• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.04a
• /
• pp.382-385
• /
• 2012

이 논문에서는 영상 검색(image retrieval) 및 영상 부류(image categorization)을 위하여 영상을 기술할 때 영상의 클레스(class)별로 서로 다른 주요 특징량(feature)에 가중치 를 주는 방법론을 제안한다. 기존에 연구되어온 영상의 특징량 벡터에 가중치를 주는 방식은 모든 영상 클레스에 대하여 동일하게 가중치를 적용하기 때문에 영상이 클레스별로 서로 다른 특징량이 중요하다는 성질을 이용할 수 없다. 영상이 클레 별로 서로 다른 특징량이 중요하다는 성질을 이용하기 위하여 영상의 클레스별로 특징량 벡터에 서로 다른 가중치 벡터(weight vector)를 학습하였다. 그 후 질의 영상(query image)이 입력되면, 기존의 영상 검색 프레임워크(framework)를 통해 데이터베이 스(database)로 부터 미리 정의된 서브 클레스(sub-class)의 수에 해당하는 영상부 집합(subset)을 만들었다. 그리고 영상부 집합의 특징량 벡터들에 클레스별로 각각 학습된 가중치 벡터를 적용하여 특징량 벡터들 간의 거리를 다시 계산하여 리랭킹(re-ranking)하였다. 이 방법론을 UKBench Dataset에 적용하여 실험을 해보았으며 가중치를 주기 전과 비교 하였을 때 더 높은 정확도를 보였다.

• International Journal of Computer Science & Network Security
• /
• v.23 no.5
• /
• pp.53-64
• /
• 2023

Early detection of endometrial carcinoma in uterus is essential for effective treatment. Endometrial carcinoma is the worst kind of endometrium cancer among the others since it is considerably more likely to affect the additional parts of the body if not detected and treated early. Non-invasive medical computer vision, also known as medical image processing, is becoming increasingly essential in the clinical diagnosis of various diseases. Such techniques provide a tool for automatic image processing, allowing for an accurate and timely assessment of the lesion. One of the most difficult aspects of developing an effective automatic categorization system is the absence of huge datasets. Using image processing and deep learning, this article presented an artificial endometrium cancer diagnosis system. The processes in this study include gathering a dermoscopy images from the database, preprocessing, segmentation using hybrid Fuzzy C-Means (FCM) and optimizing the weights using the Whale Optimization Algorithm (WOA). The characteristics of the damaged endometrium cells are retrieved using the feature extraction approach after the Magnetic Resonance pictures have been segmented. The collected characteristics are classified using a deep learning-based methodology called Long Short-Term Memory (LSTM) and Bi-directional LSTM classifiers. After using the publicly accessible data set, suggested classifiers obtain an accuracy of 97% and segmentation accuracy of 93%.

• Korean Institute of Interior Design Journal
• /
• v.20 no.1
• /
• pp.33-42
• /
• 2011

This study, by applying the experiential and psychological thought category of "impression" as the space design strategy for drawing out "sensitivity," aims to break down the psychological mechanism forming the image held by the subject, and based on such segmentation, seek and strategize an effective design methodology. The subject's memory, pure sensation, and movement sensation are set as the preceding determinants comprising the psychological mechanism of space impression. The control determinants for achieving activation of psychological effect are reinterpreted as the relations of memory-cognition, sensation-perception, and movement-sensation and categorized into a cognitive strategy based on association, metaphor and remembrance; a direct sensation strategy based on formation, superposition and transposition of sensation; and a sensation strategy of process-formation based on expectation organization and reversal, contraction and relaxation. Each strategy is achieved through the formal, material and structural control of architecture. As a restructuring of the design methodology that has been experientially applied, the strategy categorization is important in that, by presenting the usefulness and effect by strategy according to space experience, it makes concrete the basic data that are useful for designing experience of sensitivity.

• Journal of Korea Multimedia Society
• /
• v.13 no.12
• /
• pp.1786-1797
• /
• 2010

Automatic understanding of contents in document image is a very hard problem due to involvement with mathematically challenging problems originated mainly from the over-determined system induced by document segmentation process. In both academic and industrial areas, there have been incessant and various efforts to improve core parts of content retrieval technologies by the means of separating out segmentation related issues using semi-structured document, e.g., invoice,. In this paper we proposed classification models for text lines on invoice document in which text lines were clustered into the five categories in accordance with their contents: purchase order header, invoice header, summary header, surcharge header, purchase items. Our investigation was concentrated on the performance of machine learning based models in aspect of linear-discriminant-analysis (LDA) and non-LDA (logic based). In the group of LDA, na$\"{\i}$ve baysian, k-nearest neighbor, and SVM were used, in the group of non LDA, decision tree, random forest, and boost were used. We described the details of feature vector construction and the selection processes of the model and the parameter including training and validation. We also presented the experimental results of comparison on training/classification error levels for the models employed.

• Journal of Fashion Business
• /
• v.12 no.5
• /
• pp.39-53
• /
• 2008

Today is a 'high concept' era in which consumers make sensible consumption that shares a sensible bond with a brand. Therefore, it is important to analyze consumers' aesthetic awareness; namely, fashion feeling in the fashion industry. This study conducted research into a fashion design planning process according to a fashion feeling focusing on computer graphics suited to the 21st century digital trend. First, the study classified a fashion feeling with eight senses including elegance, classic, modern, mannish, sporty, avant-garde, ethnic, and romantic feelings. Second, the study made an image map, color map, material map, and style map with Adobe Photoshop CS3 by dividing a fashion planning process with a computer graphics program. Also, the study made a flat illustration with Adobe Illustrator CS3. Third, the study proposed the image map, color map, material map, style map, fashion illustration and flat illustration in the design planning process under the theme of the aforementioned eight fashion feelings.

