[1]童俊毅,李效宇,苑宇豪,等.基于卷积神经网络的羊绒纤维长度检测模型及其应用[J].服装学报,2025,10(06):471-477.
　TONG Junyi,LI Xiaoyu,YUAN Yuhao,et al.Cashmere Fiber Length Measurement Model Based on Convolutional Neural Network and Its Application[J].Journal of Clothing Research,2025,10(06):471-477.
点击复制

基于卷积神经网络的羊绒纤维长度检测模型及其应用()

《服装学报》[ISSN:2096-1928/CN:32-1864/TS]

卷:
第10卷
期数:
2025年06期
页码:
471-477
栏目:
服装材料
出版日期:
2025-12-30

文章信息/Info

Title:
Cashmere Fiber Length Measurement Model Based on Convolutional Neural Network and Its Application
作者:
童俊毅1;  李效宇2;  苑宇豪1;  杨瑞华*1
1.江南大学 纺织科学与工程学院,江苏 无锡 214122; 2.内蒙古中科融汇绒业发展有限公司,内蒙古 巴彦淖尔 015000
Author(s):
TONG Junyi1;  LI Xiaoyu2;  YUAN Yuhao1;  YANG Ruihua*1
1.College of Textile Science and Engineering, Jiangnan University, Wuxi 214122, China; 2.Inner Mongolia ZHONG KE RONG HUI Cashmere Industry Development Co., Ltd., Bayannur 015000,China
分类号:
TS 131.9; TP 183
文献标志码:
A
摘要:
针对传统羊绒纤维长度测量方法效率低、精度受人为因素影响的问题,采用卷积神经网络技术,对羊绒纤维在阈值化处理中的断裂修复和交叉区域检测进行系统研究; 设计了基于U-Net框架的纤维补断模型和基于ResNet-50编码器的交叉点检测模型,通过引入跳跃连接机制和混合损失函数,解决因阈值处理导致的纤维断裂和类别不平衡的问题。研究表明,纤维补断模型的像素准确率达到98.72%,交叉点检测模型具有良好的分割精度和泛化能力; 模型测得的纤维平均长度与手排法结果的标准差最低为0.28 mm,验证了该方法在羊绒纤维长度测量中具有较高的精度、稳定性和实用性。
Abstract:
To address the issues of low efficiency and human factor-induced inaccuracies in traditional cashmere fiber length measurement methods, convolutional neural network technology was adopted to conduct a systematic study on fracture repair and cross-region detection during the thresholding process of cashmere fibers. A fiber fracture repair model based on the U-Net framework and a cross-point detection model based on the ResNet-50 encoder were designed. By incorporating skip connection mechanisms and hybrid loss functions, the problems of fiber continuity restoration and class imbalance were effectively resolved. The research demonstrates that the fiber fracture repair model achieved a pixel accuracy of 98.72%, and the cross-point detection model exhibited strong segmentation precision and generalization capability. The standard deviation between the average fiber length measured by the model and the results from the manual arrangement method was as low as 0.28 mm, verifying that this method offers high precision, stability, and practicality in cashmere fiber length measurement.

参考文献/References:

