Work

Object Recognition Using Artificial Fish Swarm Algorithm on Fourier Descriptors

Year: 2015

Type: preprint

Abstract: In this paper, we present an Artificial Fish Swarm Algorithm is a class of an evolutionary optimization technique with three types of classifier combinations using different geometrics’ shape for the recognition of the plant leaves. Fish Swarm Algorithm is applied on Fourier descriptors to get optimum weights that maximize the recognition rate. Fourier descriptors are invariant to rotation, translation or scaling. These optimum Fourier descriptors are then used in process of recognition. The obtained results achieve a recognition rate of 98.75% for Log of Euclidean Distance classifier. Results show that our proposed system advances object recognition with highly effective.

Source: SSRN Electronic Journal

Authors: Hamid Alasadi, Majida Ali Abed

Institutions: Institute of Electrical and Electronics Engineers, University of Tikrit

Language: English

Topic: Image Retrieval and Classification Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2191214601

Cites: 19

Cited by: 3

Related to: 10