• Journal of the Korean Society of Costume
• /
• v.63 no.5
• /
• pp.72-86
• /
• 2013

This research aims to analyze the expressive characteristics of the fashion illustration in various fashion products such as clothing, accessories, other fashion products, and magazine advertisements. Targeting 223 items of products that had adjoined fashion illustration from 2000 to 2008, which had been collected through from magazines and web sites using the fashion illustration expression categorization (expression technique drawing style, body expression, expression image, attaching method to product) based on the theoretical background and the general trends by products. In frequency analysis results, painting technique and graphic technique were of great importance in the expression technique, and shading drawing and contour drawing were of great importance over all product groups for the drawing style. In body expression, exaggerative expression was the highest; simple expression and realistic expression were of great importance over all product groups relatively. In particular, there was a very distinct difference by fashion products in expression image. Humor image has the most importance in fashion clothing and fashion accessories. Casual image is the most important in magazine advertisements, and feminine image is the most important for other fashion products. Lastly, in attaching method to products, finished goods printings made up the largest proportion over all products. In fashion clothing, textile printings was the highest in proportions. Stitch in fashion accessory, the original form of commodity in other fashion products. This study will become a very valuable source in fashion products development using fashion illustrations.

• The Journal of Korean Medicine
• /
• v.34 no.1
• /
• pp.52-68
• /
• 2013

Objectives: Hyungsang medicine (HM) is an inspection which emphasizes the relationships between pathological patterns and one's facial or bodily shape, color and movement. The purpose of this study was to review previously published study results of the HM. Methods: The authors reviewed a total of 51 HM-related studies published from 2000 to 2012 found on PubMed and various domestic Oriental medicine journals. Each study was classified into theoretical, diagnostic, or treatment-related category. Results: Theoretical studies were mostly based on the Nei-Ching and Dong-Eui-Bo-Gam texts, and dealt with differences in form between types such as masculine and feminine, the five organ image types, the four-type categorization of body essence, vital energy (Qi), mentality, and Blood, Gallbladder and Bladder, the four-type categorization of fish, bird, horse, and turtle types, and the six meridian types. Research on diagnosis has been performed on diagnostic characteristics of HM, correlation between HM and general coordinative manipulation (GCM), and Hyungsang medicine and ante-disease pattern (未病類型). Studies on treatments could largely be classified as treatments for specific diseases using certain acupuncture or herbal prescriptions based on HM. Treatments were mostly evaluated solely through subjective symptom improvement of patients. Conclusions: Our review results suggest that HM-related studies were focused on the constitutional characteristics and clinical utility of HM. To strengthen the theoretical basis of HM and its clinical utility, clinical trials including randomized, treatment-placebo and blind methods are needed.

• Journal of the Korean Society for information Management
• /
• v.19 no.3
• /
• pp.123-143
• /
• 2002

Developing good methods for image description and indexing is fundamental for successful image retrieval, regardless of the content of images. Researchers and practitioners in the field of image indexing have developed a variety of image indexing systems and methods with the consideration of information types delivered by images. Such efforts in developing image indexing systems and methods include Panofsky's levels of image indexing and indexing systems adopting different approaches such as thesauri-based approach, classification approach. description element-based approach, and categorization approach. This study investigated users' perception of the objectiveness of image indexing, especially the iconographical analysis of image information advocated by Panofsky. One of the best examples of subjectiveness and conditional-dependence of image information is emotion. As a result, this study dealt with visual emotional information. Experiments were conducted in two phases : one was to measure the degree of agreement or disagreement about the emotional content of pictures among forty-eight participants and the other was to examine the inter-rater consistency defined as the degree of users' agreement on indexing. The results showed that the experiment participants made fairly subjective interpretation when they were viewing pictures. It was also found that the subjective interpretation made by the participants resulted from the individual differences in terms of their educational or cultural background. The study results emphasize the importance of developing new ways of indexing and/or searching for images, which can alleviate the limitations of access to images due to the subjective interpretation made by different users.

• Journal of Multimedia Information System
• /
• v.7 no.1
• /
• pp.17-24
• /
• 2020

Rice (Oryza Sativa) is an important source of food for the people of our country, even though of world also .It is also considered as the staple food of our country and we know agriculture is the main source country's economy, hence the crop of Rice plays a vital role over it. For increasing the growth and production of rice crop, ground-breaking technique for the detection of any type of disease occurring in rice can be detected and categorization of rice crop diseases has been proposed in this paper. In this research paper, we perform comparison between two classifiers namely MDC and Bayes' classifiers Survey over different digital image processing techniques has been done for the detection of disease in rice crops. The proposed technique involves the samples of 200 digital images of diseased rice leaf images of five different types of rice crop diseases. The overall accuracy that we achieved by using Bayes' Classifiers and MDC are 69.358 percent and 81.06 percent respectively.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.402-404
• /
• 1998

최근 영상 정보를 저장하는 시스템의 급증으로, 영상의 특징 요소들의 유사성(similarity)에 근거하여 영상을 분류.검색하는 기술에 많은 관심을 보이고 있다. 본 논문에서는 칼라영상의 분류를 위해 기존의 N$\times$M-grams를 변형한 Color N$\times$M-grams를 제안한다. Color N$\times$M-grams는 영상의 칼라정보를 이용하여 영상고유의 구조 정보를 추출한 후 유사성을 측정하여 영상을 분류한다. 제안된 방법의 성능 평가를 위하여 39쌍의 Benchmark 영상을 사용하여 실험하였다. 실험결과, 제안한 Color N$\times$M-grams를 사용한 방법이 기존의 N$\times$M-grams를 사용하여 칼라 영상을 분류하는 방법보다 1순위로 분류되는 비율에 있어서 약 19% 더 좋은 결과를 보였다.