Lychee cultivar fine-grained image classification method based on improved ResNet-34 residual network

• Published in: Journal of agricultural engineering (Pisa, Italy) Vol. 55; no. 3
• Main Authors: Xiao, Yiming, Wang, Jianhua, Xiong, Hongyi, Xiao, Fangjun, Huang, Renhuan, Hong, Licong, Wu, Bofei, Zhou, Jinfeng, Long, Yongbin, Lan, Yubin
• Format: Journal Article
• Language: English
• Published: Bologna PAGEPress Publications 01.01.2024
• Subjects: Attention mechanism; Classification; Cultivars; Image classification; lychee classification; Receptive field; residual network; Transfer learning
• ISSN: 1974-7071; 2239-6268
• DOI: 10.4081/jae.2024.1593

Lychee, a key economic crop in southern China, has numerous similar-looking varieties. Classifying these can aid farmers in understanding each variety's growth and market demand, enhancing agricultural efficiency. However, existing classification techniques are subjective, complex, and costly. This paper proposes a lychee classification method using an improved ResNet-34 residual network for six common varieties. We enhance the CBAM attention mechanism by replacing the large receptive field in the SAM module with a smaller one. Attention mechanisms are added at key network stages, focusing on crucial image information. Transfer learning is employed to apply ImageNet-trained model weights to this task. Test set evaluations demonstrate that our improved ResNet-34 network surpasses the original, achieving a recognition accuracy of 95.8442%, a 5.58 percentage point improvement.