[1]刘 伟,华顺刚.基于模态特征融合的零件模型识别与检索算法[J].机械与电子,2025,(08):3-9.
　LIU Wei,HUA Shungang.Part Model Recognition and Retrieval Algorithm Based on Modal Feature Fusion[J].Machinery & Electronics,2025,(08):3-9.
点击复制

基于模态特征融合的零件模型识别与检索算法()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2025年08期
页码:
3-9
栏目:
研究与设计
出版日期:
2025-08-25

文章信息/Info

Title:
Part Model Recognition and Retrieval Algorithm Based on Modal Feature Fusion
文章编号:
1001-2257 ( 2025 ) 08-0003-07
作者:
刘 伟; 华顺刚
大连理工大学高性能精密制造国家重点实验室,辽宁 大连 116024
Author(s):
LIU Wei ;  HUA Shungang
( State Key Laboratory of High-performance Precision Manufacturing , Dalian University of Technology , Dalian 116024 , China )
关键词:
零件识别; 零件检索; 模态特征融合; PointNet++
Keywords:
part model recognition ;  part model retrieval ;  modal feature fusion ;  PointNet++
分类号:
TP391.4
文献标志码:
A
摘要:
针对只用单一模态特征或多模态特征简单拼接导致的识别与检索性能不佳的问题,提出一种零件模型识别与检索算法。在特征提取阶段,使用特定的网络提取各自模态的特征;在特征融合阶段,引入了跨模态中心损失函数指导模态间的特征融合,以增强网络对零件模型的识别能力。在 CADNET 数据集上的实验结果显示,该算法相比现有典型算法显著提高了识别和检索效果,取得 96.3% 的识别准确率和92.3% 的平均检索精度均值,证明了其在处理零件模型识别和检索任务中的有效性。
Abstract:
Aiming at the problem of poor recognition and retrieval performance caused by using only single modal features or simple splicing of multimodal features , the paper proposes an algorithm for identifying and retrieving part models using feature fusion.During the phase of features extraction , the characteristics of each modality are derived through a designated network.During the phase of feature fusion , a loss function focused on cross modal aspects is implemented to steer the fusion of inter-modal features , thereby improving the network ’ s capacity to identify part models.Tests on the CADNET dataset reveal that this algorithm significantly enhances recognition and retrieval outcomes over conventional algorithms , attaining 96.3% accuracy in recognition and 92.3% in Mean Average Precision , thus demonstrating its proficiency in recognizing and retrieving part models.

参考文献/References:

[ 1 ] HU N , ZHOU H Y , LIU A A , et al.Collaborative distribution alignment for 2D image-based 3D shape retrieval [ J ] .Journal of visual communication and image representation , 2022 , 83 : 103426.

[ 2 ] MU P P , ZHANG S Y , ZHANG Y , et al.Image-based 3D model retrieval using manifold learning [ J ] .Frontiers of information technology and electronic engineering , 2018 , 19 ( 11 ): 1397-1408.
[ 3 ] ZHOU H , NIE W , SONG D , et al.Semantic consistency guided instance feature alignment for 2D image based 3D shape retrieval [ C ] ∥Proceedings of the 28th ACM International Conference on Multimedia , 2020 : 925-933.
[ 4 ] SU H , MAJI S , KALOGERAKIS E , et al.Multi-view convolutional neural networks for 3D shape recognition [ C ] ∥2015 IEEE International Conference on Computer Vision ( ICCV ), 2015 : 945-953.
[ 5 ] LIU Z , ZHANG Y , GAO J , et al.VFMVAC : view-filtering-based multi-view aggregating convolution for 3D shape recognition and retrieval [ J ] .Pattern recognition , 2022 , 129 : 108774.
[ 6 ] QI C R , SU H , MO K , et al.PointNet : deep learning on point sets for 3D classification and segmentation [ C ] ∥ IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ), 2017 : 77-85.
[ 7 ] 华顺刚,尚政,王雪飞 . 结合总体及零件参数的装配体 CAD 模型检索[ J ] . 大连理工大学学报, 2023 , 63 ( 6 ):592-599.
[ 8 ] WU Z , SONG S , KHOSLA A , et al.3D ShapeNets : a deep representation for volumetric shapes [ C ] ∥IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ), 2015 : 1912-1920.
[ 9 ] QI C R , YI L , SU H , et al.PointNet++ : deep hierarchical feature learning on point sets in a metric space [ C ] ∥Proceedings of the 31st International Conference on Neural Information Processing Systems , 2017 : 5105-5114.
[ 10 ] FENG Y , ZHANG Z , ZHAO X , et al.GVCNN : group view convolutional neural networks for 3D shape recognition [ C ] ∥IEEE / CVF Conference on Computer Vision and Pattern Recognition ( CVPR ), 2018 : 264-272.
[ 11 ] HUANG Y , DU C , XUE Z , et al.What makes multi modal learning better than single ( Provably )[ C ] ∥ Proceedings of the 35th Conference on Neural Information Processing Systems ( NeurIPS ), 2021 : 10944-10956.
[ 12 ] JING L L , VAHDANI E , TAN J X , et al.Cross-modal center loss for 3D cross-modal retrieval [ C ] ∥ IEEE / CVF Conference on Computer Vision and Pattern Recognition ( CVPR ), 2021 : 3141-3150.
[ 13 ] 苏北 . 基于图像的三维模型检索方法研究[ D ] . 武汉:华中科技大学,2022.
[ 14 ] MANDA B , BHASKARE P , MUTHUGANAPATHY R. A convolutional neural network approach to the classification of engineering models [ J ] .IEEE Access , 2021 , 9 : 22711-22723.

备注/Memo

备注/Memo:
收稿日期: 2025-03-07
基金项目:国家自然科学基金资助项目( 52175455 )
作者简介:刘 伟 ( 1998- ),男,安徽安庆人,硕士,研究方向为计算机图形学;华顺刚 ( 1964- ),男,辽宁大连人,博士,教授,博士研究生导师,研究方向为 CAD 与图形学、图形图像处理。
更新日期/Last Update: 2025-09-04