Title: A multi-channel convolutional neural network driven computer vision system towards identification of species and maturity stage of banana fruits: case studies with Martaman and Singapuri banana
Authors: Gunjan Mukherjee; Arpitam Chatterjee; Bipan Tudu
Addresses: Department of Master of Computer Applications, Regent Education and Research Foundation Group of Institutions, Kolkata, India ' Department of Printing Engineering, Jadavpur University, Kolkata, India ' Department of Instrumentation and Electronics Engineering, Jadavpur University, Kolkata, India
Abstract: Banana is a widely consumed fruit worldwide due to its high nutritional values. The nutritional impact of banana considerably varies with the species and ripening stages. The existing practices of both species and ripening stage detection of banana are performed majorly by human experience and chemical analysis. This paper presents a computer vision-based system development to identify banana species and corresponding ripening stages simultaneously. The proposed system is less expensive, non-invasive and faster with potential to provide up to 98% accuracy. The work utilises multi-channel convolutional neural network (CNN) architecture to classify the species and ripening stage in a single go. The results of the proposed system was assessed against different popular metrics and found competitive to the existing techniques. This technique can be also integrated to a handheld device or mobile app in future for firsthand assessment by the consumers and sellers in the market.
Keywords: banana fruits; computer vision; colour features; multi-channel convolutional neural network; CNN; deep neural network; DNN.
International Journal of Computational Intelligence Studies, 2022 Vol.11 No.1, pp.1 - 23
Accepted: 30 Nov 2021
Published online: 07 Jun 2022 *