Harvestable Black Pepper Recognition Using Computer Vision

The objective of the research presented in this paper is to speed up recognition of harvestable black pepper using computer vision for automated black pepper harvesting. In this paper we introduce a novel dataset of black pepper images acquired using a digital camera. The proposed system is based on a combination of several image processing techniques and a deep learning model to achieve a system capable of recognizing and detecting harvestable black pepper from different elements of the scene, such as leaves, tree trunks branches and unripe pepper. The system is composed of a 3-stage image processing and a verification model in order to achieve 100% accuracy. This approach not only increase the accuracy but also reduce the processing time and computational resources required as the system moves from one stage to another only if a set of pre-defined conditions are met. After performing trial and error method on a number of different classifiers we decided to use ResNet-50, a CNN based classifier for the final validation of test results due to its immense speed and accuracy. The experimental results are showing promising 100% global accuracy with reasonable scan time which will enable real time application.