• The KIPS Transactions:PartB
• /
• v.12B no.7 s.103
• /
• pp.737-744
• /
• 2005

In this paper, we propose a three-level color clustering algerian for the binarization of text regions extracted from natural scene images. The proposed algorithm consists of three phases of color segmentation. First, the ordinary images in which the texts are well separated from the background, are binarized. Then, in the second phase, the input image is passed through a high pass filter to deal with those affected by natural or artificial light. Finally, the image Is passed through a low pass filter to deal with the texture in texts and/or background. We have shown that the proposed algorithm is more effective used gray-information binarization algorithm. To evaluate the effectiveness of the proposed algorithm we use a commercial OCR software ARMI 6.0 to observe the recognition accuracies on the binarized images. The experimental results on word and character recognition show that the proposed approach is more accurate than conventional methods by over $35\%$.

• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1236-1243
• /
• 2017

In this paper, we propose a novel way of producing keyword networks, named LSI-based ClusterTextRank, which extracts significant key words from a set of clusters with a mutual information metric, and constructs an association network using latent semantic indexing (LSI). The proposed method reduces the dimension of documents through LSI, decomposes documents into multiple clusters through k-means clustering, and expresses the words within each cluster as a maximal spanning tree graph. The significant key words are identified by evaluating their mutual information within clusters. Then, the method calculates the similarities between the extracted key words using the term-concept matrix, and the results are represented as a keyword association network. To evaluate the performance of the proposed method, we used travel-related blog data and showed that the proposed method outperforms the existing TextRank algorithm by about 14% in terms of accuracy.

• 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.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.181-184
• /
• 2005

무수히 많은 정보 중에서 특정 사용자에게 가장 유용할 것으로 판단되는 정보를 추천하여 제공함으로써 특정 사용자의 편의를 돕는 시스템이 추천시스템이다. 이러한 추천시스템에 성공적으로 적용된 알고리즘이 협력적 필터링이며 이것은 다른 사용자로부터 먼저 평가된 웹 문서를 제공받아 이를 축적하고 다시 사용자에게 환원하는 알고리즘이다. 하지만 이 알고리즘은 초기평가, 희소성, 확장성 둥의 문제점을 내포하고 있다. 따라서 본 논문은 이러한 문제점을 해결하고 성능 향상을 하기 위해 적용된 개인화 추천시스템 관련 최신 알고리즘들을 비교하고 분석한 결과를 제시한다. 이를 위해 먼저 최근에 발표된 협력적 필터링과 최근접 이웃 알고리즘, 인공 지능기술을 이용한 알고리즘, 군집화 알고리즘 둥 각각에 대한 기술적 분석 결과를 수행한다. 그런 후 이들 다양한 알고리즘들의 조합을 통한 성능 향상 결과에 대한 비교분석과 각각의 조합에 대한 장단점 분석 결과도 또한 제시한다.

• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.591-600
• /
• 2006

This paper describes the development and implementation of a algorithm to decompose word images from image regions mixed text/graphics in document images using statistical analyses. To decompose word images from image regions, the character components need to be separated from graphic components. For this process, we propose a method to separate them with an analysis of box-plot using a statistics of structural components. An accuracy of this method is not sensitive to the changes of images because the criterion of separation is defined by the statistics of components. And then the character regions are determined by analyzing a local crowdedness of the separated character components. finally, we devide the character regions into text lines and word images using projection profile analysis, gap clustering, special symbol detection, etc. The proposed system could reduce the influence resulted from the changes of images because it uses the criterion based on the statistics of image regions. Also, we made an experiment with the proposed method in document image processing system for keyword spotting and showed the necessity of studying for the proposed method.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.7
• /
• pp.2108-2115
• /
• 2000

