This work evaluates the performance of a Deep Learning technique for classification of challenging hyperspectral images of the interior of fruits and vegetables when they are combined. Some of these samples have low contrast, similar colour features, and their skins or characteristic shapes are lost when cut to expose their interiors. We implemented a two-dimensional convolutional neural network for this classification task and compared their results against the technique of support vector machines. We randomly selected a group of 13 hyperspectral images from a public database containing information of the interior of 42 fruits and vegetables. Using parts of these 13 selected images, we constructed three artificial hyperspectral images merging these parts differently. We applied the two proposed techniques over the three of them. The comparison of the classification results shows that the two-dimensional convolutional neural network over-performs the support vector machine in all three composite images. The two-dimensional convolutional neural network exceeded 98% classification accuracy in all of them. These results show that the two-dimensional convolutional network benefits from the spatial and spectral data in the images obtaining proper levels of classification even in samples mixed in complex contexts, as it can occur in the food or pharmaceutical industries.
Ornamental floriculture is one of the main economic activities in different regions of Colombia. Different flowers have a great success, but its industry faces some challenges on phytosanitary controls caused mainly by the dependence on human monitors and the expertise in the detection of diseases throughout the crop fields. This paper focuses on the detection of the affection patterns caused by tomato spotted wilt virus, puncture leaf miner, and leaf miner larvae on chrysanthemum flowers (Dendrathema grandiflorum). A spectral imaging system was with 11 spectral channels was implemented which were generated by the same number of light emitting diodes groups. By using these images, there were carried out different image processing techniques and the combination of different linear relations among the spectral images were tested to enhance, isolate and quantify the affected area on the leaves. The results show that our system has more selective spectral width than common artificial vision systems and the effects of the diseases can be effectively detected.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.