Plant classification using SVM classifier

The plants play an important role in nature, this paper deals with the plant identification and classification. So, in this paper we are classifying the plants based on colour histogram, edge detection and direction features using support vector machine (SVM) classifier. The feature extraction helps in extracting the features which help in analysis of an image classification. Colour histogram feature is easy to compute and is effective in characterizing the distribution of the colour in an image. The Edge Histogram (EH) is the feature uses the sobel operator to capture the spatial distribution of edges. The edge histogram has eight bins corresponding to the sobel filters to count the number of edge pixels in eight directions. These features will be stored in database which contains 100 plant images. The feature vector is trained and tested with 100 plant images. The support vector machines (SVM) are superior of all machine learning algorithms and the overall percentage of the classification accuracy is 78%.