CNFA: ConvNeXt Fusion Attention Module for Age Recognition of the Tangerine Peel

Xinhui tangerine peel has valuable medicinal value. The longer it is stored in an appropriate environment, the higher its flavonoid content, resulting in increased medicinal value. In order to correctly identify the age of the tangerine peel, previous studies have mostly used manual identification o...

Full description

Saved in:
Bibliographic Details
Main Authors: Fuqin Deng, Junwei Li, Lanhui Fu, Chuanbo Qin, Yikui Zhai, Hongmin Wang, Ningbo Yi, Nannan Li, TinLun Lam
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:Journal of Food Quality
Online Access:http://dx.doi.org/10.1155/2024/6439900
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832546281806888960
author Fuqin Deng
Junwei Li
Lanhui Fu
Chuanbo Qin
Yikui Zhai
Hongmin Wang
Ningbo Yi
Nannan Li
TinLun Lam
author_facet Fuqin Deng
Junwei Li
Lanhui Fu
Chuanbo Qin
Yikui Zhai
Hongmin Wang
Ningbo Yi
Nannan Li
TinLun Lam
author_sort Fuqin Deng
collection DOAJ
description Xinhui tangerine peel has valuable medicinal value. The longer it is stored in an appropriate environment, the higher its flavonoid content, resulting in increased medicinal value. In order to correctly identify the age of the tangerine peel, previous studies have mostly used manual identification or physical and chemical analysis, which is a tedious and costly process. This work investigates the automatic age recognition of the tangerine peel based on deep learning and attention mechanisms. We proposed an effective ConvNeXt fusion attention module (CNFA), which consists of three parts, a ConvNeXt block for extracting low-level features’ information and aggregating hierarchical features, a channel squeeze-and-excitation (cSE) block and a spatial squeeze-and-excitation (sSE) block for generating sufficient high-level feature information from both channel and spatial dimensions. To analyze the features of tangerine peel in different ages and evaluate the performance of CNFA module, we conducted comparative experiments using the CNFA-integrated network on the Xinhui tangerine peel dataset. The proposed algorithm is compared with related models of the proposed structure and other attention mechanisms. The experimental results showed that the proposed algorithm had an accuracy of 97.17%, precision of 96.18%, recall of 96.09%, and F1 score of 96.13% for age recognition of the tangerine peel, providing a visual solution for the intelligent development of the tangerine peel industry.
format Article
id doaj-art-8f7f98c56035453db541dfd30d8821fb
institution Kabale University
issn 1745-4557
language English
publishDate 2024-01-01
publisher Wiley
record_format Article
series Journal of Food Quality
spelling doaj-art-8f7f98c56035453db541dfd30d8821fb2025-02-03T07:23:23ZengWileyJournal of Food Quality1745-45572024-01-01202410.1155/2024/6439900CNFA: ConvNeXt Fusion Attention Module for Age Recognition of the Tangerine PeelFuqin Deng0Junwei Li1Lanhui Fu2Chuanbo Qin3Yikui Zhai4Hongmin Wang5Ningbo Yi6Nannan Li7TinLun Lam8School of Electronic and Information EngineeringSchool of Electronic and Information EngineeringSchool of Electronic and Information EngineeringSchool of Electronic and Information EngineeringSchool of Electronic and Information EngineeringSchool of Electronic and Information EngineeringSchool of Textile Materials and EngineeringSchool of Computer Science and EngineeringSchool of Science and EngineeringXinhui tangerine peel has valuable medicinal value. The longer it is stored in an appropriate environment, the higher its flavonoid content, resulting in increased medicinal value. In order to correctly identify the age of the tangerine peel, previous studies have mostly used manual identification or physical and chemical analysis, which is a tedious and costly process. This work investigates the automatic age recognition of the tangerine peel based on deep learning and attention mechanisms. We proposed an effective ConvNeXt fusion attention module (CNFA), which consists of three parts, a ConvNeXt block for extracting low-level features’ information and aggregating hierarchical features, a channel squeeze-and-excitation (cSE) block and a spatial squeeze-and-excitation (sSE) block for generating sufficient high-level feature information from both channel and spatial dimensions. To analyze the features of tangerine peel in different ages and evaluate the performance of CNFA module, we conducted comparative experiments using the CNFA-integrated network on the Xinhui tangerine peel dataset. The proposed algorithm is compared with related models of the proposed structure and other attention mechanisms. The experimental results showed that the proposed algorithm had an accuracy of 97.17%, precision of 96.18%, recall of 96.09%, and F1 score of 96.13% for age recognition of the tangerine peel, providing a visual solution for the intelligent development of the tangerine peel industry.http://dx.doi.org/10.1155/2024/6439900
spellingShingle Fuqin Deng
Junwei Li
Lanhui Fu
Chuanbo Qin
Yikui Zhai
Hongmin Wang
Ningbo Yi
Nannan Li
TinLun Lam
CNFA: ConvNeXt Fusion Attention Module for Age Recognition of the Tangerine Peel
Journal of Food Quality
title CNFA: ConvNeXt Fusion Attention Module for Age Recognition of the Tangerine Peel
title_full CNFA: ConvNeXt Fusion Attention Module for Age Recognition of the Tangerine Peel
title_fullStr CNFA: ConvNeXt Fusion Attention Module for Age Recognition of the Tangerine Peel
title_full_unstemmed CNFA: ConvNeXt Fusion Attention Module for Age Recognition of the Tangerine Peel
title_short CNFA: ConvNeXt Fusion Attention Module for Age Recognition of the Tangerine Peel
title_sort cnfa convnext fusion attention module for age recognition of the tangerine peel
url http://dx.doi.org/10.1155/2024/6439900
work_keys_str_mv AT fuqindeng cnfaconvnextfusionattentionmoduleforagerecognitionofthetangerinepeel
AT junweili cnfaconvnextfusionattentionmoduleforagerecognitionofthetangerinepeel
AT lanhuifu cnfaconvnextfusionattentionmoduleforagerecognitionofthetangerinepeel
AT chuanboqin cnfaconvnextfusionattentionmoduleforagerecognitionofthetangerinepeel
AT yikuizhai cnfaconvnextfusionattentionmoduleforagerecognitionofthetangerinepeel
AT hongminwang cnfaconvnextfusionattentionmoduleforagerecognitionofthetangerinepeel
AT ningboyi cnfaconvnextfusionattentionmoduleforagerecognitionofthetangerinepeel
AT nannanli cnfaconvnextfusionattentionmoduleforagerecognitionofthetangerinepeel
AT tinlunlam cnfaconvnextfusionattentionmoduleforagerecognitionofthetangerinepeel