Recognition of Plant Species using Deep Convolutional Feature Extraction
share
There are more than 391,000 plant species currently known to global science, and it is challenging to distinguish among them. The identification of plant species requires in-depth surveyors and botanists who possess a tremendous amount of knowledge on native plant species. Therefore, plant recognition has become an interdisciplinary concentration in both botanical taxonomy and machine learning for a faster identification process. In this paper, a convolutional neural network system has been proposed to perform feature extraction using different deep learning models in large-scale plant classification methods. The plant image dataset was collected from the PlantCLEF2003 dataset, which consists of 51,273 images from 609 plant species. Four deep convolutional feature extraction methods, including Resnet50V2, Inception Resnet V2, MobilenetV2, and VGG16, are used to extract features from the images. A comparative evaluation of four deep learning models using two classification methods, Support Vector Machine (SVN) and k-nearest neighbor (KNN), is presented. With the highest accuracy of 95.6%, MobilenetV2 performed better than the other deep learning models for plant recognition in both SVM and KNN classification methods. Moreover, the SVM classifier has outperformed the KNN in terms of accuracy in the plant image recognition system. The outcomes are promising for further applications and future work gears towards experiments on a larger dataset with high-performance computing facilities to propose a higher accuracy system of plant image identification in natural environments.
READ FULL TEXT