• 한국컴퓨터정보학회논문지
• /
• 제11권4호
• /
• pp.55-60
• /
• 2006

문자 영역 추출을 위해서 FFT와 신경망을 이용한 방법을 본 논문에서 제안하고자 한다. 일반적으로 문자 영역은 고주파 영역에서 발견되므로 FFT를 이용하여 이 특징을 추출할 수 있다. 문자(고 주파) 영역과 비 문자(저 주파) 영역을 신경망에 학습을 시킨다. 신경망에 고주파 영역을 입력으로써 후보 영역을 추출한다. 그리고 최종 문자 영역은 후보 영역 검증을 통하여 추출된다. 실험 결과 후보 영역 추출은 학습된 경우 100% 추출율을 보여주고 있으며, 검증을 통한 후보 영역 추출율은 95%임을 알 수 있었다. 제안된 알고리즘의 장점은 알고리즘의 단순성과 실시간 처리에 있다.

• 대한원격탐사학회지
• /
• 제34권4호
• /
• pp.693-702
• /
• 2018

With the development of data analysis methods and data processing capabilities, semantic analysis of floorplans has been actively studied. Therefore, studies for extracting text information from drawings have been conducted for semantic analysis. However, existing research that separates rasterized text from floorplan has the problem of loss of text information, because when graphic and text components overlap, text information cannot be extracted. To solve this problem, this study defines the morphological characteristics of the text in the floorplan, and classifies the class of the corresponding region by applying the class of the SIFT key points through the SVM models. The algorithm developed in this study separated text components with a recall of 94.3% in five sample drawings.

• 농촌계획
• /
• 제27권3호
• /
• pp.103-116
• /
• 2021

In this study, the characteristics of rural tourism image perceived by urban residents were analyzed through text analysis of blog data. In order to examine the images related to rural tourism, blog data written with the keyword "Gochang-gun travel" was used. LDA topic analysis, one of the text mining techniques, was used for the analysis. In the tourism image of Gochang-gun, 9 topics were derived, and 112 major places appeared. This was divided into 3 main activities and 5 object spaces through the review of keywords and the original text of blog data. As a result of the analysis, the traditional main resources of the region, Seonun mountain, Seonun temple, and Gochang-eup fortress, formed topic. On the other hand, world heritage such as dolmen and Ungok wetland did not appear as topic. In particular, the farms operated by the private sector form individual topics, and the theme farm can be seen as an important resource for tourism in Gochang-gun. Also, through the distribution of place keywords, it was possible to understand the characteristics of travel by region and the usage behavior of visitors. In the case of Gochang-gun, there was a phenomenon in which visitors were biased by region. This seems to be the result of Gochang-gun seeking to vitalize local tourism focusing on natural, ecological, and scenic resources. It is necessary to establish a plan for balanced regional development and develop other types of tourism resources. This study is different in that it identified the types and characteristics of rural tourism images in the region perceived by visitors, and the status of tourism at the regional level.

• 전자공학회논문지CI
• /
• 제46권2호
• /
• pp.44-51
• /
• 2009

자연 영상에서의 텍스트 이해는 지난 수년간 매우 활발한 연구 분야로 자리하고 있다. 논문에서 우리는 한국어 간판 영상으로부터 자동으로 텍스트를 인식하는 방법을 제안한다. 제안된 방법은 상호명의 인식을 위한 텍스트 영역의 검출 및 이진화를 포함하고 있다. 먼저 수직, 수평 방향의 에지 히스토그램을 이용하여 텍스트 영역의 정교한 검출을 수행하였다. 두 번째 단계는 검출된 텍스트 영역에 대해서 연결요소 기법을 적용하여 각각의 독립된 한 개의 문자 영역으로 분할되어지고, 마지막으로 최소 거리 분류법에 의해 각각의 글자를 인식한다. 각각의 문자 인식을 위해 모양 기반 통계적 특징을 추출한다. 실험에서 제안된 전체적인 효율성 및 정확성을 분석하였으며, 현재 구현된 모바일 시스템의 실용성을 확인할 수 있었다.

• International Journal of Contents
• /
• 제11권4호
• /
• pp.77-85
• /
• 2015

Table detection is a challenging problem and plays an important role in document layout analysis. In this paper, we propose an effective method to identify the table region from document images. First, the regions of interest (ROIs) are recognized as the table candidates. In each ROI, we locate text components and extract text blocks. After that, we check all text blocks to determine if they are arranged horizontally or vertically and compare the height of each text block with the average height. If the text blocks satisfy a series of rules, the ROI is regarded as a table. Experiments on the ICDAR 2013 dataset show that the results obtained are very encouraging. This proves the effectiveness and superiority of our proposed method.

