Compartmentalization of Wheat Cultivars by Employing Computer Vision

Machine learning methods majorly comprise image processing and soft computing methods and are mainly responsible for automation. Wheat production is influenced by assorted varying factors. A basic requisite for best production is the seed. Sorting or grading of agricultural products influenced by computer varies product wise and even product variety wise which changes region wise. Grading for new varieties released by the agricultural scientist is the major concerned as new varieties are produced by crossing existing varieties and for these proven optimized machine learning algorithms may give an adverse result. This book highlights various applications of image processing in agriculture and introduces a machine learning algorithm capable of classifying major 5 wheat cultivars (TRITICUM ¿ DURUM: GDW 1255 (released in 2013 by ICAR) & TRITICUM ¿ AESTVIUM: GW 273, GW 322, GW 496 & LOK 1) cultivated in Gujarat region. Experimental data consist of 11 traits comprised of shape, color & morphological characteristics. After applying feature selection algorithm,5 traits were considered & LM backpropagation was used to classify above wheat cultivars which ensued to more than 90.0% accuracy.