A semi automatic plant identification based on digital leaf and flower images

This paper present a framework for semi automatic plant identification technique based on different flower and leaf images. A single feature is not sufficient for classification and recognition. Flower and leaf of different plant are different in shape, color, texture. This paper propose an algorithm for identification using multiclass classification based on color, shape volume and cell feature. Three stage comparisons: first stage compares Redness, Greenness, Blueness index feature, second stage compare shape feature and the last compare Cell feature and Volume fraction feature. Experiment is performed on a sample of diverse collection of 1000 leaf and flower images. Recognition rate is up to 85% percent on an average.