Gender Segregation of Silkworm Pupae Using Transfer Learning

In response to the imperative demand for precision in gender segregation of silkworm pupae within sericultural practices, this research endeavors to present a comprehensive model. Leveraging advanced techniques and transfer learning models such as InceptionV3, EfficientNet, DenseNet, VGG16, and Xception, our study addresses the critical need for an accurate and efficient solution. The model developed herein meticulously considers a spectrum of parameters including signal strength, pupal morphology, and pupal size to discern and classify genders with accuracy. The proposed methodology not only streamlines the pupal sorting process but also offers valuable insights into the broader applications of computer vision techniques in the field of entomology and agriculture. This research stands as a significant stride towards automated and precise gender classification, promising to revolutionize current sericultural practices for improved efficiency and productivity.