Masashi Koga

Lexicon-driven segmentation and recognition of handwritten character strings for Japanese address reading

This paper describes a handwritten character string recognition system for Japanese mail address reading on a very large vocabulary. The address phrases are recognized as a whole because there is no extra space between words. The lexicon contains 111,349 address phrases, which are stored in a trie structure. In recognition, the text line image is matched with the lexicon entries (phrases) to obtain reliable segmentation and retrieve valid address phrases. The paper first introduces some effective techniques for text line image preprocessing and presegmentation. In presegmentation, the text line image is separated into primitive segments by connected component analysis and touching pattern splitting based on contour shape analysis. In lexicon matching, consecutive segments are dynamically combined into candidate character patterns. An accurate character classifier is embedded in lexicon matching to select characters matched with a candidate pattern from a dynamic category set. A beam search strategy is used to control the lexicon matching so as to achieve real-time recognition. In experiments on 3,589 live mail images, the proposed method achieved correct rate of 83.68 percent while the error rate is less than 1 percent.

Gabor feature extraction for character recognition: comparison with gradient feature

Gabor filter feature has been applied to character recognition but was not compared with the best direction feature: gradient feature. In this paper, we propose a principled method for implementing Gabor filters for character feature extraction and compare the recognition performances of Gabor feature and gradient feature on three databases. The results show that Gabor filters with low orientation sensitivity and broad frequency band favor recognition accuracy. The Gabor feature performs comparably or better than the gradient feature on two of the three databases, but is inferior on the rest one.

A high-speed algorithm for propagation-type labeling based on block sorting of runs in binary images

A fast algorithm for component labeling of binary images is proposed. Component labeling is an important method for separation of objects in document image understanding, especially in character and picture extraction. The proposed algorithm is based on sorting and tracking of runs and label propagation to the connected runs. Each scan line is partitioned into small segments, i.e. blocks and runs on the scan line are sorted according to the block sequence to speed up tracking of runs. It was ascertained by experiment that the processing time is 16.7 times faster than that of the conventional pixel-based labeling method.<<ETX>>

Towards high accuracy road maps generation from massive GPS Traces data

We present a novel approach to dynamically generate high accuracy road maps through the statistical analysis of in- vehicle GPS trace data. Our approach opens a possibility to implement an optional system in a very economic way for mapping roads to support the applications in Intelligent Transportation Systems (ITS). The results presented in this paper show the potential with respect to the map update technology.

Camera-based Kanji OCR for mobile-phones: practical issues

A camera based optical character reader (OCR) for Japanese Kanji characters was implemented on a mobile phone. This OCR has three key features. The first is discriminative feature extraction (DFE) which enables a character classifier needing only small memory size. The second is a word segmentation method specially designed for looking up Japanese words in a dictionary. The third feature is a GUI suitable for a mobile phone. A prototype mobile phone Kanji OCR was constructed and experimentally tested. Recognition accuracy of over 95% was obtained under the best conditions, which shows the potential of our prototype as a new type of electronic dictionary.

Building compact classifier for large character set recognition using discriminative feature extraction

In this paper, we propose an approach to building compact classifier for camera-based printed Japanese character recognition on mobile phones. We design feature vector prototypes using learning vector quantization (LVQ) for achieving high accuracy, while the complexity is lowered by linear dimensionality reduction. The discriminative feature extraction (DFE) strategy, which optimizes both subspace axes and classifier parameters, is shown to yield high classification accuracy even on low dimensional subspace. On a 120D sub-space, a 4,344-class classifier consumes only 613KB storage, and an accuracy of 99.41% was obtained on a test set.

Aspect Ratio Adaptive Normalization for Handwritten Character Recognition

The normalization strategy is popularly used in character recognition to reduce the shape variation. This procedure, however, also gives rise to excessive shape distortion and eliminates some useful information. This paper proposes an aspect ratio adaptive normalization (ARAN) method to overcome the above problems and so as to improve the recognition performance. Experimental results of multilingual character recognition and numeral recognition demonstrate the advantage of ARAN over conventional normalization method.

Lexical Search Approach for Character-String Recognition

A novel method for recognizing character strings, based on a lexical search approach, is presented. In this method, a character string is recognized by searching for a sequence of segmented patterns that fits a string in a lexicon. A remarkable characteristic of this method is that character segmentation and character classification work as subfunctions of the search. The lexical search approach enables the parameters of character classifier to adapt to each segmented pattern. As a result, it improves the recognition accuracy by omitting useless candidates of character classification and by changing the criterion of rejection dynamically. Moreover, the processing time is drastically reduced by using minimum sets of categories for each segmented pattern. The validity of the developed method is shown by the experimental results using a lexicon including 44,700 character strings.

A recognition method for touching Japanese handwritten characters

Describes a method for recognizing Japanese handwritten characters, including touching ones. The touching characters are segmented by cutting the connected components in a pre-segmentation process. The proposed segmentation method consists of the following steps: (1) identification of the touching components by checking the size of candidate character patterns; (2) estimation of the breakpoint and cutting of the components; and (3) generation of candidate character patterns by merging the components with adjacent patterns. The proposed method has the feature that the touching components can be identified even if they are comprised of relatively small patterns. The touching components are cut by using stroke width analysis and projection image analysis. This cut-and-merge procedure was able to segment 134 (88.2%) address lines correctly out of 152 Japanese address lines having touching portions, and could generate correct candidate character patterns.

Segmentation of Japanese handwritten characters using peripheral feature analysis

A method of character segmentation of Japanese handwritten characters has been developed. It is effective especially in character recognition with the over-segmentation process. The method is based on the credibility measurement of each presegmented pattern for being a true character by analyzing peripheral features such as gaps between patterns and widths and heights of patterns. A heuristic statistical method is applied to the analysis. Experimental results show that the developed method increases the accuracy of character segmentation. It is effective especially when no linguistic feedback to segmentation is available and/or the character classifier ability is not high enough. In such cases, the recognition accuracy is increased from 30% to 70% by the new segmentation method.