Browsing by Author "Lee, HJ"

Now showing 1 - 20 of 26

A Bezier curve-based approach to shape description for Chinese calligraphy characters
(2001)
Yang, HM
;
Lu, JJ
;
Lee, HJ
;
資訊工程學系
;
Department of Computer Science
In this paper, we propose a method to vectorize Chinese characters in calligraphy documents. Our system can prevent tire zigzag phenomena when the characters are enlarged. The system contains two modules: contour segment extraction and description. In the former, high curvature points on contours are detected as corner points, which divide the contour into several segments. In the latter, a contour segment can be described either by a straight line or a cubic Bezier curve. according to relations between the contour segment and the Bezier curve, control points are adjusted to fit the contour segment better. When the curve fitness cost is small enough, the shape is described well. The processing time of our curve fitting is about five seconds per A4 image, which has 4488 contour segments. Experimental results demonstrate that our system is efficient and promising.
A language model based on semantically clustered words in a Chinese character recognition system
(1997-08-01)
Lee, HJ
;
Tung, CH
;
資訊工程學系
;
Department of Computer Science
This paper presents a new method for clustering the words in a dictionary into ward groups. A Chinese character recognition system can then use these groups in a language model to improve the recognition accuracy. In the language model, the number of parameters we must train beforehand can be kept to a reasonable value. The Chinese synonym dictionary Tong2yi4ci2 ci2lin2 providing the semantic features is used to calculate the weights of the semantic attributes of the character-based word classes. The weights of the semantic attributes are next updated according to the words of the Behavior dictionary, which has a rather complete word set. Then, the word classes are clustered to In groups according to the semantic measurement by a greedy method. The words in the Behavior dictionary can finally be assigned to the m groups. The parameter space for the bigram contextual information of the character recognition system is m(2). From the experimental results, the recognition system with the proposed model has shown better performance than that of a character-based bigram language model. (C) 1997 Pattern Recognition Society. Published by Elsevier Science Ltd.
A language model based on semantically clustered words in a Chinese character recognition system
(1997-08-01)
Lee, HJ
;
Tung, CH
;
交大名義發表
;
資訊工程學系
;
National Chiao Tung University
This paper presents a new method for clustering the words in a dictionary into ward groups. A Chinese character recognition system can then use these groups in a language model to improve the recognition accuracy. In the language model, the number of parameters we must train beforehand can be kept to a reasonable value. The Chinese synonym dictionary Tong2yi4ci2 ci2lin2 providing the semantic features is used to calculate the weights of the semantic attributes of the character-based word classes. The weights of the semantic attributes are next updated according to the words of the Behavior dictionary, which has a rather complete word set. Then, the word classes are clustered to In groups according to the semantic measurement by a greedy method. The words in the Behavior dictionary can finally be assigned to the m groups. The parameter space for the bigram contextual information of the character recognition system is m(2). From the experimental results, the recognition system with the proposed model has shown better performance than that of a character-based bigram language model. (C) 1997 Pattern Recognition Society. Published by Elsevier Science Ltd.
An efficient algorithm for form structure extraction using strip projection
(1998-09-01)
Chen, JL
;
Lee, HJ
;
資訊工程學系
;
Department of Computer Science
This paper presents an efficient strip-projection-based approach to extracting form structures from form documents for office automation. To locate the data, we have to extract and interpret the form structure. In this paper, a strip projection method is presented for extracting the form structure. We first segment input form images into uniform vertical and horizontal strips. Since most form lines are vertical or horizontal, we project the image of each vertical strip horizontally and that of each horizontal strip vertically. The peak positions in these projection profiles denote possible locations of lines in form images. We then extract the lines starting with the possible line positions in the source image. After all lines have been extracted, redundant lines are removed using a line-verification algorithm and broken lines are linked using a line-merging algorithm. Experimental results show that the proposed method can extract form structures from A4-sized documents in about 3 seconds which is very efficient, compared with the methods based on Hough transformation and run-based line-detection algorithms. (C) 1998 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.
