Abstract:
In this paper, a bark recognition algorithm for plant classification is presented. A Least-Square Support Vector Machine (LSSVM) with image and data processing techniques...View moreMetadata
Abstract:
In this paper, a bark recognition algorithm for plant classification is presented. A Least-Square Support Vector Machine (LSSVM) with image and data processing techniques is used to implement a general purpose automated classifier. Using a data base of 40 sections of photographs taken of each of the 23 species, we applied an algorithm to homogenize the illumination of the images. After applying it, we obtained a 256-elements array from the Local Binary Pattern (LBP) histogram. Each element of the array was introduced in the LSSVM for classification. The success rate of the resultant recognizer is 82.38%.
Date of Conference: 11-13 August 2016
Date Added to IEEE Xplore: 20 March 2017
ISBN Information: