Transfer Learning with Deep Convolutional Neural Network for Automated Plant Identification

Abstract

Automated plant identification enables experts to process significantly greater numbers of plants with higher efficiencies in shorter periods. It is time-consuming and difficult to determine the name of species based on observations, even for botanist experts. However, plant recognition is a kind of fine-grained visual recognition problem, which is relatively harder than conventional image recognition. To solve this problem, we present a solution that transfers the learning information from a Deep Convolutional Neural Network (DCNN) trained on the ImageNet database, which contains millions of images, for automated plant identification based on flower and fruit images. First, we modify the last three layers of the pre-trained network to adapt ResNet-50 model to our classification task and replace the fully connected layer in the original pre-trained network with another fully connected layer, in which the output size represents the class of plants. Second, we use transfer experience and fine-tuned pre-trained DCNN for experiments using flower and fruit images. Finally, we evaluate the proposed network on two available botanical datasets: the Oxford flowers dataset with 102 classes and the HNPlant flowers and fruits dataset with 20 classes and determine the optimal values of the associated hyperparameters to improve the overall performance. Experiment results demonstrate that the highest classification accuracies exhibited by the proposed model on the Oxford-102 and HNPlant-20 datasets are 92.4% and 95.0%, respectively, thus establishing their effectiveness and superiority.