Towards Automatic Defect Detection in Sugarcane Billets from Images

Sugarcane billets are shorter segments of cane harvested and used globally for plantations. Due to such a mechanical approach, billets are often damaged and directly impact crop yield. Hence, automatic identification of sugarcane billet quality is a fundamental problem in the context of intelligent farming. Many familiar convolutional neural network (CNN) architectures are used for image classification tasks in the literature. This paper proposes an improved deep neural network architecture, SBDNet (Sugarcane Billet Diagnosis Network), that takes an image of the sugarcane billet as input and labels it healthy or damaged. We have conducted experiments on three different sugarcane billet varieties and obtained an overall accuracy of 73.81%. We have compared our work with recently published works on the same domain and got a 3% overall performance accuracy gain. The proposed SBDNet also shows impressive outcomes relating to the number of parameters and computational cost compared to other state-of-the-art models.