• Journal of Korea Multimedia Society
• /
• v.8 no.10
• /
• pp.1347-1359
• /
• 2005

We propose an efficient block classification of the document images using the second-order statistical texture features computed from spatial gray level dependence matrix (SGLDM). We studied on the techniques that will improve the block speed of the segmentation and feature extraction speed and the accuracy of the detailed classification. In order to speedup the block segmentation, we binarize the gray level image and then segmented by applying smoothing method instead of using texture features of gray level images. We extracted seven texture features from the SGLDM of the gray image blocks and we applied these normalized features to the BP (backpropagation) neural network, and classified the segmented blocks into the six detailed block categories of small font, medium font, large font, graphic, table, and photo blocks. Unlike the conventional texture classification of the gray level image in aerial terrain photos, we improve the classification speed by a single application of the texture discrimination mask, the size of which Is the same as that of each block already segmented in obtaining the SGLDM.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.9 no.4
• /
• pp.444-450
• /
• 1999

This paper deals with several methods: the clustering method that uses k-means algorithm to abstract the area of characters on the image document and the distance function that suits for the HIS coordinate system to cluster the image. For the prepossessing step to recognize this, or the method of characters segmentate, the algorithm to abstract a discrete character is also proposed, using the linking picture element. This algorithm provides the feature that separates any character such as the touching or overlapped character. The methods of projecting and tracking the edge have so far been used to segment them. However, with the new method proposed here, the picture element extracts a discrete character with only one-time projection after abstracting the character string. it is possible to pull out it. dividing the area into the character and the rest (non-character). This has great significance in terms of processing color documents, not the simple binary image, and already received verification that it is more advanced than the previous document processing system.

• 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.

• Journal of Korea Multimedia Society
• /
• v.10 no.2
• /
• pp.218-225
• /
• 2007

This paper presents a technique to detect a document skew that often occurs during document scanning. To correct a skewed document is essential for automatic processing system including character segmentation, character recognition and so on. The proposed algorithm can detect a skew angle exactly by searching characters baselines that have slant information of the document within a candidated area. To reduce processing time, we resized the image small and then established a ROI (region of interest) by morphology operations and connected components analysis. We compared our method with the existing method based on morphology operations and proved correctness and efficiency of the proposed algorithm through experiments and analysis with various kind of document images.

• Journal of Korea Multimedia Society
• /
• v.23 no.7
• /
• pp.883-890
• /
• 2020

In this paper, we propose a variational expectation-maximization algorithm that computes posterior probabilities from Latent Dirichlet Allocation (LDA) model. The algorithm approximates the intractable posterior distribution of a document term matrix generated from a corpus made up by 50 papers. It approximates the posterior by searching the local optima using lower bound of the true posterior distribution. Moreover, it maximizes the lower bound of the log-likelihood of the true posterior by minimizing the relative entropy of the prior and the posterior distribution known as KL-Divergence. The experimental results indicate that documents clustered to image classification and segmentation are correlated at 0.79 while those clustered to object detection and image segmentation are highly correlated at 0.96. The proposed variational inference algorithm performs efficiently and faster than Gibbs sampling at a computational time of 0.029s.

• Journal of KIISE:Software and Applications
• /
• v.28 no.11
• /
• pp.795-813
• /
• 2001

Sophisticated geometric structure analysis must be preceded to create electronic document from logical components extracted from document image. this paper presents a knowledge-based method for sophisticated geometric structure analysis of technical journal pages. The proposed knowledge base encodes geometric characteristics that are not only common in technical journals but also publication-specific in the form rules. The method takes the hybrid of top-down and bottom-up techniques and consists of two phases: region segmentation and identification. Generally, the result of segmentation process does not have a one-to-one matching with composite layout components. Therefore, the proposed method identifies non-text objects such as image, drawing and table, as well as text objects such as text line and equation by splitting or grouping segmented regions into composite layout components. Experimental results with 372 images scanned from the IEEE Transactions on Pattern Analysis and Machine Intelligence show that the proposed method has performed geometrical structure analysis successfully on more than 99% of the test images, resulting in sophisticated performance compared with previous works.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.75-86
• /
• 2004

This paper proposes a method to speed up the document image binarization using a water flow model. The proposed method extracts the region of interest (ROI) around characters from a document image and restricts pouring water onto a 3-dimensional terrain surface of an image only within the ROI. The amount of water to be filed into a local valley is determined automatically depending on its depth and slope. The proposed method accumulates weighted water not only on the locally lowest position but also on its neighbors. Therefore, a valley is filed enough with only one try of pouring water onto the terrain surface of the ROI. Finally, the depth of each pond is adaptively thresholded for robust character segmentation, because the depth of a pond formed at a valley varies widely according to the gray-level difference between characters and backgrounds. In our experiments on real document images, the Proposed method has attained good binarization performance as well as remarkably reduced processing time compared with that of the existing method based on a water flow model.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.8A
• /
• pp.805-813
• /
• 2002

Document image should be classified into detailed regions as text, picture, table and etc through the geometric layout analysis if paper documents can be converted automatically into electronic documents. However, complexity of the document layout and variety of the size and density of a picture are the reason to make it difficult to analyze the geometric layout of the document images. In this paper, we propose the method which have a better performance of the region segmentation and classifications, and the line extraction in the table region than the commercial softwares and previous methods. The proposed method can segment the document into detailed regions by using connected components method even if its layout is complex. This method also classifies texts and pictures by using separable median filter even. Though their size and density are diverse, In addition, this method extracts the lines from the table adapting one dimensional median filter to the each horizontal and vertical direction, even though lines are deformed or texts attached to them.

• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.117-140
• /
• 2013

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the document's textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.6A
• /
• pp.575-583
• /
• 2002

JBIG2 is an International Standard fur compression of Bi-level images and documents. JBIG2 supports three encoding modes for high compression according to region features of documents. One of which is generic region coding for bitmap coding. The basic bitmap coder is either MMR or arithmetic coding. Pattern matching coding method is used for text region, and halftone pattern coding is used for halftone region. In this paper, a document is segmented into line-art, halftone and text region for JBIG2 encoding and JBIG2 CODEC is implemented. For efficient region segmentation of documents, region segmentation method using wavelet coefficient is applied with existing boundary extraction technique. In case of facsimile test image(IEEE-167a), there is improvement in compression ratio of about 2% and enhancement of subjective quality. Also, we propose arbitrary shape halftone region coding, which improves subjective quality in talc neighboring text of halftone region.