Share Email Print
cover

Proceedings Paper

Shape from texture using a neural network incorporated with edge information
Author(s): Shinya Tatsumi; Yasuhiro Okano; Takahide Kayanuma; Nozomu Hamada
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, we propose a method of Shape from Texture. There are some major approaches to estimate 3D shape. Our method uses the peak frequency for feature of texture, as it is known to be used in human perception. Our proposed system is composed of 1D and 2D system. The 1D system estimates a local peak frequency is composed of two steps. First is the feature extraction step. For extracting the feature of image, we use 16 Gabor filters with successive Gauss filters as post smoothing filter. Second is the estimation of a local peak frequency step with neural network. A local peak frequency is estimated from the neural network. We use a three layer network whose parameters are determined by Back Propagation network training. By using neural network, the performance of 16 Gabor filters is demonstrated as efficient as that with more filters. We use this algorithm for separate orientation channel. 2D system inhibits estimated local peak frequency of 4 orientations in 1D system. And we estimate 3D shape from the ratio of local peak frequencies in 2D. This system is not effective for the estimation near object edge. Then, we use Edge information for improving the method.

Paper Details

Date Published: 9 March 1999
PDF: 10 pages
Proc. SPIE 3647, Applications of Artificial Neural Networks in Image Processing IV, (9 March 1999); doi: 10.1117/12.341114
Show Author Affiliations
Shinya Tatsumi, Keio Univ. (Japan)
Yasuhiro Okano, Keio Univ. (Japan)
Takahide Kayanuma, Keio Univ. (Japan)
Nozomu Hamada, Keio Univ. (Japan)


Published in SPIE Proceedings Vol. 3647:
Applications of Artificial Neural Networks in Image Processing IV
Nasser M. Nasrabadi; Aggelos K. Katsaggelos, Editor(s)

© SPIE. Terms of Use
Back to Top