Multi-level Fusion of Multi-spectral Images to Detect the Artificially Ripened Banana

Abstract

Automatic detection of artificially ripened fruits based on a non-destructive approach has recently gained significant attention. This work explores the inherent properties of multi-spectral imaging to distinguish between natural and artificially ripened bananas. The proposed method combines the prediction scores computed from the Support Vector Machine (SVM) on the individual and fused spectral bands images to detect the artificially ripened banana. Extensive analyses are performed on 5760 banana images captured in eight different spectrum bands covering visible and near-Infra-Red ranges. Obtained results indicate the average detection accuracy of 97.1± 3.6%, thereby illustrating our proposed work’s applicability.