Advanced Leaf Recognition Algorithm using Artificial Neural Network

Plant identification is an important field of biological and medical sciences. Medicinal plants must be classified and recognized with high accuracy. Classification errors can lead to high costs and losses. Several methods have been proposed so far for plant classification based on leaf image. Generally, the methods don't include all the physical attributes of the leaf which entails important information. In this paper, various characteristics shape, color, texture and vein have been computed which resulted in more reliable results. The use of neural networks in science has seen a huge revolution in the last decades. Neural networks have been introduced in different scientific applications and proved their high efficiency with minimum costs. The identification of plant's category of input images has been accomplished along with the classification of various plants into their respective categories. In this case, combined classifier using majority voting technique has been proposed for recognizing leaf's category along with SVM, Naïve Bay's and Decision tree classifiers. The experimental results show that combined classifier outperforms the performance of SVM; Naïve Bay's and Decision tree classifiers.