Papaver somniferum and Papaver rhoeas Classification Based on Visible Capsule Images Using a Modified MobileNetV3-Small Network with Transfer Learning

• Published in: Entropy (Basel, Switzerland) Vol. 25; no. 3; p. 447
• Main Authors: Zhu, Jin, Zhang, Chuanhui, Zhang, Changjiang
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 03.03.2023; MDPI
• Subjects: Accuracy; Algorithms; Artificial intelligence; Classification; Datasets; Deep learning; Energy consumption; Identification; Identification methods; Learning; MobileNetV3-Small; Narcotics; Neural networks; Papaver rhoeas; Papaver somniferum; poppy capsule image dataset; Remote sensing; transfer learning; Unmanned aerial vehicles; Wavelet transforms; transfer learning; Papaver somniferum; identification; MobileNetV3-Small; poppy capsule image dataset; Papaver rhoeas
• ISSN: 1099-4300; 1099-4300
• DOI: 10.3390/e25030447

Traditional identification methods for and (PSPR) consume much time and labor, require strict experimental conditions, and usually cause damage to the plant. This work presents a novel method for fast, accurate, and nondestructive identification of PSPR. First, to fill the gap in the PSPR dataset, we construct a PSPR visible capsule image dataset. Second, we propose a modified MobileNetV3-Small network with transfer learning, and we solve the problem of low classification accuracy and slow model convergence due to the small number of PSPR capsule image samples. Experimental results demonstrate that the modified MobileNetV3-Small is effective for fast, accurate, and nondestructive PSPR classification.