SCENIC BEAUTY ESTIMATION USING INDEPENDENT COMPONENT ANALYSIS AND SUPPORT VECTOR MACHINES


ABSTRACT

The main focus of this project is to estimate the scenic beauty of forest images using independent component analysis and support vector machines, two of the most valuable tools for multigroup classification and data reduction. This project originated from the United States Forest Service (USFS) to determine the scenic beauty of forests to preserve recreation and aesthetic resources in forest management. The results of this project would be useful to determine a predefined pattern to cut the trees so as to retain the scenic beauty even after cutting the forest for timber.The algorithm will be initially developed and tested in Matlab and later developed in C++. The software developed will be tested on 637 images available in the database to determine their scenic quality. Every image will be classified into one of the three classes: high scenic beauty class, medium scenic beauty class and the low scenic class. Results obtained will be compared with the Scenic Beauty Estimation using human subjective ratings.

Vijay Ramani, Xinping Zhang, Zhiling Long, and Yu Zeng
Department of Electrical and Computer Engineering
Mississippi State University
Email: {ramani, zhang, long, zeng}@cavs.msstate.edu
URL: http://www.cavs.msstate.edu/group_image/presentation/