A computer-based vision systems for automatic identification of plant species using kNN and genetic PCA

Abstract

Precision farming involves integration of different areas of disciplines to lower production costs and improve productivity. One major arm of precision farming or agriculture is the development of computer-based vision systems for automatic identification of plant species. This work involves application of k Nearest Neighbour (kNN) and genetic principal component analysis (GA-PCA) for the development of computer-based vision systems for automatic identification of plant species. As the first contribution, several image descriptors were extracted from the images of plants found in the Flavia dataset. Lots of these image features are affine maps and amalgamation of such massive features in one study is a novel idea. These descriptors are Zernike Moments (ZM), Fourier Descriptors (FDs), Lengendre Moments (LM) Hu 7 Moments, Texture, Geometrical properties and colour features. The GA-PCA (1907 x 41) feature space improved the classification accuracy of kNN from 84.98% to 88.75%.