Classification Flower Images Based on Deep Learning and Machine Learning

Image classification has grown increasingly popular due to the growing significance of machine learning and deep learning. Flower images may sometimes exhibit resemblances in terms of hue, form, and visual characteristics. The problem lies in the classification of flowers. This work employs a hybrid approach that integrates deep learning and machine learning techniques to classify 17 discrete flower species. In order to do this, we utilised the ResNet_50, PCA, and SVM architecture to classify several species from the “Oxford-17” dataset. With this goal in mind, we have made efforts to improve our model in order to get more accuracy compared to similar methods. Prior to inputting our images into our pretrained model, we resized them, and subsequently fine-tuned the model. The dataset was partitioned into two distinct sets: a training set and a testing set. We attained a precision rate of 95.58% while utilising the “Oxford-17” dataset. Our approach outperformed previous machine learning and deep learning-based methods on this dataset.