Recognition of Leaf Image Based on Ring Projection Wavelet Fractal Feature

摘要

Recognizing plant leaves has been an important and difficult task. This paper introduces a method of recognizing leaf images based on Ring Projection Wavelet Fractal Feature. Firstly, we apply pre-processing to leaf images, and extract from leaves around the border area by the white pixels and all pixel black background binary contour map. Secondly, we get one-dimensional feature of leaves by using Ring Projection to reduce the dimension of two-dimensional pattern. Then, the one-dimensional is decomposed with Daubechies discrete wavelet transform to obtain sub pattern. Finally, we seek the fractal dimension of each sub model. Leaf shape features are extracted from pre-processed leaf images, which include fractal dimension of each sub model and seven Hu moment invariants. As a result there are 30 classes of plant leaves successfully classified.