Automatic image orientation determination with natural image statistics
Author:
Open Access
- 6 November 2005
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 491-494
Abstract
In this paper, we propose a new method for automatically determining image orientations. This method is based on a set of natural image statistics collected from a multi-scale multi-orientation image decomposition (e.g., wavelets). From these statistics, a two-stage hierarchal classification with multiple binary SVM classifiers is employed to determine image orientation. The proposed method is evaluated and compared to existing methods with experiments performed on 18040 natural images, where it showed promising performance.Keywords
This publication has 3 references indexed in Scilit:
- How realistic is photorealistic?IEEE Transactions on Signal Processing, 2005
- Image compression via joint statistical characterization in the wavelet domainIEEE Transactions on Image Processing, 1999
- Automatic image orientation detection1999