithm selects only a small subset of image features which will be used in image retrieval process. By reducing the number of features to be used, the proposed algorithm can reduce the memory requirement of the image database and accelerate the retrieval process.

• 한국의상디자인학회지
• /
• 제17권4호
• /
• pp.91-100
• /
• 2015

The purpose of this study is to analyze the style of check dresses shown in collections from 2011 to 2014 and to extract main expressional words for the development of semantic differential scales of visual images according to the change in silhouette of block check dresses. The results of this study are as follows: 1) 120 check dresses shown in collections were composed of 57 straight silhouette dresses, 38 fitted silhouette dresses, 23 hourglass silhouette dresses, 1 barrel silhouette dress, and 1 atypical silhouette dress. And check pattern mostly used in the current collections a square pattern of block check, tartan check that is a Scotch traditional lattice pattern, a small lattice pattern of gingham check, over check that other check patterns are arranged on check pattern, star-shaped hound tooth check, glen check mixing small pattern and big pattern. The visual image for check dress differs according to changes in the check pattern and silhouette of the dress. 2) Main expressional words of visual images for block check dresses differ greatly depending on the silhouette of dresses. The visual images are ranked in the order of 'graphic', 'simple', 'hard', 'modern' for straight silhouette of block check dresses. The words of 'lively', 'girlish', 'feminine', 'cute' are ranked for hourglass silhouette of block check dresses. And the words of 'confident', 'feminine', 'modern' are marked down for fitted silhouette of block check dresses.

• 패션비즈니스
• /
• 제13권6호
• /
• pp.137-146
• /
• 2009

This study analyzed hierarchy of image for visual evaluation of flare skirt. This study analyzed expression words about flare skirt with frequency data of image expression words with different length and volume of flare. Stimuli for the study were set to be 4 different volume of flare ($90^{\circ}$, $180^{\circ}$, $270^{\circ}$, $360^{\circ}$) and 3 different length of skirt(48cm, 58cm, 68cm). Stimuli were made by using I-Designer which is Virtual Sewing System. From simulation of flare skirt, the subjects were asked to write down suggested adjective freely and selected 210 adjectives. With this, we chose total 38 adjectives considering frequencies in the pre-study. And we analyzed the combination process of expression words according to construction factor of flare skirt and hierarchy of image from dendrogram which was resulted by hierarchical cluster analysis. 'Feminine' got high score in all 12 flare skirt. When the skirt was short, it was vivid, and as the skirt got longer, ordinary and pure image showed. Also, as the volume of flare got larger, the average of visual effect was higher than visual image. Visual hierarchy construction according to construction factors of flare skirt could be divided into visual image and visual effect, and visual image was shown to be form 'A type - large volume of flare and short skirt length', 'H type-small volume of flare and short skirt length' and 'X type - large volume of flare and long skirt length'.

• 한국의상디자인학회지
• /
• 제14권2호
• /
• pp.147-156
• /
• 2012

The purpose of this study is to analyze the style of wide pants shown in collections from 2008 to 2011 and to extract main expressional words for the development of semantic differential scales of visual images according to the change in silhouette of wide pants. The results of this study are as follows: 1) The wide pants which women wore in the 1970s were similar to men's. The aesthetic values for the wide pants included the social women's requests of the time. On the other hand, new wide pants shown in the current collections have diversified by adding designers' will to express contemporary women's tastes and fashion senses. 2) 742 wide pants shown in collections were composed of 459 straight, 147 bell-bottom and 136 flared pants. The design differs according to changes in the waist position and width of the wide pants. 3) Main expressional words of visual images for wide pants differ greatly depending on the silhouette of wide pants. The visual images are ranked in the order of 'showed that legs are long', 'looked taller', 'neat', 'relaxed', 'retro', 'modern' for straight pants. The words of 'retro', 'countrified', 'legs seemed to be long', 'enough' 'confident' 'looked like thighs that are slim' are ranked for bell-bottom pants. And the words of 'plentiful' 'loose', 'enough', 'retro' 'uncomfortable', 'relaxed', 'countrified' are marked down for flared pants.

• 대한한의진단학회지
• /
• 제15권3호
• /
• pp.235-244
• /
• 2011

Objectives: There are four types of diagnostic methods in Oriental medicine, and visual inspection is the first method among them. This study was written in order to complement further understanding on visual inspection. Methods: The authors reviewed a word related with visual inspection in Nei-Ching. The authors researched static words such as bigger/smaller, longer/shorter, slower/faster, curved/straight, one-sided/fair, and groove/uplift, and active words such as extension and contraction, shake, tremor, slow, fast, walk, run, standing, lying, and sitting related with visual inspection in Nei-Ching. Results: The static words linked with visual inspection are related with skin, muscles, fat, and especially the liver, stomach, and large intestine. The active words linked with visual inspection are related with movement of muscles, fat, and bone. Conclusion: In this study, the authors provided further understanding on visual inspection in Nei-Ching. However, there was no clear reference point about appearances and movements.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제3권12호
• /
• pp.547-552
• /
• 2014

플리커, 페이스북과 같은 대용량 소셜 미디어 공유 사이트의 발전으로 이미지 정보가 매우 빠르게 증가하고 있다. 이에 따라 소셜 이미지를 정확하게 검색하기 위한 다양한 연구가 활발히 진행되고 있다. 이미지 태그들의 의미적 연관성을 이용하여 태그기반의 이미지 검색의 정확도를 높이고자 하는 연구를 비롯하여 이미지 단어집(Bag of Visual Words)을 기반으로 웹 이미지를 분류하는 연구도 다양하게 진행되고 있다. 본 논문에서는 이미지에서 배경과 같은 중요도가 떨어지는 정보를 제거하여 중요부분을 찾는 GBVS(Graph Based Visual Saliency)모델을 기존 연구에 사용할 것을 제안한다. 제안하는 방법은 첫 번째, 이미지 태그들의 의미적 연관성을 이용해 1차 분류된 데이터베이스에 SIFT알고리즘을 사용하여 이미지 단어집(BoVW)을 만든다. 두 번째, 테스트할 이미지에 GBVS를 통해서 이미지의 관심영역을 선택하여 테스트한다. 의미연관성 태그와 SIFT기반의 이미지 단어집을 사용한 기존의 방법에 GBVS를 적용한 결과 더 높은 정확도를 보임을 확인하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2015년도 추계학술대회
• /
• pp.79-82
• /
• 2015

이미지를 분류하고 검색하는 기술(Image retrieval)중 하나인 Bag of visual words(BoVW)는 특징점(feature point)을 이용하는 방법으로 데이터베이스의 이미지 특징벡터들의 분포를 통해 쿼리 이미지를 자동으로 분류하고 검색해주는 시스템이다. Words를 구성하는데 특징벡터만을 이용하는 기존의 방법은 이용자가 원하지 않는 이미지를 검색하거나 분류할 수 있다. 이러한 단점을 해결하기 위해 특징벡터뿐만 아니라 이미지의 전체적인 분위기를 표현할 수 있는 색상정보나 반복되는 패턴 정보를 표현할 수 있는 텍스처 정보를 Words를 구성하는데 포함시킴으로서 다양한 검색을 가능하게 한다. 실험 부분에서는 특징정보만을 가진 words를 이용해 이미지를 분류한 결과와 색상정보와 텍스처 정보가 추가된 words를 가지고 이미지를 분류한 결과를 비교하였고 새로운 방법은 80~90%의 정확도를 나타내었다.