Guava fruit (Psidium guajava) damage and disease detection using deep convolutional neural networks and thermal imaging

ABSTRACT

Guava is a fruit grown predominantly in the tropical and subtropical regions of the world. Its skin is thin and soft. Although postharvest handling and transportation of fruits are unavoidable, hand harvesting is preferred to avoid physical injuries. Visually identifying internal damage is a laborious and time-consuming task. In this study, 4129 thermal and digital images of guava fruits were collected. A digital image-based convolution neural network (CNN) model was developed to classify the quality of damaged and diseased fruits. The surface temperatures of all three levels of maturity-indexed and damaged fruits were measured using thermal images. During the storage period, the temperature of the immature fruits was less than half of the mature fruits. Because the architecture was trained on dehydrated and diseased guava, it accurately predicted fruit quality. The prediction accuracy of the developed CNN model was approximately 99.92%.

GRAPHICAL ABSTRACT

KEYWORDS:

• Guava fruit
• surface temperature
• thermal image
• classification
• CNN model
• deep learning
• damage detection
• digital image

Acknowledgements

The authors would like to acknowledge the Department of Computer Science Engineering and Food Technology of Velammal Engineering College, Easwari Engineering College, for providing the facilities for this work. We would like to thank Editage (www.editage.com) for English language editing.

Author contributions

Pathmanaban P: Conceptualization; Investigation; Writing – original draft; Validation; Methodology; Visualization. Gnanavel B.K: Supervision; Data curation; Validation; Methodology. Shanmuga Sundaram Anandan: Writing – review & editing; Visualization; Software; Formal analysis; Project administration; Resources; Methodology; Validation.

Conflicts of interest

The authors declare that they have no known competing interest, whether financial or otherwise regarding the publication of this paper.

Data reference

P. PATHMANABAN; B K, GNANAVEL; Anandan, Shanmuga Sundaram (2022), ‘Guava Fruit Digital and Thermal Images,’ Mendeley Data, V1. doi:10.17632/5kptnn7ycr.1.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

P. Pathmanaban

Pathmanaban P received his B.E degree in Automobile Engineering from Anna university, Chennai, India in the year 2009. He completed his M.E degree in CAD/CAM from Anna university, Chennai, India in the year 2013. He is currently working as an Assistant professor in Velammal Engineering college and pursuing his Ph.D in Thermal Image Processing in Easwari Engineering college, under Anna University, Chennai, India. His research interests include postharvest transportation, cold chain, thermal image processing, computer vision and deep learning.

B. K. Gnanavel

Dr. B. K. Gnanavel received his B.E. degree in Mechanical Engineering from the University of Madras, Chennai, India, a Master's degree in Engineering Design from Bharathiyar University, and a Ph.D. from the College of Engineering Guindy. He is the recognized supervisor for Anna University (Ref. No. 1920104). Professional Body Membership: Life Member of the Indian Society for Technical Education (ISTE) and a Member of SAEINDIA, ASME, IAEngg. One of the reviewers for various International Journals. His research interests include Cable Mechanics, Vibration and Finite Element Analysis, Contact Mechanics and Tribology, Structural Design of Composite Materials, Electronic cooling, thermal image processing, computer vision, and deep learning.

Shanmuga Sundaram Anandan

Dr. Shanmuga Sundaram Anandan is an experienced Professor with a demonstrated history of working in the Mechanical Engineering Department. He was skilled in Thermal Analysis, Thermal Management, Cold Storage, and Renewable Energy. Vital education professional with a bachelor’s degree focused in B.E. (Mechanical Engineering) from the Institute of Road and Transport Technology, Tamil Nādu, India, Medallist for securing University First rank in M.E. (Thermal Engineering) from university of madras, and Doctoral degree from Anna university, Chennai, India. He served as a Principal Investigator for projects funded by various organizations, such as DST, DST-SEED, and AICTE.