• Journal of Digital Convergence
• /
• v.19 no.1
• /
• pp.307-314
• /
• 2021

This study aimed to apply the principle of the semantic network to a long novel in an attempt to understand the structure of the entire document and the manifested relationships between words and words. The costume expressions in Murakami's novel Norwegian Wood were analyzed based on the characters' symbols, relationships, and personality characteristics. The study identified the symbols of the characters in the novel and the relationship properties between the characters through the Clauset-Newman-Moore clustering algorithm. The descriptions and symbols of the relationships between the characters were identified within the worldview that the author had intended. Further, it was confirmed that the expression of each costume according to the character's personality was also connected to the clue that explained said character. This fusion study is academically significant in that it presents a new methodology for analyzing literary works

• Journal of Korea Multimedia Society
• /
• v.9 no.7
• /
• pp.872-893
• /
• 2006

In this study, I classify the elements of physiognomic judgment of character with regard to form and meaning from a visual perspective based on physiognomic judgment of character study in 'the cosmic dual forces and the Five Elements theory'. Individual characters for each type are designed using graphic data. Based on that, design system of individual characters for each personality type is investigated using Neural Network system. Faces with O-Haeng (Five Elements) shapes are shown to constitute the system with ${\pm}0.3%$ degree of error tolerance for the non-loaming input data. For the shapes of Chinese characters 'tree, fire, soil, gold and water', their MSE(Mean Square Error) are 0.3, 0.3, 0.2, 0.5, 0.2. It seems to be the best regarding the scoring system which ranges from 0 to 5. Therefore, this system might be regarded to produce the most accurate facial shape of character automatically when we input character's personality we desire to make.

• Journal of the Korean Society of Costume
• /
• v.65 no.7
• /
• pp.75-85
• /
• 2015

The purpose of this study is to examine ways to vitalize cause related marketing (CRM) by proposing character T-shirts The campaign will employ Neo-Pop art, a genre popular with both companies and consumers. Study results are as follows: First, campaign T-shirts on the issue of human alienation resulting from digitalization can be utilized to generate financial profit that can be returned to society. This can lead to the acts of exchange for profit generation, public image improvemen of companies, and enhancement of their external status. As for the non-financial aspect, the campaign could lead to increased awareness of social issues and present opportunities to take actions of improvement. Second, the financial objective of character T-shirts dealing with environmental issue of sustainability involves brand distribution network support and revitalization of promotion such as shopping basket of love and eco-friendly store matching program for eco-friendly campaign. As for the non-financial aspect, it can help raise consumers' awareness of cause related activities such as crowd funding and fundraising and prepare opportunities of direct participation. Third, the financial objective of character T-shirts dealing with natural disaster relief activities on the global level involves brand recognition level increase and enhancement of positive association of companies through emergency relief and articles support as a result of drastic increases in casualties from nature disasters. As for the non-financial aspect, it can induce people's participation in relief activities and lead to the establishment of crisis response procedures. The information on the development of pop-art character T-shirts proposed in this study is expected to be used as basic information on cause marketing of fashion companies in the future, while providing inspiration to related fashion design.

• Journal of Korea Multimedia Society
• /
• v.22 no.4
• /
• pp.455-462
• /
• 2019

This paper proposes a method of utilizing convolutional neural network to classify the images of Bender Gestalt Test (BGT), which is a tool to understand and analyze a person's characteristic. The proposed network is composed of 29 layers including 18 convolutional layers and 2 fully connected layers, where the network is to be trained with augmented images. To verify the proposed method, 10 fold validation was adopted. In results, the proposed method classified the images into 9 classes with the mean f1 score of 97.05%, which is 13.71%p higher than a previous method. The analysis of the results shows the classification accuracy of the proposed method is stable over all the patterns as the worst f1 score among all the patterns was 92.11%.

• Journal of Korea Society of Industrial Information Systems
• /
• v.5 no.1
• /
• pp.25-30
• /
• 2000

Hangul is regarded as one of the difficult character set due to the large number of classes and the shape similarity among different characters. Most of the conventional researches attempted to recognize the 2,350 characters which are popularly used, but this approach has a problem or low recognition performance while it provides a generality. On the contrary, recognition of a small character set appearing in specific fields like postal address or bank checks is more practical approach. This paper describes a research for recognizing the handwritten Hangul characters appearing in monetary fields. The modular neural network is adopted for the classification and three kinds of feature are tested. The experiment performed using standard Hangul database PE92 showed the correct recognition rate 91.56%.

• International Journal of Computer Science & Network Security
• /
• v.22 no.11
• /
• pp.121-126
• /
• 2022

The number of vehicles has increased exponentially over the past 20 years due to technological advancements. It is becoming almost impossible to manually control and manage the traffic in a city like Karachi. Without license plate recognition, traffic management is impossible. The Framework for License Plate Detection & Recognition to overcome these issues is proposed. License Plate Detection & Recognition is primarily performed in two steps. The first step is to accurately detect the license plate in the given image, and the second step is to successfully read and recognize each character of that license plate. Some of the most common algorithms used in the past are based on colour, texture, edge-detection and template matching. Nowadays, many researchers are proposing methods based on deep learning. This research proposes a framework for License Plate Detection & Recognition using a custom YOLOv5 Object Detector, image segmentation techniques, and Tesseract's optical character recognition OCR. The accuracy of this framework is 0.89.

