High-Throughput Online Visual Detection Method of Cracked Preserved Eggs Based on Deep Learning
Cracked preserved eggs can easily decay, emit a peculiar smell, and cause cross-infection. The identification of cracked preserved eggs during production suffers from low efficiency and high cost. This paper proposes an online detection and identification method of cracked preserved eggs to address...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/3/952 |
_version_ | 1797489486458781696 |
---|---|
author | Wenquan Tang Jianchao Hu Qiaohua Wang |
author_facet | Wenquan Tang Jianchao Hu Qiaohua Wang |
author_sort | Wenquan Tang |
collection | DOAJ |
description | Cracked preserved eggs can easily decay, emit a peculiar smell, and cause cross-infection. The identification of cracked preserved eggs during production suffers from low efficiency and high cost. This paper proposes an online detection and identification method of cracked preserved eggs to address this issue. First, the images of preserved eggs are collected online. Then, each collected image is cut into a single image of the preserved egg, and the images of different surfaces of the same preserved egg are respectively spliced by the sequential splicing scheme and the matrix splicing scheme. Finally, the data sets obtained by the two stitching methods are exploited to establish a deep learning detection model. The experimental results indicate that the MobileNetV3_egg model, an improved version of the MobileNetV3_large model, achieves the best recognition ability for cracked preserved eggs by using the matrix splicing scheme. The accuracy reaches 96.3%, and the detection time for 300 images is only 4.267 s. The proposed method can meet the needs of actual production, and the application of this method will make the identification of cracked preserved eggs more automated and intelligent. |
first_indexed | 2024-03-10T00:17:17Z |
format | Article |
id | doaj.art-c4a64236720b403e84598970b3f2cfc7 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T00:17:17Z |
publishDate | 2022-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-c4a64236720b403e84598970b3f2cfc72023-11-23T15:49:27ZengMDPI AGApplied Sciences2076-34172022-01-0112395210.3390/app12030952High-Throughput Online Visual Detection Method of Cracked Preserved Eggs Based on Deep LearningWenquan Tang0Jianchao Hu1Qiaohua Wang2College of Engineering, Huazhong Agricultural University, Wuhan 430070, ChinaCollege of Engineering, Huazhong Agricultural University, Wuhan 430070, ChinaCollege of Engineering, Huazhong Agricultural University, Wuhan 430070, ChinaCracked preserved eggs can easily decay, emit a peculiar smell, and cause cross-infection. The identification of cracked preserved eggs during production suffers from low efficiency and high cost. This paper proposes an online detection and identification method of cracked preserved eggs to address this issue. First, the images of preserved eggs are collected online. Then, each collected image is cut into a single image of the preserved egg, and the images of different surfaces of the same preserved egg are respectively spliced by the sequential splicing scheme and the matrix splicing scheme. Finally, the data sets obtained by the two stitching methods are exploited to establish a deep learning detection model. The experimental results indicate that the MobileNetV3_egg model, an improved version of the MobileNetV3_large model, achieves the best recognition ability for cracked preserved eggs by using the matrix splicing scheme. The accuracy reaches 96.3%, and the detection time for 300 images is only 4.267 s. The proposed method can meet the needs of actual production, and the application of this method will make the identification of cracked preserved eggs more automated and intelligent.https://www.mdpi.com/2076-3417/12/3/952online detectionMobileNetV3preserved eggcrack detectionmachine vision |
spellingShingle | Wenquan Tang Jianchao Hu Qiaohua Wang High-Throughput Online Visual Detection Method of Cracked Preserved Eggs Based on Deep Learning Applied Sciences online detection MobileNetV3 preserved egg crack detection machine vision |
title | High-Throughput Online Visual Detection Method of Cracked Preserved Eggs Based on Deep Learning |
title_full | High-Throughput Online Visual Detection Method of Cracked Preserved Eggs Based on Deep Learning |
title_fullStr | High-Throughput Online Visual Detection Method of Cracked Preserved Eggs Based on Deep Learning |
title_full_unstemmed | High-Throughput Online Visual Detection Method of Cracked Preserved Eggs Based on Deep Learning |
title_short | High-Throughput Online Visual Detection Method of Cracked Preserved Eggs Based on Deep Learning |
title_sort | high throughput online visual detection method of cracked preserved eggs based on deep learning |
topic | online detection MobileNetV3 preserved egg crack detection machine vision |
url | https://www.mdpi.com/2076-3417/12/3/952 |
work_keys_str_mv | AT wenquantang highthroughputonlinevisualdetectionmethodofcrackedpreservedeggsbasedondeeplearning AT jianchaohu highthroughputonlinevisualdetectionmethodofcrackedpreservedeggsbasedondeeplearning AT qiaohuawang highthroughputonlinevisualdetectionmethodofcrackedpreservedeggsbasedondeeplearning |