Green Plums Surface Defect Detection Based on Deep Learning Methods

Abstract

Green plums are a characteristic fruit resource in China, with a long history of cultivation. Many surface defects will appear in the growth, transportation and preservation of green plums which seriously affect the processing quality of by-products. The existing manual sorting method of green plums is limited by the experience of workers. It is difficult to ensure the quality and speed of detection. Therefore, the formation of automatic detection of green plums surface defects is of great significance to the development of green plum industry. According to the surface defects of green plums, this paper divides green plums into five categories : rot, cracks, scars, spots and normal. A total of 1235 images of green plums were obtained by self-built image acquisition device. The WideResNet50-AdamW-Wce model based on WideResNet model was built to classify the surface defects of green plums. Accuracy, recall and F1-measure were selected as the indexes to evaluate the accuracy of classification. The accuracy of classification reached 98.95 %, and the classification accuracy of rain spots, normal, scars, rot and crack reached 100 %, 99.56 %, 98.59 %, 98.25 % and 96.10 % respectively. Comparing the performance of ResNet50-SGD, WideResNet50-SGD, WideRes-Net50-SGD-Wce and WideResNet50-AdamW network models, the F1-Measure based on WideResNet50-AdamW-Wce is the highest in each defect, and more greengage defect features can be learned. The detection results can meet the production needs of plum deep processing enterprisesevaluating 1800 green plums per hour on the assembly line.INDEX TERMS green plum; surface defects; defect detection; deep learning;

Convolutional neural network based on the fusion of image classification and segmentation module for weed detection in alfalfa

“…For example, recent studies have shown that deep learning can be employed to accurately diagnose coronavirus disease, 29 predict seizure recurrence, 30 perform a high‐accuracy three‐dimensional optical measurement, 31 predict the activity of potential drug molecules, 32 analyze particle accelerator data, 33,34 discriminate the maturity stage of oil camellia ( Camellia oleifera Abel.) fruit, 35 detect surface defects of green plums ( Vatica mangachapoi Blanco), 36 and reconstruct brain circuits 37 . Moreover, DCNNs have exhibited an exceptional capability for object detection 38,39 and classification in digital images 40,41 …”

Bird Sound Feature Extraction and Recognition Model Design Based on Neural Network Architecture Search

“…Although classical deep learning models [20][21][22][23][24][25][26][27] have demonstrated good results in bird sound recognition, the model design relies heavily on human experience and is subjective. Furthermore, the current mainstream method involves extracting bird sound signals, converting them into Mel spectra, and feeding them into a deep learning model.…”

Evaluation Method of Potato Storage External Defects Based on Improved U-Net

“…To achieve the automatic detection of jujube crack, Zheng et al [18] presented an attention feature fusion network (AFFU-Net) based on U-Net architecture and integrated it with the loss and residual mixing refinement module (RRM). To categorize the surface flaws (rot, cracks, wounds, and spots) of green plums, Zhou et al [19] employed a WideRes-Net model using the WideResNet50 AdamW-Wce model, which has outstanding performance in terms of recall, precision, etc. A ConvNeXt-based, high-precision lightweight classification network was proposed by Jiang et al [20], which greatly reduces the number of model parameters while still guaranteeing that the model precision criterion is satisfied.…”