• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.10
• /
• pp.1535-1544
• /
• 2013

There are many Hangul input systems to input Korean letter on computer or smart phone. However, the existing systems need to be required more efforts to modify the already inputted letters. This research suggests the Hangul letter modification method which can modify letter effectively based on reusing the alphabets previously inputted. The Hangul modification system using "Jamo Modification Window" follows the composition principle of Hangul, and utilize the already inputted alphabets. It can be applicable to the existing input system without any modification using only "Jamo Modification Window". Especially, this system is very useful on smart phone with small screen.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.799-802
• /
• 2009

We have been studying the next generation of video creation solution based on TVML (TV program Making Language) technology. TVML is a well-known scripting language for computer animation and a TVML Player interprets the script to create video content using real-time 3DCG and synthesized voices. TVML has a long history proposed back in 1996 by NHK, however, the only available Player has been the one made by NHK for years. We have developed a new TVML Player from scratch and named it T2V (Text-To-Vision) Player. Due to the development from scratch, the code is compact, light and fast, and extendable and portable. Moreover, the new T2V Player performs not only a playback of TVML script but also a Text-To-Vision conversion from input written in XML format or just a mere plane text to videos by using 'Text-filter' that can be added as a plug-in of the Player. We plan to make it public as freeware from early 2009 in order to stimulate User-Generated-Content and a various kinds of services running on the Internet and media industry. We think that our T2V Player would be a key technology for upcoming new movement.

• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.511-521
• /
• 2011

As the use of image input and output devices increases, the importance of extracting text area in color images is also increasing. In this paper, in order to extract text area of the images efficiently, we present a text area extraction method for color images based on labeling and gradient difference method. The proposed method first eliminates non-text area using the processes of labeling and filtering. After generating the candidates of text area by using the property that is high gradient difference in text area, text area is extracted using the post-processing of noise removal and text area merging. The benefits of the proposed method are its simplicity and high accuracy that is better than the conventional methods. Experimental results show that precision, recall and inverse ratio of non-text extraction (IRNTE) of the proposed method are 99.59%, 98.65% and 82.30%, respectively.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.208-214
• /
• 2009

As an advance in medical technology development is being made, and people are increasingly aware of the importance of health, related investments and people's average life expectancy rise, which in turn leads to an increase in elderly people. Also, with a growing number of elderly people enjoying their leisure activities, the utilization of multimedia contents using computers is on the increase, leading to an activated research into the establishment of digital culture for the elderly people. This paper proposes a Korean text input system to enable the elderly to utilize digital contents. Text input interface has conventionally depended on keyboards. However, the keyboard wherein many keys are dispersed creates problems for the elderly, such as a protracted recognition of keys and a lowered concentration when they use the keyboard. To address these problems, in this paper, the grip type controller interface for console games was used and a corresponding alphabet location algorithm was developed. To verify these efforts, a simulator was developed to test 20 elderly people; as a result, their satisfaction over and convenience of using the grip type interface invreased.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.8
• /
• pp.703-710
• /
• 2003

Because of their human-like synthesized speech quality, recently Corpus-Based Text-To-Speech(CB-TTS) have been actively studied worldwide. However, due to their large size speech database (DB), their application is very restricted. In this paper we propose and evaluate three DB reduction algorithms to which are designed to solve the above drawback. The first method is based on a K-means clustering approach, which selects k-representatives among multiple instances. The second method is keeping only those unit instances that are selected during synthesis, using a domain-restricted text as input to the synthesizer. The third method is a kind of hybrid approach of the above two methods and is using a large text as input in the system. After synthesizing the given sentences, the used unit instances and their occurrence information is extracted. As next step a modified K-means clustering is applied, which takes into account also the occurrence information of the selected unit instances, Finally we compare three pruning methods by evaluating the synthesized speech quality for the similar DB reduction rate, Based on perceptual listening tests, we concluded that the last method shows the best performance among three algorithms. More than this, the results show that the last method is able to reduce DB size without speech quality looses.

