Hiroshi Shinjo

A recursive analysis for form cell recognition

It is very difficult to analyze form structures because of breaks in lines and additional noises in the form image. This paper focuses on cell recognition in low quality form images. The recognition method has two features to achieve robustness in cell recognition. One is grid representation using several types of intersection and the terminal points of the frame lines. The other is the recursive modification of the representation. A new representation is created according to the determination of the breaks in the line and the hypothesized location of the missed intersections by using the previous representation. The modification is processed recursively until the representation has perfect consistency and all form cells are detected. In an experiment using 1565 form samples, all cells in 1538 samples (98.3% of 1565 samples) were recognized correctly by this method.

Character Normalization Methods Using Moments of Gradient Features and Normalization Cooperated Feature Extraction

Normalization is a particular important preprocessing operation, and has a large effect on the performance of character recognition. One of the purposes of normalization is to regulate the size, position, and shape of character images so as to reduce within-class shape variations. Among various methods of normalization, moment-based normalizations are known to greatly improve the performance of character recognition. However, conventional moment-based normalization methods are susceptible to the variations of stroke length and/or thickness. In order to alleviate this problem, we propose moment normalization methods that use the moments of character contours instead of character images themselves to estimate the transformation parameters. Our experiments show that the proposed methods are effective particularly for printed character recognition.

Information Management System Using Structure Analysis of Paper/Electronic Documents and Its Applications

An information management system using analyzing document structure is presented. The purpose is simultaneous management of information in various paper and electronic documents. The system contains image document analysis, PDF document analysis, and HTML document analysis. The two applications are presented and the developed prototypes are described. One application is document summarization. The other application is table understanding to correlate data to items.

Simplified polynomial network classifier for handwritten character recognition

Class-specific feature polynomial classifier (CFPC), a variant of a polynomial classifier (PC), yields high classification accuracy especially in high dimensional feature spaces. However, the computational cost for classification in such a high dimensional space is rather expensive. To overcome this difficulty, we propose a simplified polynomial network (SPN) classifier that reduces the complexity of polynomial networks with little deterioration of classification accuracy. In experiments of handwritten digit recognition on USPS, SPN using features of 30.0 dimensions on average achieved higher classification accuracy and a classification speed about 12.8 times faster than CFPC using features of 250 dimensions. In experiments on MNIST, SPN using features of 40.0 dimensions on average achieved a classification speed about 2.0 times faster than CFPC using features of 100 dimensions with nearly the same classification accuracy.

Semi-supervised Clustering Framework Based on Active Learning for Real Data

In this paper, we propose a real data clustering method based on active learning. Clustering methods are difficult to apply to real data for two reasons. First, real data may include outliers that adversely affect clustering. Second, the clustering parameters such as the number of clusters cannot be made constant because the number of classes of real data may increase as time goes by. To solve the first problem, we focus on labeling outliers. Therefore, we develop a stream-based active learning framework for clustering. The active learning framework enables us to label the outliers intensively. To solve the second problem, we also develop an algorithm to automatically set clustering parameters. This algorithm can automatically set the clustering parameters with some labeled samples. The experimental results show that our method can deal with the problems mentioned above better than the conventional clustering methods.

Moment-Based Character-Normalization Methods Using a Contour Image Combined with an Original Image

Moment-based character-normalization methods are known to improve character-recognition accuracy. These methods use the moments of an input image, which has two dimensions because of the thickness of its stroke lines, to estimate transformation parameters, whereas character is essentially composed of one dimensional stroke lines. This implies that these methods overestimate the moments of the thick parts of character strokes. To solve this problem, moment-based normalization methods, which use the moments of a contour image of a character combined with the input image of that character, are proposed. To extract the contours of character strokes, two methods, chain code contour (CC) and gradient contour (GC), are used. Character-recognition experiments on two printed-character databases and on two handwritten-character databases show that the character-recognition accuracies of the proposed methods are comparable to or significantly higher than those of conventional methods. In particular, the proposed methods are more effective for printed-character recognition.