A Novel Approach for Weed Classification using Curvelet Transform and Tamura Texture Feature (CTTTF) with RVM classification

摘要

A weed is a surplus plant growing along with the useful agriculture products. These weed also consumes the water from the soil which will leads to the in sufficient water for the useful agro-products, hence these weeds should be identified earlier and removed. This paper present an efficient curvelet transform and patch level tamura texture feature extraction method for weed classification. The Relevance Vector Machine classification technique was developed for crop and weeds classification and weed separation. The results are compared Support Vector Machine and with Random Forest classifier technique. The proposed system outperforms all the other transform in terms of accuracy, specificity and sensitivity. Also, the result analysis reveals the fact that, as the weed discrimination accuracy as 99%.