An X-band front-end module using HTS technique for a commercial dual mode radar
(2005-06-01)
Niu, DC
;
Huang, TW
;
Lee, HJ
;
Chang, CY
;
電信工程研究所
A front end module of receiver has been designed to eliminate the interference between the tracking and searching radar used in commercial radar application. The module is located at the receiving path of the searching radar. The proposed module includes two parts, the HTS superconducting filter and cryogenic low noise amplifier. The bandwidth of the eight-resonator HTS hairpin filter is 2% at the X-band frequency. Low insertion loss (below1 dB) and good skirt rejection (down to 60 dB at 50 MHz from the pass-band edge) are obtained. The two-stage low noise amplifier is designed by commercial low noise HEMT devices, NE321000. Two Lange couplers are located at output and input port of each amplifier stage to improve the return loss and to make LNA easily match to optimal low noise impendence. The cryogenic amplifier shows 30 dB gain and 0.4 dB NF at 77 K in X-band. A very high rejection is necessary for the elimination of unwanted spurious signals. The acceptable specification is 110 dB down at 500 MHz away from the band-edge of the filter. In general, the skirt rejection of a hairpin HT filter is pretty good near the pass-band edge, but may become worse far from the pass-band edge. To meet the requirement of this commercial radar application, a high rejection suspended stripline filter is put after the low noise amplifier. The whole module shows an maximal NF of 1.5 dB, a gain of 25 dB around pass-band frequencies, and a rejection of better than 110 dB at 500 MHz away from the band edge of the filter. It totally solves the interference problem in this dual mode radar.
Anchor text mining for translation of Web queries
(2001)
Lu, WH
;
Chien, LF
;
Lee, HJ
;
交大名義發表
;
National Chiao Tung University
This paper presents an approach to automatically extracting translations of Web query terms through mining of Web anchor texts and link structures. One of the existing difficulties in cross-language information retrieval (CLIR) and Web search is the lack of the appropriate translations of new terminology and proper names. Such a difficult problem can be effectively alleviated by our proposed approach, and the resource of anchor texts in the Web is proven a valuable corpus for this kind of term translation.
Anchor text mining for translation of Web queries: A transitive translation approach
(2004-04-01)
Lu, WH
;
Chien, LF
;
Lee, HJ
;
資訊工程學系
;
Department of Computer Science
To discover translation knowledge in diverse data resources on the Web, this article proposes an effective approach to finding translation equivalents of query terms and constructing multilingual lexicons through the mining of Web anchor texts and link structures. Although Web anchor texts are wide-scoped hypertext resources, not every particular pair of languages contains sufficient anchor texts for effective extraction of translations for Web queries. For more generalized applications, the approach is designed based on a transitive translation model. The translation equivalents of a query term can be extracted via its translation in an intermediate language. To reduce interference from translation errors, the approach further integrates a competitive linking algorithm into the process of determining the most probable translation. A series of experiments has been conducted, including performance tests on term translation extraction, cross-language information retrieval, and translation suggestions for practical Web search services, respectively. The obtained experimental results have shown that the proposed approach is effective in extracting translations of unknown queries, is easy to combine with the probabilistic retrieval model to improve the cross-language retrieval performance, and is very useful when the considered language pairs lack a sufficient number of anchor texts. Based on the approach, an experimental system called LiveTrans has been developed for English-Chinese cross-language Web search.
Binarization of color document images via luminance and saturation color features
(2002-04-01)
Tsai, CM
;
Lee, HJ
;
資訊工程學系
;
Department of Computer Science
This paper presents a novel binarization algorithm for color document images. Conventional thresholding methods do not produce satisfactory binarization results for documents with close or mixed foreground colors and background colors. Initially, statistical image features are extracted from the luminance distribution. Then, a decision-tree based binarization method is proposed, which selects various color features to binarize color document images. First, if the document image colors are concentrated within a limited range, saturation is employed. Second, if the image foreground colors are significant, luminance is adopted. Third, if the image background colors are concentrated within a limited range, luminance is also applied. Fourth, if the total number of pixels with low luminance (less than 60) is limited, saturation is applied; else both luminance and saturation are employed. Our experiments include 519 color images, most of which are uniform invoice and name-card document images. The proposed binarization method generates better results than other available methods in shape and connected-component measurements. Also, the binarization method obtains higher recognition accuracy in a commercial OCR system than other comparable methods.
Chinese handwritten character segmentation in form documents
(1999)
Chen, JL
;
Wu, CH
;
Lee, HJ
;
資訊工程學系
;
Department of Computer Science
This paper presents a projection based method for segmenting handwritten Chinese characters in form documents with known structures. In the preprocessing phase, a noise removal method is proposed that preserves stroke connections and character edge points. In the character segmentation phase, the projection profile analysis method is used to segment a text line image into projection blocks. In addition, projection blocks are classified into one of four types: mark, half-word, single-word, and two-word. Large blocks are then split and small blocks are merged. In addition, an OCR system is adopted to eliminate errors resulting from the inappropriate merging of Chinese numerical characters with other characters. As for 1319 Chinese characters are tested during our experiments, the correct segmentation rates of 92.34% and 91.76% are obtained with and without the OCR module.
Design of a mathematical expression understanding system
(1997-03-01)
Lee, HJ
;
Wang, JS
;
交大名義發表
;
資訊工程學系
;
National Chiao Tung University
A scientific document usually consists of text and mathematical expressions. In this paper, we present a system for segmenting and understanding text and mathematical expressions in a document, The system can be divided into six stages: page segmentation and labeling, character segmentation, feature extraction, character recognition, expression formation, and error correction and expression extraction. After we extract all text lines in a document, we separate all symbols in each text line and calculate direction-feature vectors and aspect ratios for those symbols. Then, a nearest-neighbor algorithm recognizes characters. In the expression formation stage, we build a symbol relation tree for each text line that represents the relationships among the symbols in the text line. Each text line is decomposed into a collection of primitive tokens: operands, operators and separators. Heuristic rules based on these primitive tokens are used to correct text recognition errors. Finally, we extract all mathematical expressions according to basic expression forms. Several pages of documents were scanned to test the method. All mathematical expressions are understood. In the expressions generated, a few symbols are misrecognized. The average recognition rate was 96.16%. (C) 1997 Elsevier Science B.V.
Detection and recognition of license plate characters with different appearances.
(2003)
Wang, SZ
;
Lee, HJ
;
資訊工程學系
;
Department of Computer Science
This paper proposes an approach to developing an automatic license plate recognition system. Car images are taken from various positions outdoors. Because of the variations of angles from the camera to the car, license plates have various locations and rotation angles in an image. In the license plate detection phase, the magnitude of the vertical gradients is used to detect candidate license plate regions. These candidate regions are then evaluated based on three geometrical features: the ratio of width and height, the size and the orientation. The last feature is defined by the major axis. In the character recognition phase, we must detect character features that are non-sensitive to the rotation variations. The various rotated character images of a specific character can be normalized to the same orientation based on the major axis of the character image. The crossing counts and peripheral background area of an input character image are selected as the features for rotation-free character recognition. Experimental results show that the license plates detection method can correctly extract all license plates from 102 car images taken outdoors and the rotation-free character recognition method can achieve an accuracy rate of 98.6%.
Dual-binarization and anisotropic diffusion of Chinese characters in calligraphy documents
(2001)
Wang, SZ
;
Lee, HJ
;
資訊工程學系
;
Department of Computer Science
In this paper, we propose a method for calligraphy document binarization. First, the properties of calligraphy documents are analyzed to classify calligraphy documents into two classes: tablet documents and writing documents. Because calligraphy documents have serious noises and large variations in gray scales of the characters, the foreground will be broken after thresholding. The anisotropic diffusion technique is used to smooth input calligraphy documents, which can preserve character boundaries well. Last, noises are removed from binarized images based on the information of stroke widths. In our experiments, 90 tablet documents and 51 writing documents are binarized and well binarized results are obtained.
