Species Identification and Classification of Rose Flower Images Using Convolutional Neural Network and K-Means Clustering Algorithm

Abstract

The proposed work in this presented paper aims to identify and classify the rose species from the rose image. In my research title “Species Identification and Classification of Rose Flower Images Using Convolutional Neural Network and K-Means Clustering Algorithm”, this experiment is conducted with a k-means clustering algorithm and convolutional neural network. The proposed work in this presented paper aims to identify and classify the rose species such as Old Garden and New Garden from the rose flower images. The experiment is conducted with a k-means clustering algorithm and convolutional neural network. The proposed work is approached in two ways. Firstly, the rose images are preprocessed by Adobe Photoshop. Secondly, the rose images are segmented multiple K values by the k-means clustering algorithm so that defective leaves are accurately recognized for classification. Furthermore, the K-means segmented images (k=8) and normal preprocessed images are employed by the classifier algorithm named convolutional neural network. As a result, the K cluster value (k=8) and normal preprocessed images give the accuracy that is 72% and 73% respectively. Finally, the results are compared with respect to the K cluster value and normal preprocessed image that extracted the standard normal preprocessed. The normal preprocessed image gives 1% better accuracy than the k-means cluster segmented image.