• Proceedings of the KAIS Fall Conference
• /
• 2006.11a
• /
• pp.220-224
• /
• 2006

The text to be included in the natural images has many important information in the natural image. Therefore, if we can extract the text in natural images, It can be applied to many important applications. In this paper, we propose a text region extraction method using pattern histogram of character-edge map. We extract the edges with the Canny edge detector and creates 16 kind of edge map from an extracted edges. And then we make a character-edge map of 8 kinds that have a character feature with a combination of an edge map. We extract text region using 8 kinds of character-edge map and 16 kind of edge map. Verification of text candidate region uses analysis of a character-edge map pattern histogram and structural feature of text region. The method to propose experimented with various kind of the natural images. The proposed approach extracted text region from a natural images to have been composed of a complex background, various letters, various text colors effectively.

• Computers and Concrete
• /
• v.10 no.4
• /
• pp.409-417
• /
• 2012

The quality of high performance concrete largely depends on water cement ratio, porosity, material composition and mix methods. The uniformity of color, texture and compressive strengths are quality indicators commonly used to assess the overall characteristics of concrete mixes. The homogeneity and share of coarse aggregates play a key role in concrete quality and must be analyzed in a microscopic point of view. This research studies the quality of high performance concrete by taking drilled cores in both horizontal and vertical directions from a 1.0 $m^3$ specimen. The coarse aggregate, expressed in digitized $100{\times}116$ dpi resolution images are processed based on brightness in colors through commercial software converted into text files. With the image converting to text format, the share of coarse aggregate is quantified leading to a satisfactory assessment of homogeneity - a quality index of high performance concrete. The compressive strengths of concrete and the shares of coarse aggregate of the samples are also compared in this research study to illustrate its correlation in concrete quality. It is concluded that a higher homogeneity of aggregate exists in the vertical plane than that of the horizontal planes of the high performance concrete. In addition, the concrete specimen showing denser particle packing has relatively higher compressive strengths. The research methodology provides an easy-to-use, direct measurement of high performance concrete when conducting quality assessment in the construction site.

• Journal of Information Technology Services
• /
• v.18 no.1
• /
• pp.153-171
• /
• 2019

Competition among cities has become fierce with decentralization and globalization, and each city tries to establish a brand image of the city to build its competitiveness and implement its policies based on it. At this time, surveys, expert interviews, etc. are commonly used to establish city brands. These methods are difficult to establish as sampling methods an empirical component, the biggest component of a city brand. In this paper, therefore, based on the precedent research's urban brand measurement and components, the words representing each city image property were extracted and relocated to five indicators to form the evaluation index. The constructed indicators have been validated through the review of three experts. Through the index, we analyzed the brands of four cities, Ulsan, Incheon, Yeosu, and Gyeongju, and identified the factors by using Topic Modeling and Word Cloud. This methodology is expected to reduce costs and monitor timely in identifying and analyzing urban brand images in the future.

• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.346-351
• /
• 2023

With the rapid development of Artificial Intelligence (AI) technology, there is an increasing variety of methods for creating 3D models. These include innovations such as text-only generation, 2D images to 3D models, and combining images with cue words. Each of these methods has unique advantages, opening up new possibilities in the field of 3D modeling. The purpose of this study is to explore and summarize these methods in-depth, providing researchers and practitioners with a comprehensive perspective to understand the potential value of these methods in practical applications. Through a comprehensive analysis of pure text generation, 2D images to 3D models, and images with cue words, we will reveal the advantages and disadvantages of the various methods, as well as their applicability in different scenarios. Ultimately, this study aims to provide a useful reference for the future direction of AI modeling and to promote the innovation and progress of 3D model generation technology.

• Journal of KIBIM
• /
• v.14 no.2
• /
• pp.13-24
• /
• 2024

This research suggests a novel visualization approach utilizing Generative AI to render photorealistic architectural alternatives images in the early design phase. Photorealistic rendering intuitively describes alternatives and facilitates clear communication between stakeholders. Nevertheless, the conventional rendering process, utilizing 3D modelling and rendering engines, demands sophisticate model and processing time. In this context, the paper suggests a rendering approach employing the text-to-image method aimed at generating a broader range of intuitive and relevant reference images. Additionally, it employs an Text-to-Image method focused on producing a diverse array of alternatives reflecting architects' styles when visualizing the exteriors of residential buildings from the mass model images. To achieve this, fine-tuning for architects' styles was conducted using the Low-Rank Adaptation (LoRA) method. This approach, supported by fine-tuned models, allows not only single style-applied alternatives, but also the fusion of two or more styles to generate new alternatives. Using the proposed approach, we generated more than 15,000 meaningful images, with each image taking only about 5 seconds to produce. This demonstrates that the Generative AI-based visualization approach significantly reduces the labour and time required in conventional visualization processes, holding significant potential for transforming abstract ideas into tangible images, even in the early stages of design.

