• International Journal of Contents
• /
• v.11 no.2
• /
• pp.1-8
• /
• 2015

In this paper, we describe a novel method for document layout analysis that is based on a Fuzzy Energy Matrix (FEM). A FEM is a two-dimensional matrix that contains the likelihood of text and non-text and is generated through the use of Fuzzy theory. The key idea is to define an Energy map for the document to categorize text and non-text. The proposed mechanism is designed for execution with a low-resolution document image, and hence our method has a fast processing speed. The proposed method has been tested on public ICDAR 2009 datasets to conduct a comparison against other state-of-the-art methods, and it was also tested with Korean documents. The results of the experiment indicate that this scheme achieves superior segmentation accuracy, in terms of both precision and recall, and also requires less time for computation than other state-of-the-art document image analysis methods.

• East Asian mathematical journal
• /
• v.37 no.5
• /
• pp.599-612
• /
• 2021

In China, Weibo is one of the social platforms with more users. It has the characteristics of fast information transmission and wide coverage. People can comment on a certain event on Weibo to express their emotions and attitudes. Judging the emotional tendency of users' comments is not only beneficial to the monitoring of the management department, but also has very high application value for rumor suppression, public opinion guidance, and marketing. This paper proposes a two-input Adaboost model based on TextCNN and BiLSTM. Use the TextCNN model that can perform local feature extraction and the BiLSTM model that can perform global feature extraction to process comment data in parallel. Finally, the classification results of the two models are fused through the improved Adaboost algorithm to improve the accuracy of text classification.

• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.8
• /
• pp.319-326
• /
• 2007

To perform fast searching in massive data such as DNA strings, the most efficient method is to construct full-text index data structures of given strings. The widely used full-text index structures are suffix trees and suffix arrays. Since the suffix may uses less space than the suffix tree, the suffix array is proper for DNA strings. Previously developed construction algorithms of suffix arrays are not suitable for DNA strings since those are designed for integer alphabets. We propose a fast algorithm to construct suffix arrays on DNA strings whose alphabet sizes are fixed by 4. We reduce the construction time by improving encoding and merging steps on Kim et al.[1]'s algorithm. Experimental results show that our algorithm constructs suffix arrays on DNA strings 1.3-1.6 times faster than Kim et al.'s algorithm, and also for other algorithms in most cases.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.161-167
• /
• 2019

Recently, the amount of created information has been rising rapidly by dissemination of state of the art and developing of the various web service based on ICT. In additionally, the user has to need a lot of times and effort to find the necessary information which is the user want to know it in the mount of information. Document summarization is the technique that making and providing the summary of given document efficiently by analyzing and extracting the key sentences and words. However, it is hard to apply the previous of word embedding technique to the document which is composed by korean language for analyzing contents in the document due to the character of language. In this paper, we propose the new query-focused korean document summarization by exploiting word embedding technique such as Word2Vec and FastText, and then compare the both result of performance.

• 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.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.865-868
• /
• 2007

Web service in operating environment independent XML about under using, It dose so, Integration of the platform for it is different each other possibly it is doing. But XML in order to have the text data which is unnecessary plentifully with wireless Internet or the mobile communication modem in together relatively will connect frequently slow communication medium and there is a problem point which decreases the case prerequisite efficiency which the resources will use from the limited small-sized machinery and tools. Hereupon XML about under make binary the standard which reduces the size of the document from ITU-T and ISO/IEC it was under proposing with commonness, currently binary XML encoding where it is in the process of advancing standard there are Fast Infoset and Fast Schema. In this paper, implementation of Fast XML encoding system through introduction Fast Infoset algorithm and Fast Schema algorithm for web services increase performance.

• Phonetics and Speech Sciences
• /
• v.13 no.4
• /
• pp.47-53
• /
• 2021

Autoregressive Text-to-Speech (TTS) models suffer from inference instability and slow inference speed. Inference instability occurs when a poorly predicted sample at time step t affects all the subsequent predictions. Slow inference speed arises from a model structure that forces the predicted samples from time steps 1 to t-1 to predict the sample at time step t. In this study, an end-to-end non-autoregressive fast text-to-speech model is suggested as a solution to these problems. The results of this study show that this model's Mean Opinion Score (MOS) is close to that of Tacotron 2 - WaveNet, while this model's inference speed and stability are higher than those of Tacotron 2 - WaveNet. Further, this study aims to offer insight into the improvement of non-autoregressive models.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.4 s.42
• /
• pp.55-60
• /
• 2006

The proposed method uses FFT(Fast Fourier Transform) and neural networks in order to extract texts in real time. In general, text areas are found in the higher frequency domain, thus, can be characterized using FFT. The neural network are learned by character region(high frequency) and non character region(low frequency). The candidate text areas can be thus found by applying the higher frequency characteristics to neural network. Therefore, the final text area is extracted by verifying the candidate areas. Experimental results show a perfect candidate extraction rate and about 95% text extraction rate. The strength of the proposed algorithm is its simplicity, real-time processing by not processing the entire image.

• International Journal of Computer Science & Network Security
• /
• v.21 no.2
• /
• pp.229-237
• /
• 2021

Our modern 'information-hungry' age demands delivery of information at unprecedented fast rates. Timely delivery of noteworthy information about recent events can help people from different segments of life in number of ways. As world has become global village, the flow of news in terms of volume and speed demands involvement of machines to help humans to handle the enormous data. News are presented to public in forms of video, audio, image and text. News text available on internet is a source of knowledge for billions of internet users. Urdu language is spoken and understood by millions of people from Indian subcontinent. Availability of online Urdu news enable this branch of humanity to improve their understandings of the world and make their decisions. This paper uses available online Urdu news data to train machines to automatically categorize provided news. Various machine learning algorithms were used on news headline for training purpose and the results demonstrate that Bernoulli Naïve Bayes (Bernoulli NB) and Multinomial Naïve Bayes (Multinomial NB) algorithm outperformed other algorithms in terms of all performance parameters. The maximum level of accuracy achieved for the dataset was 94.278% by multinomial NB classifier followed by Bernoulli NB classifier with accuracy of 94.274% when Urdu stop words were removed from dataset. The results suggest that short text of headlines of news can be used as an input for text categorization process.

• Proceedings of the IEEK Conference
• /
• 2000.11c
• /
• pp.121-124
• /
• 2000

In this paper, we propose a pen gesture recognition system for user interface in multimedia terminal which requires fast processing time and high recognition rate. It is realtime and interaction system between graphic and text module. Text editing in recognition system is performed by pen gesture in graphic module or direct editing in text module, and has all 14 editing functions. The pen gesture recognition is performed by searching classification features that extracted from input strokes at pen gesture model. The pen gesture model has been constructed by classification features, ie, cross number, direction change, direction code number, position relation, distance ratio information about defined 15 types. The proposed recognition system has obtained 98% correct recognition rate and 30msec average processing time in a recognition experiment.