• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.72-74
• /
• 2000

인터넷을 효과적으로 검색하기 위하여 검색엔진을 많이 이용하고 있다. 그런데 문서의 키워드를 추출할 적에 지금까지는 Anchor Text를 염두에 두지 않았었다. Anchor Text는 사람이 직접 요약한 것이고(요약성), 하이퍼링크를 포함하는 웹 문서에 반드시 존재하므로(보편성) 그 하이퍼링크가 가리키는 곳의 문서의 키워드를 추출에 적합한 용도가 될 수 있다. 웹 그래프는 이러한 Anchor Text를 이용하여 키워드를 추출함으로써 문서와 문서간, 단어와 단어간의 관계(연관성)까지도 나타내 줄 수 있게 한 검색 엔진 시스템이다. 그러나 Anchor Text 자체가 본문의 내용이 아니고, Anchor Text를 작성한 사람에 따라 다르게 작성되며, 본문의 내용과 무관한 내용도 작성할 수 있다. 따라서 Anchor Text 자체를 어떠한 여과 없이 문서의 키워드로 받아들이긴 힘들다. 본 논문에서는 TFIDF를 통해 좀 더 정확성이 있는 키워드를 추출하였다.

• Journal of Computing Science and Engineering
• /
• v.5 no.2
• /
• pp.150-160
• /
• 2011

Automatic text classification has a long history and many studies have been conducted in this field. In particular, many machine learning algorithms and information retrieval techniques have been applied to text classification tasks. Even though much technical progress has been made in text classification, there is still room for improvement in text classification. In this paper, we will discuss remaining issues in improving text classification. In this paper, three improvement issues are presented including automatic training data generation, noisy data treatment and term weighting and indexing, and four actual studies and their empirical results for those issues are introduced. First, the semi-supervised learning technique is applied to text classification to efficiently create training data. For effective noisy data treatment, a noisy data reduction method and a robust text classifier from noisy data are developed as a solution. Finally, the term weighting and indexing technique is revised by reflecting the importance of sentences into term weight calculation using summarization techniques.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2000.10a
• /
• pp.337-340
• /
• 2000

Using the Information Retrieval systems on the Internet, the demand of exact and specific information has also been popularized. To offer exact information, there k3 been generalized demand of searching from the keyword of the shortened text and also of the full-text. This study is to suggest a scheme for full-text searches. It is to compare the existing scheme of information search and full-text information search with interMedia text. We suggest search methods for the full-text.

• International journal of advanced smart convergence
• /
• v.8 no.3
• /
• pp.95-101
• /
• 2019

Recently, there have been many issues related to text recognition using Tesseract. One of these issues is that the text recognition accuracy is significantly lower for smaller fonts. Tesseract extracts text by creating an outline with direction in the image. By searching the Tesseract database, template matching with characters with similar feature points is used to select the character with the lowest error. Because of the poor text extraction, the recognition accuracy is lowerd. In this paper, we compared text recognition accuracy after applying various super-resolution methods to smaller text images and experimented with how the recognition accuracy varies for various image size. In order to recognize small Korean text images, we have used super-resolution algorithms based on deep learning models such as SRCNN, ESRCNN, DSRCNN, and DCSCN. The dataset for training and testing consisted of Korean-based scanned images. The images was resized from 0.5 times to 0.8 times with 12pt font size. The experiment was performed on x0.5 resized images, and the experimental result showed that DCSCN super-resolution is the most efficient method to reduce precision error rate by 7.8%, and reduce the recall error rate by 8.4%. The experimental results have demonstrated that the accuracy of text recognition for smaller Korean fonts can be improved by adding super-resolution methods to the OCR preprocessing module.

• Journal of Korean Classical Literature and Education
• /
• no.16
• /
• pp.91-116
• /
• 2008

This Study aims to research how we read Korean classical narrative in the digital era and the culture digital made. The meaning of reading Korean classical narrative in digital culture can be divided in four category; first, reading the old narrative text that made and enjoyed a long time ago in digital era, second, reading the old narrative text that made in the old times not as th book but by the media environment that the digital technology made up, third, reading the extended and modified media text by the digital technology from the original old narrative text, fourth, reading the text by the digital technology seeking for the original narrative text as archetype. And it is inspected that the characteristic of the digital era and how to read the four type of Korean classical narrative through the example. So we can consider about the characteristic of enjoying Korean classical narrative and method of reading the diversified Korean classical narrative by the digital. Finally, it is conclusion that we must think over the original text of Korean classical narrative and adhere classicality. And we learned we should research more abundant Korean classical narrative text.

• Journal of Computing Science and Engineering
• /
• v.4 no.2
• /
• pp.110-127
• /
• 2010

In this study, we propose a method for encoding documents into string vectors, instead of numerical vectors. A traditional approach to text categorization usually requires encoding documents into numerical vectors. The usual method of encoding documents therefore causes two main problems: huge dimensionality and sparse distribution. In this study, we modify or create machine learning-based approaches to text categorization, where string vectors are received as input vectors, instead of numerical vectors. As a result, we can improve text categorization performance by avoiding these two problems.

• Proceedings of the Korean Fiber Society Conference
• /
• 1989.06a
• /
• pp.67-68
• /
• 1989

• Journal of KIISE:Software and Applications
• /
• v.29 no.6
• /
• pp.417-424
• /
• 2002

Automatic text categorization is a problem of assigning predefined categories to free text documents. In order to classify text documents, we have to extract good features from them. In previous researches, a text document is commonly represented by the frequency of each feature. But there is a difference between important and unimportant sentences in a text document. It has an effect on the importance of features in a text document. In this paper, we measure the importance of sentences in a text document using text summarizing techniques. A text document is represented by features with different weights according to the importance of each sentence. To verify the new method, we constructed Korean news group data set and experiment our method using it. We found that our new method gale a significant improvement over a basis system for our data sets.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.11
• /
• pp.85-91
• /
• 2016

This paper proposes a collective approach to cited text recognition by exploiting a set of citing text from different articles citing the same article. First, the proposed method gathers highly-ranked cited sentences from the cited article using a group of citing text to create a collective information of probable cited sentences. Then, such collective information is used to determine final cited sentences among highly-ranked sentences from similarity-based cited text recognition. Experiments have been conducted on the data set which consists of research articles from a computational linguistics domain. Evaluation results showed that the proposed method could improve the performance of similarity-based baseline approaches.

• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.912-919
• /
• 2009

A novel algorithm using 2D tensor voting and edge-based approach is proposed for text detection in natural scene images. The tensor voting is used based on the fact that characters in a text line are usually close together on a smooth curve and therefore the tokens corresponding to centers of these characters have high curve saliency values. First, a suitable edge-based method is used to find all possible text regions. Since the false positive rate of text detection result generated from the edge-based method is high, 2D tensor voting is applied to remove false positives and find only text regions. The experimental results show that our method successfully detects text regions in many complex natural scene images.