Targeting Complex Textures in Guangxi Native Tree Species Wood Defects Intelligent Diagnosis: A Multi-Feature Fusion and Multi-Task Collaborative Learning Method

The wood of Guangxi native tree species exhibits unique material properties and textures. It poses challenges for intelligent defect recognition and surface quality evaluation during mechanical processing. Traditional methods perform poorly in handling complex texture features. They ignore the intri...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2025 IEEE 3rd International Conference on Image Processing and Computer Applications (ICIPCA) S. 49 - 53
Hauptverfasser: Dajun, Long, Yinluan, Qin
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 28.06.2025
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The wood of Guangxi native tree species exhibits unique material properties and textures. It poses challenges for intelligent defect recognition and surface quality evaluation during mechanical processing. Traditional methods perform poorly in handling complex texture features. They ignore the intrinsic relationship between defect information and surface roughness. This study proposes an intelligent diagnosis method for wood defects based on multi-feature fusion and multi-task collaborative learning. The proposed method innovatively combines multi-level texture features extracted by local binary patterns (LBP), Gabor filters, and a deep convolutional neural network (ResNet-50). It builds a robust feature representation adapted to complex texture backgrounds. It also constructs a multi-task collaborative optimization framework. It leverages shared low-level features and designs dedicated network structures for defect classification and roughness prediction. This enables synchronized and precise prediction for both tasks. Experimental results on the public WSDD dataset and a self-built dataset covering four dominant Guangxi native tree species (Dingguomu, Goushu, Kumian, and Yinhua) indicate that the proposed method achieves an accuracy of 94.5 % for defect classification. It shows improvements of approximately 16 % and 6 % over traditional methods and a single CNN model, respectively. For surface roughness prediction, it obtains an RMSE of 0.52 and an MAE of 0.41. These results are significantly better than existing methods. The study effectively addresses the challenges of intelligent diagnosis of wood defects in Guangxi native tree species under complex texture backgrounds. It also provides novel technical means and theoretical support for quality control and process optimization in wood processing.
AbstractList The wood of Guangxi native tree species exhibits unique material properties and textures. It poses challenges for intelligent defect recognition and surface quality evaluation during mechanical processing. Traditional methods perform poorly in handling complex texture features. They ignore the intrinsic relationship between defect information and surface roughness. This study proposes an intelligent diagnosis method for wood defects based on multi-feature fusion and multi-task collaborative learning. The proposed method innovatively combines multi-level texture features extracted by local binary patterns (LBP), Gabor filters, and a deep convolutional neural network (ResNet-50). It builds a robust feature representation adapted to complex texture backgrounds. It also constructs a multi-task collaborative optimization framework. It leverages shared low-level features and designs dedicated network structures for defect classification and roughness prediction. This enables synchronized and precise prediction for both tasks. Experimental results on the public WSDD dataset and a self-built dataset covering four dominant Guangxi native tree species (Dingguomu, Goushu, Kumian, and Yinhua) indicate that the proposed method achieves an accuracy of 94.5 % for defect classification. It shows improvements of approximately 16 % and 6 % over traditional methods and a single CNN model, respectively. For surface roughness prediction, it obtains an RMSE of 0.52 and an MAE of 0.41. These results are significantly better than existing methods. The study effectively addresses the challenges of intelligent diagnosis of wood defects in Guangxi native tree species under complex texture backgrounds. It also provides novel technical means and theoretical support for quality control and process optimization in wood processing.
Author Dajun, Long
Yinluan, Qin
Author_xml – sequence: 1
  givenname: Long
  surname: Dajun
  fullname: Dajun, Long
  organization: Guangxi Eco-Engineering Vocational & Technical College,Liuzhou,Guangxi,China,545004
– sequence: 2
  givenname: Qin
  surname: Yinluan
  fullname: Yinluan, Qin
  email: ldjlunwen000@163.com
  organization: Guangxi Eco-Engineering Vocational & Technical College,Liuzhou,Guangxi,China,545004
BookMark eNo1kM1Kw0AcxFfQg9a-gYf1AVJ3s9kvbyU1NdCqYMBj2ST_xMV0tyQbqY_jm9rSehqYgd8Mc4MunXeA0D0lM0qJfsjT_C2dCy4SPotJzA8uZUpwcoGmWmrFGOVxrBJ6jX4L07cQrGtx6re7Dva4gH0YexiwdXg5GtfuLX4xwX4DLnoA_L6Dyh7iD-9rvIAGqjDg3AXoOtuCC3hhTev8YIdHPMfrsQs2ysAcmTgbB-sdNq4-B4UZvg7NXWdK359KVmB6dxy0hvDp61t01ZhugOlZJ6jInor0OVq9LvN0voqsZiFSTVxSySpTCiaZKCVpNOUyAZEkUnFJDCm5qpKyErzRpGpA1FJqKWvdqFgAm6C7E9YCwGbX263pfzb_x7E_ZrdrMA
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICIPCA65645.2025.11138650
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331522841
EndPage 53
ExternalDocumentID 11138650
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i93t-8f2b173cab63736b70f91574e64478570a0b58c4bc65f90cfe6d77977d9f826e3
IEDL.DBID RIE
IngestDate Wed Sep 10 07:40:45 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-8f2b173cab63736b70f91574e64478570a0b58c4bc65f90cfe6d77977d9f826e3
PageCount 5
ParticipantIDs ieee_primary_11138650
PublicationCentury 2000
PublicationDate 2025-June-28
PublicationDateYYYYMMDD 2025-06-28
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-28
  day: 28
PublicationDecade 2020
PublicationTitle 2025 IEEE 3rd International Conference on Image Processing and Computer Applications (ICIPCA)
PublicationTitleAbbrev ICIPCA
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.913334
Snippet The wood of Guangxi native tree species exhibits unique material properties and textures. It poses challenges for intelligent defect recognition and surface...
