[1]张启泽,杜 聪,庹 武,等.基于图像处理的男西装前身褶皱弊病识别[J].服装学报,2024,9(06):484-491.
　ZHANG Qize,DU Cong,TUO Wu,et al.Recognition of Front Bodice Wrinkle Defects in Men’s Suits Based on Image Processing[J].Journal of Clothing Research,2024,9(06):484-491.
点击复制

基于图像处理的男西装前身褶皱弊病识别()
分享到：

《服装学报》[ISSN:2096-1928/CN:32-1864/TS]

卷:
第9卷
期数:
2024年06期
页码:
484-491
栏目:
服装工程
出版日期:
2025-01-01

文章信息/Info

Title:
Recognition of Front Bodice Wrinkle Defects in Men’s Suits Based on Image Processing
作者:
张启泽1;  杜 聪2;  庹 武1;  郝潇潇3
1.中原工学院 服装学院,河南 郑州 451191; 2.黄河交通学院 智能工程学院,河南 焦作 454950; 3.上海视觉艺术学院 时尚设计学院,上海 201620
Author(s):
ZHANG Qize1;  DU Cong2;  TUO Wu1;  HAO Xiaoxiao3
1.College of Fashion, Zhongyuan University of Technology, Zhengzhou 451191, China; 2.School of Intelligent Enginee-ring, Huanghe Jiaotong University, Jiaozuo 454950, China; 3.College of Fashion Design, Shanghai Institute of Visual Arts,Shanghai 201620,China
分类号:
TS 941.26
文献标志码:
A
摘要:
前身不良褶皱是西装常见的弊病之一,在西装定制过程中对专业人员依赖较强、耗时且易受主观影响。以男西装为例,构建一种前身褶皱弊病自动识别方法。从企业收集男西装弊病图,借助分割标注工具EISeg提取目标图像,采用双三次插值统一图像分辨率,规范特征参数; 对图像进行灰度化、伽马变换及阈值分割,简化运算数据,增强图像信息,突出褶皱走势; 根据褶皱局部灰度曲线图提取褶皱的宽度、深度和密度3种参数指标,按照阈值分割图提取褶皱方向和褶皱部位2种参数指标; 在BP神经网络中加入粒子群算法改进网络模型,输出弊病类别。研究表明:与传统BP神经网络模型相比,优化网络模型的测试集准确率上升了8.3%,该方法可准确实现男西装前身褶皱弊病的自动识别,并为行业带来新的技术手段和方法。
Abstract:
The poor front bodice wrinkles is one of the common drawbacks of suits, which is highly dependent on professionals, time-consuming and susceptible to subjective influence in the suit customization process. Taking men’s suits as an example, this paper constructs an automatic recognition method for the defects of predecessor pleats. The male suit malpractice map was collected from the enterprise, and the target image was extracted by using the segmentation and annotation tool EISeg. The bicubic interpolation was used to unify the image resolution and standardize the feature parameters. The image was grayed, gamma transform and threshold segmentation to simplify the operation data, enhance the image information, and highlight the fold trend. According to the local gray curve of the fold, the width, depth and density of the fold are extracted. According to the threshold segmentation map, the fold direction and the fold position are extracted. The particle swarm optimization algorithm is added to the BP neural network to improve the network model and output the malpractice category. The results show that the test set accuracy of the optimized network model is 8.3% higher than that of the traditional BP neural network model. This method can accurately realize the automatic identification of the defects of the front of the men’s suit, and bring new technical means and methods to the industry.

参考文献/References:

