• International Journal of Contents
• /
• v.16 no.2
• /
• pp.8-18
• /
• 2020

Data is critical in deep learning but the scarcity of data often occurs in research, especially in the preparation of the paired training data. In this paper, document image binarization with unpaired data is studied by introducing adversarial learning, excluding the need for supervised or labeled datasets. However, the simple extension of the previous unpaired training to binarization inevitably leads to poor performance compared to paired data training. Thus, a new deep learning approach is proposed by introducing a multi-diversity of higher quality generated images. In this paper, a two-stage model is proposed that comprises the generative adversarial network (GAN) followed by the U-net network. In the first stage, the GAN uses the unpaired image data to create paired image data. With the second stage, the generated paired image data are passed through the U-net network for binarization. Thus, the trained U-net becomes the binarization model during the testing. The proposed model has been evaluated over the publicly available DIBCO dataset and it outperforms other techniques on unpaired training data. The paper shows the potential of using unpaired data for binarization, for the first time in the literature, which can be further improved to replace paired data training for binarization in the future.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.796-799
• /
• 2006

This paper presents a new method for automatic detection of skew in a document image using mathematical morphology. To speed up processing, we use reduced image but it still requires long time to estimate the skew angle so the proposed method works with region of interest, not with whole image. Character strings are connected by using morphological closing operation and a component labeling is used to select region of interest. The method considers the lowermost pixels of characters in candidate regions in the binary image of original document image. Experimental results shows that the proposed method is extremely fast and robust as well as independent of script forms.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.369-376
• /
• 2006

The degradation and its inverse modeling can achieve restoration of corrupted image, caused by scaled digitization and electronic transmission. De-speckle process on the noisy document(or SAR) images is one of the basic examples. Non-linearity of the speckle noise model may hinder the inverse process. In this paper, our study is focused on investigation of the restoration methods for bi-level document image degraded by the impulse noise model. Our study shows that, on bi-level document images, the weighted-median filter and the Lee filter methods are very effective among other spatial filtering methods, but wavelet filter method is ineffective in aspect of processing speed: approximately 100 times slower. Optimal values of the weight to be used in the weighted median filter are investigated and presented in this paper.

• Journal of Information Processing Systems
• /
• v.2 no.3 s.4
• /
• pp.189-193
• /
• 2006

In this study we propose an automatic reading system for diagnostic DNA chips. We define a general specification for an automatic reading system and propose a possible implementation method. The proposed system performs the whole reading process automatically without any user intervention, covering image acquisition, image analysis, and report generation. We applied the system for the automatic report generation of a commercialized DNA chip for cervical cancer detection. The fluorescence image of the hybridization result was acquired with a $GenePix^{TM}$ scanner using its library running in HTML pages. The processing of the acquired image and the report generation were executed by a component object module programmed with Microsoft Visual C++ 6.0. To generate the report document, we made an HWP 2002 document template with marker strings that were supposed to be searched and replaced with the corresponding information such as patient information and diagnosis results. The proposed system generates the report document by reading the template and changing the marker strings with the resultant contents. The system is expected to facilitate the usage of a diagnostic DNA chip for mass screening by the automation of a conventional manual reading process, shortening its processing time, and quantifying the reading criteria.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.7
• /
• pp.1487-1494
• /
• 2012

This paper proposes an algorithm detecting the skew of the degraded as well as the clear document images using edge and correcting it. The proposed algorithm detects edges in a character region selected by image complexity and generates projection histograms by projecting them to various directions. And then it detects the document skew by estimating the edge concentrations in the histograms and corrects the skewed document image. For the fast skew detection, the proposed algorithm uses downsampling and 3 step coarse-to-fine searching. In the skew detection of the clear and the degraded images, the maximum and the average detection errors in the proposed algorithm are about 50% of one in a conventional similar algorithm and the processing time is reduced to about 25%. In the non-uniform luminance images acquired by a mobile device, the conventional algorithm can't detect skews since it can't get valid binary images, while the proposed algorithm detect them with the average detection error of 0.1o or under.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.571-574
• /
• 2003

This research is aimed to automate the generating process of the database from paper based table forms like this work. The registration table has so complicate table structures, ana in this research we used the registration tables as an example of general table structure understanding. We propose a table structure understanding system for some table types, and it has some steps. The first step is that the document images on paper are read from the image scanner. The second step is that a document image segments into some tables. In the third step, the character strings is extracted using image processing technology and the property of the character strings is determined. And the structured database is generated automatically. The proposed system consists of two systems. "Master document generation system" is used for the table form definition, and it doesn′t include the handwritten characters. "Structure analysis system for complete d table" is used for the written form, and it analyzes the table form filled in the handwritten character. We implemented the system using MS Visual C＋＋ on Windows, and it can get the correct extraction rate 98％ among 51 registration tables written by the different students.

• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.151-159
• /
• 2021

To derive grid lines for analyzing a table layout, line image enhancement techniques are studying such as various filtering or morphology methods. In spite of line image enhancement, it is still hard to extract line components and to express table cell's layout logically in which the cutting points are exist on the line or the tables are skewing . In this paper, we proposed a line tracking algorithm to extract line components under the cutting points on the line or the skewing lines. The table document layout analysis algorithm is prepared by searching grid-lines, line crossing points and gird-cell using line tracking algorithm. Simulation results show that the proposed method derive 96.4% table document analysis result with average 0.41sec processing times.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.10
• /
• pp.100-112
• /
• 1992

In this paper, an integrated document input/output system is developed which constructs the graphic document from a text file, converts the document into encoded facsimile data, and also recognizes printed/handwritten alphanumerics and Korean characters in a facsimile or graphic document. For an output system, we develop the method which generates bit-map patterns from the document consisting of the KSC5601 and ASCII codes. The binary graphic image, if necessary, is encoded by the G3 coding scheme for facsimile transmission. For a user friendly input system for documents consisting of alphanumerics and Korean characters obtained from a facsimile or scanner, we propose a document recognition algirithm utilizing several special features(partial projection, cross point, and distance features) and the membership function of the fuzzy set theory. In summary, we develop an integrated document input/output system and its performance is demonstrated via computer simulation.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.3 s.35
• /
• pp.143-150
• /
• 2005

Camera image is very sensitive to illumination that result in difficulties for recognizing character. Also Camera captured document images have not only skew but also vignetting effect and geometric distortion. Vignetting effect make it difficult to separate characters from the document images. Geometric distortion, occurred by the mismatch of angle and center position between the document image and the camera, make the shape of characters to be distorted, so that the character recognition is more difficult than the case of using scanner. In this paper, we propose a method that can increase the performance of character recognition by correcting the geometric distortion of document images using a linear approximation which changes the quadrilateral region to the rectangle one. The proposed method also determine the quadrilateral transform region automatically, using the alignment of character lines and the skewed angles of characters located in the edges of each character line. Proposed method, therefore, can correct the geometric distortion without getting positional information from camera.

• 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.