Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
482661 | European Journal of Operational Research | 2006 | 13 Pages |
Abstract
This paper presents a new, scaling and rotation invariant encoding scheme for shapes. Support vector machines (SVMs) and artificial neural networks (ANNs) are used for the classifications of shapes encoded by the new method. The SVM classification accuracy rate is 95.9 ∓ 2.9% in 14 categories and 79.2 ∓ 2.1% in 40 categories. This shows that SVM is one of the best tools for classification problems. The experimental results showed that SVM achieved better performance than ANN. A sensitivity test is performed to show that SVM is quite robust against different parameter values. In addition, our coding method is comparable to previous coding scheme in terms of SVM and ANN performance.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Science (General)
Authors
Wai-Tak Wong, Sheng-Hsun Hsu,