Masaaki Yoneda

Character string extraction from color documents

Abstract A new algorithm for the extraction of character strings from color documents is proposed. We first divide a full color image into several representative binary color images. Then, character strings are nominated from each binary image by using multi-stage relaxation. However, the nominated strings are not always characters. They may be a part of the background, concatenated holes of characters, or dotted lines, etc. Therefore, when all nominated strings of all binary images are superimposed, some strings overlap each other. So, we selected the appropriate strings from them using the likelihood of a character string and two kinds of conflict resolution. In the experiments, we used color images like magazine covers, posters, etc. After applying color segmentation and the multi-stage relaxation, many character strings were nominated. Next, some adequate strings were selected. Finally, we show the experimental results and discuss some problems of extracting character strings from a color document.

Real-time snowfall noise elimination

We propose a new method that removes snowfall noise from successive images recorded by a TV camera. This method utilizes the size and velocity of a moving object. The intensity of a pixel changes when an object passes over the pixel. Snow particles pass a pixel very quickly due to their small size. Therefore, after holding the odd number of video frames, they are sorted by intensity in each pixel independently. Then we can obtain the background intensity of the pixel by taking the median intensity from them. This was confirmed by experiments. We also proposed a stochastic model of this algorithm. By comparison between a measurement value and the model, we obtained the agreement with each other. Furthermore, we consider the effect for the other moving objects. Experimental results are also shown.

Color segmentation for text extraction

Abstract.The capability of extracting and recognizing characters printed in color documents will widen immensely the applications of OCR systems. This paper describes a new method of color segmentation to extract character areas from a color document. At first glance, the characters seem to be printed in a single color, but actual measurements reveal that the color image has a distribution of components. Compared with clustering algorithms, our method prevents oversegmentation and fusion with the background while maintaining real-time usability. It extracts the representative colors based on a histogram analysis of the color space. Our method also contains a selective local color averaging technique that removes the problem of mesh noise on high-resolution color images.

Recognition of rotated characters by Eigen-space

In this paper, we present a method of recognizinginclined, rotated characters. First we construct an eigensub-space for each category using the covariance matrixwhich is calculated from a sufficient number of rotatedcharacters. Next, we can obtain a locus by projectingtheir rotated characters onto the eigen sub-space andinterpolating between their projected points. An unknowncharacter is also projected onto the eigen sub-space ofeach category. Then, the verification is carried out bycalculating the distance between the projected point ofthe unknown character and the locus. In our experiment,we obtained quite good results for the CENTURY font of26 capital letters of the English alphabet (A, B, .... ,Z).This method has the added advantage of obtaining therecognition result (category) and angle of inclination atthe same time

1/ f fluctuation in the “Game of Life”

Abstract The Fourier power spectra are examined for the Game of Life and its variants. The results show that only the Game of Life exhibits fluctuation. By means of observing patterns and measuring entropy and difference pattern spreading rate, we conclude that the Game of Life only belongs to Wolframs class-IV cellular automata which are thought to be capable of supporting universal computation. This predicts a connection between fluctuation and computational universality.

Alignment of free layout color texts for character recognition

A realignment algorithm for irregular character strings on color documents is proposed. Color documents often contain poorly aligned texts such as inclined or curved texts sometimes with distortion. In order to recognize them, we classify these texts into five types. After determining the type, we realign all the characters in a text horizontally, then test them with an ordinary character recognition method. Lastly, we show some experimental results for texts extracted from real color documents and discuss some causes of misrecognition.

Character string extraction from a color document

An algorithm for the extraction of character strings from a color document is proposed. We first divide the full color image of a document into several representative color images. Then, character strings are nominated from each binary image by using multi-stage relaxation. However, the nominated strings are not always characters. Therefore, when all nominated strings of all images are superimposed, some strings overlap each other. So, we selected the appropriate strings from them using a likelihood of a character string and two binds of conflict resolution. Finally, we show the results of the experiments and discuss some problems of character string extraction from a color document.

A new robust quadratic discriminant function

We propose a new quadratic discriminant function. It is devised based on the fact that eigenvalues of a sample covariance matrix are biased estimates of true eigenvalues. First, we rectify the biased eigenvalues. Then we construct a new covariance matrix whose eigenvalues are the rectified ones. Our quadratic discriminant function uses the covariance matrix. In a two-dimensional normal case, we show by a Monte Carlo method that our discriminant function works effectively, especially in the case of a small sample size.

A proposal for a face plane

Changes in facial expressions or differences in individual faces appear not only in distinctive features such as eyes, nose and mouth but also in the bone structure or the movement of facial muscles. We present a new concept that reflects the differences of the bone structure of a face and/or the movement of facial muscles and name this a face plane. The face plane can be described by a few parameters and reduce vague facial features. This paper describes the concept and the way of calculation of the face plane.

Character string extraction by multi-stage relaxation

An extraction algorithm for character strings is proposed. We first obtain a set of eight-connected components from a document image. For the components, we apply a relaxation method. The method makes mutual connections between components increase or decrease depending on the state of the neighboring components. While applying the relaxation method several times, the process proceeds from a local connection to a global connection, and finally character strings are extracted. We call this process multi stage relaxation. The advantages of this algorithm are that it does not need to nominate character components from an image beforehand, it is adaptive for character size and font, and it can also cope with a document which includes strings with various orientations. In our experiments we use a color image of a magazine cover and a monochromatic image of a graph. For the color image, the multi stage relaxation was executed for each binary image obtained by color segmentation. Lastly, we show the results of the experiments and discuss the effectiveness of our method.