SourceID ieee
SourceType Publisher
StartPage 49
SubjectTerms Accuracy
deep learning
defect classification
Dingguomu
Feature extraction
Gabor filters
Guangxi native tree species
image processing
multi-task learning
Multitasking
Optimization
Process control
Rough surfaces
Surface roughness
Surface treatment
Vegetation
wood processing
Title Targeting Complex Textures in Guangxi Native Tree Species Wood Defects Intelligent Diagnosis: A Multi-Feature Fusion and Multi-Task Collaborative Learning Method
URI https://ieeexplore.ieee.org/document/11138650
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwGA06RHxSceKdT_C1Wy9rkvo2OocDHXsouLeR6yhKK1sr-zv-U5Os2_DBB99KUhrI11xO8p1zEHro8ZAGhCQe5Zrba0btMV8STwSB1qHghEjnWvJCxmM6nSaThqzuuDBKKZd8pjr20d3ly1LU9qisa23RKbYIfZ8QvCZrHaL7RjezO0pHk7SPrT6KAX5h3Nm8_8s5xS0cw-N_NnmC2jsKHky2i8sp2lPFGfrOXN62KQA7jj_UCjIzudYGMkNegAl3MV_lMHZi3pAtlALnL2-q38pSwkC55A0YbXU4Kxisc-3y5SP0wdFxPbstNN-EYW2P0oAVsqnI2PId0t2fYxpp9Fnn8OqsqNsoGz5l6bPXeCx4eRJVHtUhD0gkGMcRiTAnvk6CmPSU2SYRq33PfB5T0eMCxzrxhVZYmsiaCCbaABMVnaNWURbqAkGkwoAJiVkUMIOCGFMxTWIpAs0lM0DsErVt984-1yoas03PXv1Rfo2ObBBtWlZIb1CrWtTqFh2IrypfLu5c7H8Az7G0bA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8IwGG4MGvWkRozfviZeB_tu542ABCIQDkvkRvpJFs1mYBj-jv_UtgyIBw_eljZdk77d2qd9n-dB6ClkPvEwThzCFDPXjMqhrsAO9zylfM4wFta1ZIBHIzKZJOOKrG65MFJKm3wmG-bR3uWLgi_NUVnT2KKT2CD0_SgMfXdN1zpEj5VyZrPf7o_brdgopGjo50eNTYtf3il26eie_LPTU1TfkfBgvF1eztCezM_Rd2ozt3UBmC_5Q64g1b_XpQbNkOWgA57PVhmMrJw3pHMpwTrM6-q3ohDQkTZ9A_pbJc4SOutsu2zxDC2whFzHbAz1O6G7NIdpQHNRVaR08Q7t3dzRnVQKrTMYWjPqOkq7L2m751QuC06WBKVDlM88HHDK4gAHMcOuSrwIh1JvlLBRv6cuiwgPGY8jlbhcyVjo2OoYJkpDExlcoFpe5PISQSB9j3IR08CjGgdRKiOSRIJ7igmqodgVqpvhnX6udTSmm5G9_qP8AR310uFgOuiPXm_QsQmoSdLyyS2qlfOlvEMH_KvMFvN7Ow9-AFhXt7M
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2025+IEEE+3rd+International+Conference+on+Image+Processing+and+Computer+Applications+%28ICIPCA%29&rft.atitle=Targeting+Complex+Textures+in+Guangxi+Native+Tree+Species+Wood+Defects+Intelligent+Diagnosis%3A+A+Multi-Feature+Fusion+and+Multi-Task+Collaborative+Learning+Method&rft.au=Dajun%2C+Long&rft.au=Yinluan%2C+Qin&rft.date=2025-06-28&rft.pub=IEEE&rft.spage=49&rft.epage=53&rft_id=info:doi/10.1109%2FICIPCA65645.2025.11138650&rft.externalDocID=11138650