Leaf classification with improved image feature based on the seven moment invariant

Abstract

Plants can be classified based on its leaves shape. The classification process is required well data extraction feature, so it needs fixing feature process at the pre-processing level. Combining median filter and image erosion is used for fixing the feature process. Whereas for feature extraction is used invariant moment method. In this research, it is used leaves classification based on leaves edge shape. K-Nearest Neighbor Method and Naïve Bayes Classifier are used for leaves classification process. Testing the result of leaves classification from an image which is on dataset has been built to get accuracy value about 84% using Naive Bayes classifier while using K-Nearest Neighbor the get accuracy value of about 84%.