In pattern recognition, it is often necessary to deal with problems to classify a transformed pattern. A neural pattern recognition system which is insensitive to rotation of input pattern by various degrees is proposed. The system consists of a fixed invariance network with many slabs and a trainable multilayered network. The system was used in a rotation-invariant coin recognition problem to distinguish between a 500 yen coin and a 500 won coin. The results show that the approach works well for variable rotation pattern recognition.

A rotation-invariant neural pattern recognition system, which can recognize a rotated pattern and estimate its rotation angle, is considered. It is well-known that humans sometimes recognize a rotated form by means of mental rotation. The occurrence of mental rotation can be explained in terms of the theory of information types. Therefore, we first examine the applicability of the theory to a rotation-invariant neural pattern recognition system. Next, we present a rotation-invariant neural network which can estimate a rotation angle. The neural network consists of a preprocessing network to detect the edge features of input patterns and a trainable multilayered network. Furthermore, a rotation-invariant neural pattern recognition system which includes the rotation-invariant neural network is proposed. This system is constructed on the basis of the above-mentioned theory. Finally, it is shown that, by means of computer simulations of a binary pattern and a coin recognition problem, the system is able to recognize rotated patterns and estimate their rotation angle.

In this paper, a new image restoration approach using the Akamatsu transform is presented. In the method, by using repeated simple calculations based on the Akamatsu transform, an out-of-focus blurred image can be restored and sharpened. Out of focus is a major problem bothering many people in photography, especially the amateurs. There exits some solution to this problem on both the hardware and software sides. However, none offers a perfect solution. The Akamatsu transform can easily be embedded into hardware to offer faster processing due to its simplicity. Although, initially proposed for speech processing, this paper show the effectiveness of the transform in image processing. The Akamatsu transform is a combination of integral and differential transforms. The algorithm can be effective tools for image restoration in realtime image processing.

No abstract

SUMMARYThis paper presents a method for gender and age estimation which is robust to changing facial pose. We propose a feature point detection method, called the adapted retinal sampling method (ARSM), and a feature extraction method. A basic concept of the ARSM is to add knowledge about the facial structure to the retinal sampling method. In this method, feature points are detected on the basis of seven points corresponding to facial organs from a facial image. The reason why we used seven points as the basis of feature point detection is that facial organs are conspicuous in the facial region, and are comparatively easy to extract. As features robust to changing facial pose, skin texture, hue, and the Gabor jet are used for gender and age estimation. For classification of gender and estimation of age, we use a multilayered neural network. We also examine the left-right symmetry of faces in connection with gender and age estimation by the proposed method.

In p a t t e r n r e c o g n i t i o n , w e must o f t e n d e a l with problems to c l a s s i f y a transformed p a t t e r n . In t h i s paper. w e p r o p o s e a pat tcrn rcc-ogiiil i o n systcm w h i c h is i n s e n s i t i v e t o r o t a t i o n of i n p u t p a t t e r n by v a r i o u s degrccs. 'l'tie S Y S I CIII c:oiisisLs ol' a l'ixed invariance network with many s l a b s and a t r a i n a b l e multilayered network. 'I'o i l l u s t r a t e t h e e f f e c -Liveiiess of' t h e system, w e a p p l y i t to a rotation-irrvarIaiit c : o I n recogiiiLlon between 500 yen aiid 500 won coins. The results oP coniputer siiiiulatioii show Ltiat a iieural iiclwork i~~~~> r o i i c * I i w l l 1 tw iisoPi11 In rol.tlt.lon i t i v r i r l i t i i t ~I ; I I I i'rii r~v~~g i i l l Ioii.

No abstract

No abstract