Bruise detection and classification in jujube using thermal imaging and DenseNet

Abstract

Jujubes (Ziziphus Mauritiana Lamk) are subjected to bruises during harvesting and post-harvest processing, which will greatly reduce their commercial values. In this study, bruises on jujube are detected and classified based on thermal imaging and convolutional neural networks. A simple thermal imaging system is constructed that can capture thermal images speedily and clearly. Temperature difference analysis is performed on the collected thermal images and accordingly, the temperature difference of boundary in the bruised area varies between 1.72 and 3.25 C during the storage period. The temperature difference in the bruise boundary area minus the temperature difference in the center area varies between 0.4 and 1.2 C, and the degree of bruise of the jujube is evaluated through temperature difference analysis.The convolutional neural network DenseNet is adjusted to ensure suitability for classification of the thermal image data set collected in this study (the training dataset comprises 5,039 original thermal images, and the test dataset comprises 2,586 original thermal images), and the best prediction accuracy achieved is 99.5%.Practical Application: This study can be used as a reference for the future development of harvest, sorting, storage, and transportation for bruise detection in jujube.Our study makes a significant contribution to the literature because the findings of this study could facilitate the development of an online thermal imaging system for bruise detection and classification in jujube in the future.

Research and implementation of crop pests recognition method based on deep convolutional neural network

“…Different from DenseNet, DenseNet uses dense connection mechanism to connect all layers, and each layer will connect with all previous layers in the channel dimension to achieve feature reuse, namely [10]: )] ,..., , [(…”

JujubeNet: A high-precision lightweight jujube surface defect classification network with an attention mechanism

“…However, at present, a large number of factories still use manual methods to classify JSD ( Bhargava et al., 2022 ), which have obvious disadvantages such as low efficiency and high costs. Manual quality sorting is subject to significant fluctuations in human factors, and the phenomenon of wrong inspection and omission often occurs, which leads to the uneven overall quality of jujube commodities ( Dong et al., 2022 ). Therefore, it is urgently necessary to introduce advanced technologies to innovate and replace the simple manual sorting methods to improve the quality of jujube products and achieve their automatic sorting.…”

Discrimination of Inner Injury of Korla Fragrant Pear Based on Multi-Electrical Parameters

“…In recent years, researchers have mainly used hyperspectral imaging [3][4][5][6][7][8][9], machine vision [10,11], thermal imaging [12], nuclear magnetic resonance [13], electronic nose [14], multispectral reflection, and fluorescence imaging [9] to detect mechanical damage, bruise, and the internal quality of fruit. However, these technologies are limited in practical application due to the high equipment costs, long data acquisition and processing time, and possible health and safety issues [15].…”