Extraction and recognition of license plates of motorcycles and vehicles on highways
(2004)
Lee, HJ
;
Chen, SY
;
Wang, SZ
;
資訊工程學系
;
Department of Computer Science
In this paper, a recognition system is proposed to extract and recognize license plates of motorcycles and vehicles on highways. In the first stage, a block-difference method is used to detect moving objects. According to the variance and the similarity of the MxN blocks defined on two diagonal lines, the blocks are categorized as three kinds: low-contrast, stationary and moving blocks. In the second stage, a screening method based on the projection of edge magnitudes is used to find two peaks in the projection histograms to bound license plates. The scanning lines with low counts can be removed. In the third stage, character images are segmented and recognized. In our experiments, we tested 180 pairs of images. The block-difference method has a 98% success rate and can remove 88% of pixels from an image on average. The screening method has a 94.4% success rate and the character recognition method has a 95.7% precision rate.
Field data extraction for form document processing using a gravitation-based algorithm
(2001-09-01)
Chen, JL
;
Lee, HJ
;
資訊工程學系
;
Department of Computer Science
This paper presents a novel approach to grouping Chinese handwritten field data filled in form documents using a gravitation-based algorithm. An algorithm is developed to extract handwritten field data which may be written out of form fields. First, form lines are extracted and removed from input form images. Connected-components are then detected from remaining data, and the gravitation for each connected-component is computed by using the black pixel counts as their mass. Next, we move connected-components according to their gravitation. As generally known, filled-in data have the locality property, i.e., data of the same field are normally written in a local area consecutively. Therefore, the relationship of these connected-components can be determined by this property. Repeatedly moving these connected-components according to their neighbor components allows us to determine which connected-components should be extracted for a particular field. Experimental results demonstrate the effectiveness of the proposed method in grouping field data, (C) 2001 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.
Field-data grouping for form document processing using a gravitation-based algorithm
(1998)
Chen, JL
;
Lee, HJ
;
資訊工程學系
;
Department of Computer Science
This paper presents a novel approach tc, grouping Chinese handwritten field-data of form documents using a gravitation-based algorithm. We develop an algorithm to extract handwritten field data which may be written out of the fields. We first extract and remove form lines for input form images. Next, we detect connected-components from remaining data, and compute the gravitation for each connected-component by using the black pixel counts as their mass. Then, we move connected-components to their field center according to their gravitation, since filled-in data have the locality property, that is, data of the same field are usually written in a local area consecutively. After moving these connected-components for a certain times, we can assign most components to the fields they should be. Thus, we can determine which connected-components should be extracted for a particular field. Experimental results show that this proposed method can group field-data effectively.
High-precision two-kernel Chinese character recognition in general document processing systems
(2001)
Zhao, SL
;
Lee, HJ
;
資訊工程學系
;
Department of Computer Science
This paper proposes a general Chinese document recognition system with high recognition rate, including preprocessing, recognition kernel, and postprocessing, especially for low quality images. In the preprocessing module, fast rotation transformation algorithm is proposed. Since characters are extracted for recognition engines, document images must be segmented into text blocks, text lines, and then character images. In the recognition module, two recognition engines are used to recognize the character images. The weights of these kernels and features are calculated fi-om the relative stroke widths of character images. In the post-processing module, we calculate confidence values for different candidates and then select the most confident candidate as the OCR result. The experiments show the system we propose is very effective and efficient.
Interfered-character recognition by removing interfering-lines and adjusting feature weights
(1998)
Tseng, YH
;
Lee, HJ
;
資訊工程學系
;
Department of Computer Science
Characters sometimes overlap with non-textual lines in form documents and these interfered-characters would generally be recognized with poor accuracy. In this paper we propose a two-step interfering-line removing method. Positions and orientations of interfering-lines are first detected by the Hough transform. Interfering-line widths are then determined from projection histograms. An ambiguous area is defined to bound an interfering-line. Black runs in the ambiguous are classified into four types and grouped into run-groups. The directions of hidden character strokes in each run-groups are predicted. Black pixels located in these hidden strokes are regarded as character pixels and the other black pixels are considered as interfering pixels, which will be removed then. Most OCR engines are trained by non-interfered sample characters. In order to recognize interfered-characters, we adjust the feature values by assigning a stability value to each of sub-regions. In our collected 1820 interfered handwritten Chinese characters, the recognition accuracy was 24.02% for interfered-characters and 89.91% for characters after removing interfering-lines.
