Mutual Augmentation of Spectral Sensing and Machine Learning for Non-Invasive Detection of Apple Fruit Damages

Abstract

Non-invasive techniques for the detection of apple fruit damages are central to the correct operation of sorting lines ensuring storability of the collected fruit batches. The choice of optimal method of fruit imaging and efficient image processing method is still a subject of debate. Here, we have dissected the information content of hyperspectral images focusing on either spectral component, spatial component, or both. We have employed random forest (RF) classifiers using different parameters as inputs: reflectance spectra, vegetation indices (VIs), and spatial texture descriptors (local binary patterns, or LBP), comparing their performance in the task of damage detection in apple fruit. The amount of information in raw hypercubes was found to be over an order of magnitude excessive for the end-to-end problem of classification. Converting spectra to vegetation indices has resulted in a 60-fold compression with no significant loss of information relevant for phenotyping and more robust performance with respect to varying illumination conditions. We concluded that the advanced machine learning approaches could be more efficient if complemented by spectral information about the objects in question. We discuss the potential advantages and pitfalls of the different approaches to the machine learning-based processing of hyperspectral data for fruit grading.

Multifunctional Robotic Device with Intelligent Positioning System

“…The Digital Gardening scientific and production system involves expanding the scope of machines, equipment and software, including the widespread use of robotic tools in horticultural production and processing technologies, in order to increase production efficiency, eliminate the "human factor" in the production of products, replace human participation in production processes with a large proportion of heavy manual labor and minimizing the harmful effects of chemical protection products on humans and the environment [1][2][3][4][5]. Another reason for the intensification of the development and implementation of robotic tools with intelligent control systems in horticulture is the acute shortage of technologists and engineers in farms, due to the unattractiveness of work in the agro-industrial complex [6][7][8].…”

Apple Flower Recognition Using Convolutional Neural Networks with Transfer Learning and Data Augmentation Technique

“…Thinning apple flowers is a key factor in a crop management strategy aimed at improving fruit quality in the perspective of long-term production [1,2]. Automated methods of flower recognition represent an efficient way to reduce labor costs in monitoring industrial apple orchards for making optimal managerial decisions [3][4][5]. Automated monitoring of apple flowers using convolutional neural networks will enable more precise adaptation of agronomic practices, optimizing crop load, preventing fruiting periodicity, and enhancing crop quality [6,7].…”

Detecting Surface Defects of Achacha Fruit (Garcinia humilis) with Hyperspectral Images

“…For example, researchers used near-infrared HSI data to establish the differences between the normal and defective skins of jujubes [16] and peaches [17]. Furthermore, the HSI data in the visible and near-infrared were used to detect common skin defects in citrus [18], early downy mildew in grapevines [19], and damage in the apples [20].…”