• Journal of the Korean Society for information Management
• /
• v.29 no.2
• /
• pp.155-171
• /
• 2012

In text categorization, core terms of an input document are hardly selected as classification features if they do not occur in a training document set. Besides, synonymous terms with the same concept are usually treated as different features. This study aims to improve text categorization performance by integrating synonyms into a single feature and by replacing input terms not in the training document set with the most similar term occurring in training documents using Wikipedia. For the selection of classification features, experiments were performed in various settings composed of three different conditions: the use of category information of non-training terms, the part of Wikipedia used for measuring term-term similarity, and the type of similarity measures. The categorization performance of a kNN classifier was improved by 0.35~1.85% in $F_1$ value in all the experimental settings when non-learning terms were replaced by the learning term with the highest similarity above the threshold value. Although the improvement ratio is not as high as expected, several semantic as well as structural devices of Wikipedia could be used for selecting more effective classification features.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.152-159
• /
• 2010

Existing character recognition algorithm recognize characters in simple conditional. It has the disadvantage that recognition rates often drop drastically when input document image has low quality, rotated text, various font or size text because of external noise or data loss. In this paper, proposes the optical character recognition algorithm which using bicubic interpolation method for the catalog retrieval when the input image has rotated text, blurred, various font and size. In this paper, applied optical character recognition algorithm consist of detection and recognition part. Detection part applied roberts and hausdorff distance algorithm for correct detection the catalog of book. Recognition part applied bicubic interpolation to interpolate data loss due to low quality, various font and size text. By the next time, applied rotation for the bicubic interpolation result image to slant proofreading. Experimental results show that proposal method can effectively improve recognition rate 6% and search-time 1.077s process result.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.29-34
• /
• 2022

We propose a novel network architecture and build dataset for recognizing clickable objects on mobile device screens. The data was collected based on clickable objects on the mobile device screen that have numerous resolution, and a total of 24,937 annotation data were subdivided into seven categories: text, edit text, image, button, region, status bar, and navigation bar. We use the Deconvolution Single Shot Detector as a baseline, the backbone network with Squeeze-and-Excitation blocks, the Single Shot Detector layer structure to derive inference results and the Feature pyramid networks structure. Also we efficiently extract features by changing the input resolution of the existing 1:1 ratio of the network to a 1:2 ratio similar to the mobile device screen. As a result of experimenting with the dataset we have built, the mean average precision was improved by up to 101% compared to baseline.

• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.289-301
• /
• 2023

Due to the development and dissemination of modern technology, anyone can easily communicate using services such as social network service (SNS) through a personal computer (PC) or smartphone. The development of these technologies has caused many beneficial effects. At the same time, bad effects also occurred, one of which was the spam problem. Spam refers to unwanted or rejected information received by unspecified users. The continuous exposure of such information to service users creates inconvenience in the user's use of the service, and if filtering is not performed correctly, the quality of service deteriorates. Recently, spammers are creating more malicious spam by distorting the image of spam text so that optical character recognition (OCR)-based spam filters cannot easily detect it. Fortunately, the level of transformation of image spam circulated on social media is not serious yet. However, in the mail system, spammers (the person who sends spam) showed various modifications to the spam image for neutralizing OCR, and therefore, the same situation can happen with spam images on social media. Spammers have been shown to interfere with OCR reading through geometric transformations such as image distortion, noise addition, and blurring. Various techniques have been studied to filter image spam, but at the same time, methods of interfering with image spam identification using obfuscated images are also continuously developing. In this paper, we propose a deep learning-based spam image detection model to improve the existing OCR-based spam image detection performance and compensate for vulnerabilities. The proposed model extracts text features and image features from the image using four sub-models. First, the OCR-based text model extracts the text-related features, whether the image contains spam words, and the word embedding vector from the input image. Then, the convolution neural network-based image model extracts image obfuscation and image feature vectors from the input image. The extracted feature is determined whether it is a spam image by the final spam image classifier. As a result of evaluating the F1-score of the proposed model, the performance was about 14 points higher than the OCR-based spam image detection performance.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.11
• /
• pp.2946-2953
• /
• 1999

Finite automation is a mathematical model to represent a system with discrete inputs and outputs. Finite automata are a useful tool for solving problems such as text editor, lexical analyzer, and switching circuit. In this paper, given a deterministic finite automaton of an input string of length n and m states, we propose a constant time parallel algorithm that represents the transition states of finite automata and determines the acceptance of an input string on a reconfigurable mesh of size [nm/2]$\times$2m.