On end-to-end architecture for transporting MPEG-4 video over the Internet
(2000-09-01)
Wu, DP
;
Hou, YWT
;
Zhu, WW
;
Lee, HJ
;
Chiang, TH
With the success of the Internet and flexibility of MPEG-4, transporting MPEG-4 video over the Internet is expected to be an important component of many multimedia applications in the near future. Video applications typically have delay and loss requirements, which cannot be adequately supported by the current Internet, Thus, it is a challenging problem to design an efficient MPEG-4 video delivery system that can maximize the perceptual quality while achieving high resource utilization. This paper addresses this problem by presenting an end-to-end architecture for transporting MPEG-4 video over the Internet, We present a framework for transporting MPEG-4 video, which includes source rate adaptation, packetization, feedback control, and error control. The main contributions of this paper are: 1) a feedback control algorithm based on Real Time Protocol (RTP) and Real Time Control Protocol (RTCP); 2) an adaptive source-encoding algorithm for MPEG-4 video which is able to adjust the output rate of MPEG-4 video to the desired rate; and 3) an efficient and robust packetization algorithm for MPEG video bit-streams at the sync layer for Internet transport. Simulation results show that our end-to-end transport architecture achieves good perceptual picture quality for MPEG-4 video under low bit-rate and varying network conditions and efficiently utilizes network resources.
Recognition of Chinese business cards
(1997)
Chiou, YH
;
Lee, HJ
;
交大名義發表
;
資訊工程學系
;
National Chiao Tung University
Business cards include many kinds of information such as name, address, and telephone number. In order to use the information effectively, it is necessary to extract the information from the cards automatically to build a data base. The goal of this paper is to extract and recognize characters from color business cards. To separate the foreground from the background in a card, we assign all pixels into eight color types. Then we calculate a dynamic threshold using the color information to extract the foreground. Next, we extract the characters by four steps: connected component extraction, local thresholding, mark, line and noise deletion and character grouping. Finally, we recognize the characters by a statistical Chinese and English character recognition systems. We test 30 business cards, which have Chinese characters, English characters, numerals and punctuation marks. The extraction rate and accuracy rate for our system are 96.97% and 95.43% respectively. The recognition rate is 88.78% for Chinese characters and 97.58% for English characters, numerals and punctuation marks.
Recognition-based handwritten Chinese character segmentation using a probabilistic Viterbi algorithm
(1999-08-01)
Tseng, YH
;
Lee, HJ
;
資訊工程學系
;
Department of Computer Science
This paper presents a recognition-based character segmentation method for handwritten Chinese characters. Possible non-linear segmentation paths are initially located using a probabilistic Viterbi algorithm. Candidate segmentation paths are determined by verifying overlapping paths, between-character gaps, and adjacent-path distances. A segmentation graph is then constructed using candidate paths to represent nodes and two nodes with appropriate distances are connected by an are. The cost in each are is a function of character recognition distances, squareness of characters and internal gaps in characters. After the shortest path is detected from the segmentation graph, the nodes in the path represent optimal segmentation paths. In addition, 125 text-line images are collected from seven form documents. Cumulatively, these text-lines contain 1132 handwritten Chinese characters. The average segmentation rate in our experiments is 95.58%. Moreover, the probabilistic Viterbi algorithm is modified slightly to extract text-lines from document pages by obtaining non-linear paths while gaps between text-lines are not obvious. This algorithm can also be modified to segment characters from printed text-line images by adjusting parameters used to represent costs of arcs in the segmentation graph. (C) 1999 Elsevier Science B.V. All rights reserved.