Taizo Iijima

A Theory of Character Recognition by Pattern Matching Method

Character recognition is a categorizing process of unknown input pattern into one of known finite number of character categories. Various practical methods of realizing this process has been devised. Pattern matching method is one of the most commonly used techniques in which the similarity of input pattern is tested with the reference pattern of each category.

OK-Quantization theory and its relationship to sampling theorem

OK-Quantization Theory for the digitization in value ensures the reconstructivity of the probabilistic density function of the image. This paper shows some experimental demonstrations to reduce the number of the gray levels, and shows mainly that there is a necessary analytical relationship between sampling and quantization based on the equivalence relationship between two kinds of the integral, Riemann and Lebesgue integrals for calculating the volume of the image. Experimental demonstrations are also shown in this paper.

Redundancy of projection data and its application to improve the quality of a reconstructed image

This paper attempts to apply the actual redundancy involved in X-ray CT projection data which have been treated as independent data for the improvement of the image quality of a reconstructed image. It is known that the projection data of an X-ray CT contains random noise, such as photon noise, which has a negative effect on image quality. A simple smoothing filter which generally is used to reduce this effect, causes the degradation of image resolution. Therefore, it is possible to suppress only high-frequency noise components. However, when the structure of the projection data was analyzed, it became clear that projection data contain a large redundancy in determining the lower-frequency components of the image. By properly taking advantage of this redundancy for image reconstruction, it is possible to suppress the low-frequency component. This paper clarifies quantitatively the noise suppression effect using redundancy by comparing the case where redundancy is not used at all with the case where redundancy is used completely.

A Theory Of Pseudo-Orthogonal Bases And Its Application To Image Transmission

A theory of pseudoorthogonal bases is proposed, which is an extended concept of orthogonal bases. Ampseudoorthogonal base in an N-dimensional Hilbert space consists of M (⟨ N ) vectors { pm }m=1 satisfying the following equation for any f in the Hilbert space: