Leaf Recognition Based on Joint Learning Multiloss of Multimodel Convolutional Neural Networks: A Testing for Vietnamese Herb. (24th September 2021)

• Record Type: Journal Article
• Authors: Dat, Trinh Tan; Le Thien Vu, Pham Cung; Truong, Nguyen Nhat; Anh Dang, Le Tran; Thanh Sang, Vu Ngoc; Bao, Pham The
• Other Names: Yi Yugen Academic Editor.
• Is Part Of: Computational intelligence and neuroscience. Volume 2021(2021)
• Publication Date: 2021-09-24
• Subjects: Neurosciences -- Data processing -- Periodicals; Computational intelligence -- Periodicals; Computational neuroscience -- Periodicals; 612.80285
• DOI: 10.1155/2021/5032359
• Languages: English
• ISSNs: 1687-5265

Abstract

Abstract : A new modification of multi-CNN ensemble training is investigated by combining multiloss functions from state-of-the-art deep CNN architectures for leaf image recognition. We first apply the U-Net model to segment leaf images from the background to improve the performance of the recognition system. Then, we introduce a multimodel approach based on a combination of loss functions from the EfficientNet and MobileNet (called as multimodel CNN (MMCNN)) to generalize a multiloss function. The joint learning multiloss model designed for leaf recognition allows each network to perform its task and cooperate with the others simultaneously, where knowledge from various trained deep networks is shared. This cooperation-proposed multimodel is forced to deal with more complicated problems rather than a simple classification. Therefore, the network can learn much rich information and improve its generalization capability. Furthermore, a multiloss trade-off strategy between two deep learning models can reduce the effect of redundancy problems in ensemble classifiers. The performance of our approach is evaluated by our custom Vietnamese herbal leaf species dataset, and public datasets such as Flavia, Leafsnap, and Folio are used to build test cases. The results confirm that our approach enhances the leaf recognition performance and outperforms the current standard single networks while having less low computation cost.