The conventional Boolean retrieval systems based on vector spae model can provide the results of retrieval fast, they can't reflect exactly user's retrieval purpose including semantic information. Consequently, the results of retrieval process are very different from those users expected. This fact forces users to waste much time for finding expected documents among retrieved documents. In his paper, we designed a bayesian SOM(Self-Organizing feature Maps) in combination with bayesian statistical method and Kohonen network as a kind of unsupervised learning, then perform classifying documents depending on the semantic similarity to user query in real time. If it is difficult to observe statistical characteristics as there are less than 30 documents for clustering, the number of documents must be increased to at least 50. Also, to give high rank to the documents which is most similar to user query semantically among generalized classifications for generalized clusters, we find the similarity by means of Kohonen centroid of each document classification and adjust the secondary rank depending on the similarity.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.4
• /
• pp.1458-1467
• /
• 2010

Recently, imitation and infringement rights of an intellectual property are being recognized as impediments to nation's industrial growth. To prevent the huge loss which comes from theses impediments, many researchers are studying protection and efficient management of an intellectual property in various ways. Especially, the prediction of patent registration is very important part to protect and assert intellectual property rights. In this study, we propose the patent document analysis method by using text mining to predict whether the patent is registered or rejected. In the first instance, the proposed method builds the database by using the word frequencies of the rejected patent documents. And comparing the builded database with another patent documents draws the similarity value between each patent document and the database. In this study, we used k-means which is partitioning clustering algorithm to select criteria value of patent rejection. In result, we found conclusion that some patent which similar to rejected patent have strong possibility of rejection. We used U.S.A patent documents about bluetooth technology, solar battery technology and display technology for experiment data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.625-628
• /
• 2002

동영상의 장면 전환의 검출은 특정 객체의 검출, 비디오 압축 또는 비디오 문서의 군집화, 비디오 데이터베이스 시스템 등 많은 응용프로그램에서 유용하게 다루어진다. 특히 멀티미디어 데이터베이스에서 이미지를 검출하는 처음 단계로서 Shot Change 검출은 아주 중요하다. 이미 장면 전환의 검출을 위한 여러 알고리즘이 개발되어 발표되었다. 본 논문에서는 대용량의 영상 데이터 사이즈를 고려하여 검출에 소요되는 시간과 검출의 정확도의 상쇄관계를 알아보기 위해서 히스토그램의 분포에 의한 알고리즘과 이미지의 평균과 분산을 이용한 알고리즘을 구현하고 그 알고리즘 간의 성능의 차이를 비교하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.261-270
• /
• 2020

In this study, we identify promising technologies for Piggyback transportation system by analyzing the relevant patent information. In order for this, we first develop the patent database by extracting relevant technology keywords from the pioneering research papers for the Piggyback flactcar system. We then employed textmining to identify the frequently referred words from the patent database, and using these words, we applied the LDA (Latent Dirichlet Allocation) algorithm in order to identify "topics" that are corresponding to "key" technologies for the Piggyback system. Finally, we employ the ARIMA model to forecast the trends of these "key" technologies for technology forecasting, and identify the promising technologies for the Piggyback system. with keyword search method the patent analysis. The results show that data-driven integrated management system, operation planning system and special cargo (especially fluid and gas) handling/storage technologies are identified to be the "key" promising technolgies for the future of the Piggyback system, and data reception/analysis techniques must be developed in order to improve the system performance. The proposed procedure and analysis method provides useful insights to develop the R&D strategy and the technology roadmap for the Piggyback system.

• Journal of Intelligence and Information Systems
• /
• v.11 no.1
• /
• pp.169-189
• /
• 2005

In order to derive a better classifier with a limited number of training examples, active teaming alternately repeats the querying stage fur category labeling and the subsequent learning stage fur rebuilding the calssifier with the newly expanded training set. To relieve the user from the burden of labeling, especially in an on-line environment, it is important to minimize the number of querying steps as well as the total number of query examples. We can derive a good classifier in a small number of querying steps by using only a small number of examples if we can select multiple of diverse, representative, and ambiguous examples to present to the user at each querying step. In this paper, we propose a cluster-based batch query selection method which can select diverse, representative, and highly ambiguous examples for efficient active learning. Experiments with various text data sets have shown that our method can derive a better classifier than other methods which only take into account the ambiguity as the criterion to select multiple query examples.