[1] AGEWALL S. A tailor-made suit always fits best[J]. European Heart Journal Cardiovascular Pharmacotherapy, 2023, 9(3): 199-200.
[2] 彭会齐,陈敏之.基于YOLOv8的女西裤板型弊病检测与修正[J].服装学报,2024,9(1):27-35.
PENG Huiqi,CHEN Minzhi.Detection and correction of women’s pants pattern defects based on YOLOv8[J].Journal of Clothing Research,2024,9(1):27-35.(in Chinese)
[3] 张蒙蒙. 基于褶皱图像识别的着装合体性研究[D]. 青岛: 青岛大学, 2019: 33-35.
[4] DENG N, WANG Y L, XIN B J, et al. A novel objective wrinkle evaluation method for printed fabrics based on multi-view stereo algorithm[J]. The Journal of the Textile Institute, 2022, 113(3): 367-377.
[5] 焦雪莹. 基于轮廓扫描法对着装布面褶曲外观的表征与仪器开发[D]. 上海: 东华大学, 2019: 23-25.
[6] 李晶晶. 服用面料褶曲外观表征与测试方法[D]. 上海: 东华大学, 2020: 23-25.
[7] 庹武, 郝潇潇, 郭鑫, 等. 基于褶皱特征参数的男西装袖弊病类别的自动识别[J]. 现代纺织技术, 2023, 31(2): 47-54.
TUO Wu, HAO Xiaoxiao, GUO Xin, et al. Automatic identification of male suit sleeve drawback categories based on pleated feature parameters[J]. Advanced Textile Technology, 2023, 31(2): 47-54.(in Chinese)
[8] LIAO D H, YIN M S, YI J Q, et al. A nondestructive testing method for detecting surface defects of Si3N4-Bearing cylindrical rollers based on an optimized convolutional neural network[J]. Ceramics International, 2022, 48(21): 31299-31308.
[9] 庹武, 王哓玉, 高雅昆, 等. 基于改进边缘检测算法的服装款式识别[J]. 纺织学报, 2021, 42(10): 157-162.
TUO Wu, WANG Xiaoyu, GAO Yakun, et al. Clothing style identification based on improved edge detection algorithm[J]. Journal of Textile Research, 2021, 42(10): 157-162.(in Chinese)
[10] 胡易, 邹立, 昝世良, 等. 基于暗通道和伽马变换的水下图像增强[J]. 电光与控制, 2021, 28(3): 81-85.
HU Yi, ZOU Li, ZAN Shiliang, et al. Underwater image enhancement based on dark channel and gamma transform[J]. Electronics Optics and Control, 2021, 28(3): 81-85.(in Chinese)
[11] QINGGE L T, ZHENG R, ZHAO X B, et al. An improved Otsu threshold segmentation algorithm[J]. International Journal of Computational Science and Engineering, 2020, 22(1): 146.
[12] 李加雷, 郑学良. 小径管手工氩弧焊气孔和氧化皮射线图像特征[J]. 化工装备技术, 2024, 45(1): 60-63.
LI Jialei, ZHENG Xueliang. Characteristics of X-ray images of pores and oxide skin in manual argon arc welding of small diameter pipes[J]. Chemical Equipment Technology, 2024, 45(1): 60-63.(in Chinese)
[13] WANG D S, TAN D P, LIU L. Particle swarm optimization algorithm: an overview[J]. Soft Computing, 2018, 22(2): 387-408.
[14] CUI K, JING X. Research on prediction model of geotechnical parameters based on BP neural network[J]. Neural Computing and Applications, 2019, 31(12): 8205-8215.
[15] 张博文, 闫德安, 和鹏越, 等. 基于PSO-BP神经网络模型的654SMO热变形行为预测[J]. 钢铁研究学报, 2024, 36(3): 368-377.
ZHANG Bowen, YAN Dean, HE Pengyue, et al. Prediction of thermal deformation behavior of 654SMO based on PSO-BP neural network model[J]. Journal of Iron and Steel Research, 2024, 36(3): 368-377.(in Chinese)
(责任编辑:张 雪)

相似文献/References:

[1]张蒙蒙,庄梅玲*,陈素英.基于褶皱图像识别的着装合体性评价技术[J].服装学报,2017,2(06):497.
　ZHANG Mengmeng,ZHUANG Meiling*,CHEN Suying.Evaluation Technique of Dress Fit Based on Wrinkle Image Recognition[J].Journal of Clothing Research,2017,2(06):497.
[2]张佳慧,王建萍*,吴巧英,等.基于图像处理的翻驳领造型与织物性能关系[J].服装学报,2021,6(01):8.
　ZHANG Jiahui,WANG Jianping*,WU Qiaoying,et al.Relationship Between Property of Fabric and Shape of Lapel Collar Based on Image Processing[J].Journal of Clothing Research,2021,6(06):8.
[3]付燕璇,何 瑛*.基于纬平织物力学性能的3D模拟效果优化[J].服装学报,2022,7(04):296.
　FU Yanxuan,HE Ying*,Optimization of 3D Simulation Effect Based on Mechanical Properties of Weft Flat Fabric[J].Journal of Clothing Research,2022,7(06):296.
[4]张 钥,陈玮婷,王利君*.基于CLO 3D的机织黏合衬悬垂效果模拟[J].服装学报,2023,8(04):290.
　ZHANG Yue,CHEN Weiting,WANG Lijun*.Simulation of the Overhang Effect of Woven Adhesive Lining Based on CLO 3D[J].Journal of Clothing Research,2023,8(06):290.

更新日期/Last Update: 2024-12-30