Shape from texture using a neural network incorporated with edge information

Shinya Tatsumi; Yasuhiro Okano; Takahide Kayanuma; Nozomu Hamada

doi:10.1117/12.341114

9 March 1999 Shape from texture using a neural network incorporated with edge information

Shinya Tatsumi, Yasuhiro Okano, Takahide Kayanuma, Nozomu Hamada

Proceedings Volume 3647, Applications of Artificial Neural Networks in Image Processing IV; (1999) https://doi.org/10.1117/12.341114
Event: Electronic Imaging '99, 1999, San Jose, CA, United States

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.

Citation Download Citation

Shinya Tatsumi, Yasuhiro Okano, Takahide Kayanuma, and Nozomu Hamada "Shape from texture using a neural network incorporated with edge information", Proc. SPIE 3647, Applications of Artificial Neural Networks in Image Processing IV, (9 March 1999); https://doi.org/10.1117/12.341114

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available