• Journal of Korean Library and Information Science Society
• /
• v.4
• /
• pp.39-60
• /
• 1977

The purpose of this study is to build a model of inter-library cooperation's network in the information of library materials. Results of this study are 1. The YTational Assembly Library and the Central National I, ibrar:; should be unified. 2. The unified organization should be organized its cooperative quarter for itself (in the Central National Library). .And every library should he organized his quarter and personnel for the inter-library cooperation. 3. The cooperatior, organization in the re~ion should organized by the Regional Central Public Library. 4. In case of the Central National Library, financial problems required of the performance in the inter-library cooperation should he charged equally among the Central National Library, the library belong to the reader and the reader. In case of the regional Central Public Library, it should be charged equally arnozlg the regional Central Public Library, the library belon-g' to the reader and the reader. 5. The Regional Central Public Library in the seat of provincial government should be managed the cooperation's work of the individual library, and upward the unified Central Xarional Library should generalize. 6. The purchase of materials should be done by the character of the each library 1r:ith the assignment of the each subject should be decided in the meeting of the each library personne!. -2nd the budget for purchasing per the year should be decided on the minimum by the circumstances of the each library regionally. 7. The unified Regional Central Public Library in the seat of provincial government should be charged of the Union Catalog's expense regionally, and the Central National Library should be charged of that National Union Catalog's expense to cumulative the Fegional Union Catalog within a definite period of time. 8. Books without presentation of a specimen copy to the unified Central National Library should be purchased, and r.cr 'oe included to the National Union Catalog. 9. The cooperation of the each library should be decided on the law, and considered the character of the each region.

• International Commerce and Information Review
• /
• v.14 no.4
• /
• pp.563-582
• /
• 2012

In this paper, UPnP Network SaaS model has been studied. Currently, this model of UPnP Network and the trade mission is being used by outsourcing. From now on, the introduction of new trading systems and existing systems and the commercialization of this model as a UPnP network service connection should work. The future of UPnP network SaaS model will become commercially available software, commercial software can be accessed remotely via the Internet should be. Customer site activities must be managed from a central location. Application software architecture, pricing, partnerships, management should not include the character models. N should be the model. When used in small and medium enterprises have a very high value.

• Korean Journal of Health Education and Promotion
• /
• v.26 no.3
• /
• pp.35-48
• /
• 2009

Objectives: The community network is a foundation laid by the local community which has been formed historically and geographically to develop itself. This paper as a Korean way of healthy network survey for the community capacity building is an exploratory research to grasp the character of Korean society and then to organize an resident-governing partnership for that. Methods: Research objectives are CBOs(Community-Based Organizations) in S-district of Seoul. This region is a new town, however the solidarity and volunteerism of this resident is lively. The survey tool is Cho's CBOs Evaluation Questionnaire which was originated to measure the community capacity. The period of survey is from the January 2009 to the March 2009 and the study organizations which were collected by snowball sampling were 80. Results: The result shows two main networks: one is the civil society and craft union cluster, the other is welfare organization cluster. Groups of high centrality were organizations whose members are mainly women and craft organizations which were organized before 1990's. The group of high betweenness was the Association of Women's Organizations(0.188). Bi-components were six and they could be divided by organization's aim. In terms of the determinants of the participation to the health center enterprise, only the number of link(B=-0.60, p<0.04) was statistically significant. It means that when organization variables are controlled a tendency appears: the more the voluntary associations network, the less participation in the health enterprise. Conclusion: CBHOs(Community-Based Health Organizations) enhances residents' spontaneity and cohesion to increase the capability of the local community. If the surveyed healthy network, together the community health project, are used for various community development projects, the existing CBOs including CBHOs will be reorganized and furthered newly. For this it will be needed to construct an effective partnership of healthy network by restructuring the existing networks of voluntary associations.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.31A no.6
• /
• pp.61-69
• /
• 1994

For distortion-invariant recognition of Korean characters, a holographic implementation of an optical associative memory system is proposed. The structure of the proposed system is a single-layer neural network employing interconneclion matrix, thresholding and feedback. To provide the interconnection matrix, we use two CGII's which are placed on intermcdiate plane of cascaded Vander Lugt corrclators to form an optical memory loop. The holographic correlator stores reference images in a hologram and retrives them in a coherently illuminated feedback loop. An input image which maybe noisy or incomplete, is applicd to the system and simultaneously correlated optically with all of the stord images. These correlations are throsholed and fed back to the input, where the strongest correlation reinforces the input image. The enhanced image passes arround the loop repeatedly, approaching the stored image more closely on each pass until the system stabilizes on the desired image. The computer simulation results show that the proposed Korean Character recognition algorithm has high discrimination capability and noise immunity.