Advancement in Sericulture Using Image Processing

The need for silk clothes is very high worldwide, and it is in high demand every year. To meet market demand, silkworm cocoons will be chosen much more often as the raw material for silk. The primary issue with the current scenario is that the identification procedure is ineffective. High-quality cocoons and faulty cocoons are now distinguished primarily by manual selection. To aid employees in choosing silkworm cocoons, automated optical equipment needs to be developed. Deep learning, particularly the YOLO algorithm, has been increasingly popular in recent years and has steadily replaced other techniques for classifying images. We created a data collection of silkworm cocoons and created a machine learning model to categorize them in order to construct a model for silkworm cocoon categorization. For conventional convolutional neural networks, the fully connected layer frequently houses the majority of the parameters for the entire model, requiring a significant amount of processing time and resources during forward propagation. Due to the fact that our suggested solution is a live capturing system, computational time is reduced. The live image of the cocoon is captured using a mobile camera. The proposed architecture yields a higher accuracy, as shown by experimental findings, making it possible to utilize cocoon categorization in industry very soon.