To search, Click below search items.


All Published Papers Search Service


Species and Variety Classification of Leaves from Images


Malay S. Bhatt, Tejas P. Patalia


Vol. 17  No. 1  pp. 109-116


Content Based Image Classification has produced many successful and automated applications in agricultural science like fruits and vegetable classification, wood type detection, plant disease detection, soil type recognition and cashew grade classification. In this paper, classification of the leaves is carried out. The proposed framework creates a fixed size descriptor of size 1632. The descriptor is composed of Local Binary Pattern, Generalized Co-occurrence Matrix properties, and edge detection. Once a feature vector is constructed, classification is performed using linear Support Vector Machine. The system is tested using leaves database having 40 leaf species. The proposed system is implemented in MATLAB and achieves the average accuracy of 99%.


Classification, Edge Detection, Generalized Co-Occurrence Matrix, Histogram, Local Binary Pattern, Support Vector Machine.