• Imaging Science in Dentistry
• /
• v.30 no.1
• /
• pp.55-62
• /
• 2000

Purpose: This study was performed to develop the electronic textbook (CD-rom title) about preclinical practice of oral and maxillofacial radiology, using multimedia technology with interactive environment. Materials and Methods: After comparing the three authoring methods of multimedia, i.e. programming language, multimedia authoring tool and web authoring tool, we determined the web authoring tool as an authoring method of our electronic textbook. Intel Pentium II 350 MHz IBM-compatible personal computer with 128 Megabyte RAM, Umax Powerlook flatbed scanner with transparency unit, Olympus Camedia l400L digital camera, ESS 1686 sound card, Sony 8 mm Handycam, PC Vision 97 pro capture board, Namo web editor 3.0, Photoshop 3.0, ThumbNailer, RealPlayer 7 basic and RealProducer G2 were used for creating the text document, diagram, figure, X-ray image, video and sound files. We made use of javascripts for tree menu structure, moving text bar, link button and spread list menu and image map etc. After creating all files and hyperlinking them, we burned out the CD-rom title with all of the above multimedia data, Netscape communicator and plug in program as a prototype. Results and Conclusions : We developed the dental radiology electronic textbook which has 9 chapters and consists of 155 text documents, 26 figures, 150 X-ray image files, 20 video files, 20 sound files and 50 questions with answers. We expect that this CD-rom title can be used at the intranet and internet environments and continuous updates will be performed easily.

• The KIPS Transactions:PartB
• /
• v.11B no.7 s.96
• /
• pp.813-820
• /
• 2004

This paper proposes a digital image watermarking which is robust to geometric distortions using an independent component analysis(ICA) of fixed-point(FP) algorithm based on secant method. The FP algorithm of secant method is applied for better performance in a separation time and rate, and ICA is applied to reject the prior knowledges for original image, key, and watermark such as locations and size, etc. The proposed method embeds the watermark into the spatial domain of original image The proposed watermarking technique has been applied to lena, key, and two watermarks(text and Gaussian noise) respectively. The simulation results show that the proposed method has higher speed and better rate for extracting the original images than the FP algorithm of Newton method. And the proposed method has a watermarking which is robust to geometric distortions such as resizing, rotation, and cropping. Especially, the watermark of images with Gaussian noise has better extraction performance than the watermark with text since Gaussian noise has lower correlation coefficient than the text to the original and key images. The watermarking of ICA doesn't require the prior knowledge for the original images.

• Journal of Broadcast Engineering
• /
• v.25 no.3
• /
• pp.399-404
• /
• 2020

The Disaster text service is a text-based service for public alert. But, foreigners who are not familiar with korean can not understand exactly the disaster text messages provided. Using multimedia information such as images is expected to solve this problem. However, the current disaster message service method is not suitable for multimedia information delivery. This study proposes a firmware-based disaster character service method for displaying disaster image in a terminal. A device using this method should store images corresponding to the type of disaster and use special characters to inform the presentation of image in a terminal. This approach can be implemented in the new firmware installed device and it can be work with the existing device.

• The KIPS Transactions:PartB
• /
• v.12B no.4 s.100
• /
• pp.369-378
• /
• 2005

Document image is segmented and classified into text, picture, or table by a document layout analysis, and the words in table regions are significant for keyword spotting because they are more meaningful than the words in other regions. This paper proposes a method to extract words from table regions in document images. As word extraction from table regions is practically regarded extracting words from cell regions composing the table, it is necessary to extract the cell correctly. In the cell extraction module, table frame is extracted first by analyzing connected components, and then the intersection points are extracted from the table frame. We modify the false intersections using the correlation between the neighboring intersections, and extract the cells using the information of intersections. Text regions in the individual cells are located by using the connected components information that was obtained during the cell extraction module, and they are segmented into text lines by using projection profiles. Finally we divide the segmented lines into words using gap clustering and special symbol detection. The experiment performed on In table images that are extracted from Korean documents, and shows $99.16\%$ accuracy of word extraction.

• Smart Media Journal
• /
• v.5 no.3
• /
• pp.54-61
• /
• 2016

According to many smart devices are development, SNS(Social Network Service) users are getting higher that is possible for real-time communicating, information sharing without limitations in distance and space. Nowadays, SNS users that based on communication and relationships, are getting uses SNS for information sharing. In this paper, we used the SNS posts for users to extract the category and information provider, how to following of recommend method. Particularly, this paper focuses on classifying the words in the text of the posts and measures the frequency using Inception-v3 model, which is one of the machine learning technique -CNN(Convolutional Neural Network) we classified image word. By classifying the category of a word in a text and image, that based on DMOZ to build the information provider DB. Comparing user categories classified in categories and posts from information provider DB. If the category is matched by measuring the degree of similarity to the information providers is classified in the category, we suggest that how to recommend method of the most similar information providers account.