We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Deep learning models for detection and classification of spongy tissue disorder in mango using X-ray images.
- Authors
Kiran, Patil Rajvardhan; Avinash, G.; Ray, Mrinmoy; Nigam, Sapna; Parray, Roaf Ahmad
- Abstract
Alphonso, a renowned mango variety cultivated in India, is commercially valuable for its delightful taste, vibrant saffron color, texture, and prolonged shelf life, attracts global attention. Spongy Tissue (ST) disorder is prevalent in mangoes, especially in the Alphonso variety, leading to spongy and corky texture in the fruit's pulp. This issue has been identified in as much as 30% of mangoes in a single lot, resulting in the entire lot being rejected during export due to the delayed detection of the disorder. Current mango quality assessment involves destructive cutting, causing fruit damage, leading to significant loss. Limited physical checks don't ensure overall batch quality. By considering above challenges present study demonstrates on use of X-ray imaging technique for detecting internal quality of mango non-destructively along with machine learning algorithms for automatic binary classification (Non spongy vs. Spongy). For evaluation 648 original X-ray images of mangoes were captured and augmented to 3888 images using different augmentation techniques. For automated classification purposes deep learning (DL) models were used. For automated classification, DL models were employed and fine-tuned through grid search hyperparameter optimization within a 5-fold cross-validation framework. Among the DL models, namely CNN, ResNet50, AlexNet, VGG16, and VGG19, they achieved notable overall accuracy rates of 87.27%, 89.18%, 90.21%, 91.75% and 95.82%, respectively, on the test dataset. Significantly, the VGG19 model demonstrated superior performance with highest classification accuracy by TukeyHSD test. DL in X-ray imaging shows promise for detecting internal issues in fruits, enhancing inspection capabilities for diverse purposes, such as identifying diseases or damages. Highlights: •'Alphonso' is variety of mango that has suffered from spongy tissue malady. •Potential of X-ray imaging was tested for identifying internal spongy tissue defects. •CNN, AlexNet, ResNet, VGG16 and VGG19 models were used for automatic classification. •Models were optimized by hyperparameter tuning and cross-validation technique. •Deep transfer learning models achieved >90% mango binary classification accuracy.
- Subjects
CONVOLUTIONAL neural networks; MACHINE learning; X-ray imaging; DEEP learning; AUTOMATIC classification; MANGO
- Publication
Journal of Food Measurement & Characterization, 2024, Vol 18, Issue 9, p7806
- ISSN
2193-4126
- Publication type
Article
- DOI
10.1007/s11694-024-02766-6