Hiromitsu Takahashi

Associative memories in cellular neural networks using a singular value decomposition

Using various templates, many applications of cellular neural network (CNN), such as a feature extraction, an edge detection and a pattern classification have been considered. In a Hopfield network, an image to be stored corresponds to the minimum value of the energy of the network. However, in CNN, an image corresponds to the equilibrium state of a differential equation. A synthesis procedure for designing a CNN that will store a set of desired vectors as memory points using a singular value matrix decomposition is considered. Also analyzed here is the indeterminate phenomenon of the equilibrium states of some cells that arise in the case in which more than two similar patterns are stored for Chinese characters.

A Far Road Sign Recognition by Applying Super-Resolution to Extracted Regions from Successive Frames

In the field of ITS technology, many methods have been proposed for detecting and recognizing road signs from car-mounted cameras. Most of these techniques are, however, for only still images. Therefore, the recognition results are affected by occasional changes of light conditions or occlusions. Moreover, though recognition of far placed signs are meaningful for safety driving, these signs are taken in low resolution images which that they are hardly recognition. In this article, we propose a novel technique for recognizing road signs. In this technique, a series of low resolution images of a road sign is extracted by using CONDENSATION from successive frames. Then, a pseudo-high resolution image of the road sign is generated by super-resolution using the series of images. The proposed techniques lead to early recognition results for far road signs even on images which are failed by traditional techniques.

Classification Method by Using the Associative Memories in Cellular Neural Networks

This paper deals with a classification problem, such as medical diag-nosis, which classes are defined by categorical forms. Classification should be done by careful and synthetical judgement for a lot of characteristic values taking each individual variations into account. We use the associative memory function of the cellular neural networks to classify by means of remembering one category from among the preregistered categories.