Flower Recognition System with Optimized Features for Deep Features

Looking at nature, flowers are everywhere. Classification is a difficult task, as the flowers have a large number of species that are very similar to each other in shape, appearance and color. Classification of flowers can be used in various fields of application such as product monitoring, flower identification, medicinal flowers, floriculture industry, plant taxonomy. In the study, a dataset with 4317 images from 5 types of flowers was used. In the classification study carried out in three stages, deep features were extracted from images with the SqueezeNet deep learning architecture of the transfer learning approach in the first stage. In the second stage the 1000 extracted features were classified using Neural Network and Logistic Regression methods from machine learning techniques. In the third stage, the deep features extracted were optimized with the help of particle swarm algorithm and the 488 features obtained were classified using machine learning Neural Network and Logistic Regression methods again. When the results obtained at both stages were compared, it was observed that the classification with the optimized features improved the success performance. The classification success of the features obtained by deep feature extraction was obtained as 85.1% by Neural Network and 79.7% by Logistic Regression method. In the classification results performed with the optimized features, the classification success was determined as 90.1% for Neural Network and 84.2% for Logistic Regression. The effect of optimized features on classification success is also understood in the study.