• 디지털융복합연구
• /
• 제17권4호
• /
• pp.49-55
• /
• 2019

본 연구는 빅데이터 분석방법인 텍스트마이닝을 이용한 부동산시장 동향분석에 관한 연구로 자료는 2016년 8월부터 2017년 8월까지의 포털사이트인 네이버에 게시된 인터넷 뉴스를 통해 수집하였다. TF-IDF 분석결과, 주택, 분양, 가구, 시장, 지역 순으로 빈도가 높게 나타났고 대출, 정부, 대책, 규제 등 정책과 관련된 단어들도 많이 추출되었으며 지역관련 단어는 서울의 출현빈도가 가장 많은 것으로 나타났다. 지역과 관련된 단어 조합은 '서울-강남', '서울-수도권', '강남-재건축', '서울-재건축'의 출현빈도가 많은 것으로 나타나 강남지역 재건축에 대한 사람들의 관심과 기대가 높은 것을 알 수 있다.

• 전기학회논문지
• /
• 제58권4호
• /
• pp.806-816
• /
• 2009

Character recognition system consists of four step; text localization, text segmentation, character segmentation, and recognition. The character segmentation is very important and difficult because of noise, illumination, and so on. For high recognition rates of the system, it is necessary to take good performance of character segmentation algorithm. Many algorithms for character segmentation have been developed up to now, and many people have been recently making researches in segmentation of touching or overlapping character. Most of algorithms cannot apply to the text regions of management number marked on the slab in steel image, because the text regions are irregular such as touching character by strong illumination and by trouble of nozzle in marking machine, and loss of character. It is difficult to gain high success rate in various cases. This paper describes a new algorithm of character segmentation to recognize slab management number marked on the slab in the steel image. It is very important that pre-processing step is to convert gray image to binary image without loss of character and touching character. In this binary image, non-touching characters are simply separated by using vertical projection profile. For separating touching characters, after we use combined profile to find candidate points of boundary, decide real character boundary by using method based on recognition. In recognition step, we remove noise of character images, then recognize respective character images. In this paper, the proposed algorithm is effective for character segmentation and recognition of various text regions on the slab in steel image.

• International Journal of Contents
• /
• 제10권3호
• /
• pp.35-40
• /
• 2014

Text line segmentation is a critical task in handwritten document recognition. In this paper, we propose a novel text-line-segmentation method using baseline estimation and watershed. The baseline-detection algorithm estimates the baseline using Adaptive Head-Tail Connection (AHTC) on the document. Then, the watershed method segments the line region using the baseline-detection result. Finally, the text lines are separated by watershed result and a post-processing algorithm defines the lines more correctly. The scheme successfully segments text lines with 97% accuracy from the handwritten document images in the ICDAR database.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.117-118
• /
• 2008

제철소에서 생산된 Slab에는 서로를 구분하기 위해 관리번호가 기재되어 있다. 호스트 컴퓨터에서 보내 온 Slab 관기번호와 제품에 마킹되어 있는 Slab 관리번호의 일치 여부를 확인하기 위하여 자동 인식 시스템이 설치되어 있다. 자동 인식 시스템은 실시간으로 Slab가 없을 때의 영상과 Slab가 있을 때의 영상을 촬영하고 이를 이용하여 Slab 관리 번호를 인식하는 방법으로 구성되어 있다. 제철소 배경 영상이 복잡하고 조명이 계속 바뀌기 때문에 Text Region을 찾는 방법은 Slab 관리 번호를 인식하는데 가장 큰 문제점이다. 본 논문에서는 복잡한 배경을 실시간으로 Training하여 Text Region을 찾기 위한 전처리 과정을 나타내었다. 복잡한 배경 영상을 이용하여 Slab가 위치한 Region을 찾을 수 있고 실시간으로 Training하기 때문에 조명의 영향을 줄일 수 있다.

• 한국통신학회논문지
• /
• 제22권11호
• /
• pp.2531-2542
• /
• 1997

This paper describes a method for region segmentation and string extractionin documents which are mixed with text, graphic and picture images by the use of the structural characteristic of connceted components. In segmentation of non-text regionas, with connection-characteristic functions which are made by structural characteristic of connected components, segmentation process is progressed. In the string extraction, first we organize basic-unit-region of which vertical and horizontal length are 1/4 of average length of connection components. Second, by merging the basic-unit-regions one other that have smaller values than a given connection intensity threshold. Third, by linking the word blocks with similar block anagles, initial strings are cresed. Finally the whold strings are generated by merging remaining word blocks whose angles are not decided, if their height and prosition are similar to the initial strings. This method can extract strings that are neither horizontal nor of various character sizes. Through computer exteriments with different style documents, we have shown that the feasibility of our method successes.