[1] 潘依诺, 杨春冰, 杜赵群, 等. MXene基羊绒织物压力传感器的构筑及性能[J]. 现代纺织技术, 2025, 33(10): 115-122.
PAN Yinuo, YANG Chunbing, DU Zhaoqun, et al. Construction and performance of MXene-based Cashmere fabric pressure sensors[J]. Advanced Textile Technology, 2025, 33(10): 115-122.(in Chinese)
[2] 穆奎, 刘慧慧, 唐孔科, 等. 基于曲线拟合及积分算法的山羊绒手扯长度检测方法[J]. 毛纺科技, 2024, 52(6): 96-100.
MU Kui, LIU Huihui, TANG Kongke, et al. Research on the detection method of Cashmere hand-pulled length based on curve fitting and integration algorithm[J]. Wool Textile Journal, 2024, 52(6): 96-100.(in Chinese)
[3] 戴千惠, 王喻, 陈丽君, 等. 羊绒长度的仪器化检测方法[J]. 东华大学学报(自然科学版), 2020, 46(6): 902-907.
DAI Qianhui, WANG Yu, CHEN Lijun, et al. A new measuring method for Cashmere length[J]. Journal of Donghua University(Natural Science), 2020, 46(6): 902-907.(in Chinese)
[4] 方娟, 庞瑞冬, 马爱琴, 等. 双须光电法羊绒测长仪1.0版的精确度分析[J]. 毛纺科技, 2020, 48(12): 67-72.
FANG Juan, PANG Ruidong, MA Aiqin, et al. Analyzing on the accuracy of the double whisker Cashmere length measuring instrument version 1.0[J]. Wool Textile Journal, 2020, 48(12): 67-72.(in Chinese)
[5] Standard test method of sampling and testing staple length of grease wool: ASTM D1234—13[S].Philadelphia: American Society for Testing and Materials, 2013.
[6] Determination of fiber length and distribution(Almeter method): IWTO-17-04[S].London: International Wool Textile Organisa-tion, 2004.
[7] BRIMS M, BAXTER P. Improving agreement on hauteur measurement between OFDA4000 and Almeter[C]// International Wool Textile Organisation Report. Shanghai: IWTO Technology and Standards Committee Sliver Group, 2004.
[8] 金敬业, 杨欢, 吴美琴, 等. 基于双端须丛试样的棉毛纤维长度频率分布测量[J]. 东华大学学报(自然科学版), 2018, 44(2): 196-204, 237.
JIN Jingye, YANG Huan, WU Meiqin, et al. Length-frequency distribution testing of cotton and wool based on dual-beard sample[J]. Journal of Donghua University(Natural Science Edition), 2018, 44(2): 196-204, 237.(in Chinese)
[9] 国家质量监督检验检疫总局. 纤维长度及其分布参数的测定方法 阿尔米特法: GB/T 21293—2007[S]. 北京: 中国标准出版社, 2007.
[10] 王喻, 戴千惠, 陈丽君, 等. 双须光电法与手排法测试羊绒长度对比[J]. 毛纺科技, 2020, 48(1): 9-13.
WANG Yu, DAI Qianhui, CHEN Lijun, et al. Comparison of double whisker measurement method and manual row test result for Cashmere length[J]. Wool Textile Journal, 2020, 48(1): 9-13.(in Chinese)
[11] 杨传颖, 高荣贵, 石宝, 等. 基于图像处理的分梳山羊绒长度检测方法[J]. 毛纺科技, 2020, 48(2): 68-72.
YANG Chuanying, GAO Ronggui, SHI Bao, et al. Test method for carding cashmere length based on image processing[J]. Wool Textile Journal, 2020, 48(2): 68-72.(in Chinese)
[12] 刘正, 吴诗豪, 侯珏, 等. 基于数据增强和改进卷积神经网络的织物纬斜检测[J]. 服装学报, 2023, 8(5): 391-399.
LIU Zheng, WU Shihao, HOU Jue, et al. Fabric skewing detection based on data augmentation and improved convolutional neural network[J]. Journal of Clothing Research, 2023, 8(5): 391-399.(in Chinese)
[13] 韩曙光, 姜凯文, 赵丽妍. 基于深度学习的服装三要素识别[J]. 服装学报, 2022, 7(5): 399- 407.
HAN Shuguang, JIANG Kaiwen, ZHAO Liyan. Recognition of clothing "three elements" based on deep learning[J]. Journal of Clothing Research, 2022, 7(5): 399- 407.(in Chinese)
[14] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[15] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolu-tional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer International Publishing, 2015: 234-241.
[16] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas: IEEE, 2016: 770-778.
[17] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Boston: IEEE, 2015: 3431-3440.
[18] KINGMA D P, BA J L. Adam: a method for stochastic optimization[C]// 3rd International Conference for Learning Representations. San Diego: ICLR, 2015: 1-15.
[19] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//2017 IEEE International Conference on Computer Vision(ICCV). Venice: IEEE, 2017: 2999-3007.

更新日期/Last Update: 2025-12-30