激光与光电子学进展, 2020, 57 (16): 161001, 网络出版: 2020-08-05   

基于S-YOLOV3模型的织物实时缺陷检测算法 下载: 1620次

Real-time Fabric Defect Detection Algorithm Based on S-YOLOV3 Model
作者单位
1 西安工程大学电子信息学院, 陕西 西安 710048
2 西安工程大学协同创新中心, 陕西 西安 710048
摘要
为了满足工业上对织物缺陷检测的实时性要求,提出一种基于S-YOLOV3(Slimming You Only Look Once Version 3)模型的织物实时缺陷检测算法。首先使用K均值聚类算法确定目标先验框,以适应不同尺寸的缺陷;然后预训练YOLOV3模型得到权重参数,利用批归一化层中的缩放因子γ评估每个卷积核的权重,将权重值低于阈值的卷积核进行剪枝以得到S-YOLOV3模型,实现模型压缩和加速;最后对剪枝后的网络进行微调以提高模型检测的准确率。实验结果表明:对于不同复杂纹理的织物,所提模型都能准确检测,且平均精度均值达到94%,剪枝后检测速度提高到55 FPS,所得的准确率与实时性均满足工业上的实际需求。
Abstract
To meet the real-time requirements of fabric defect detection in industry, a real-time fabric defect detection algorithm based on S-YOLOV3 (Slimming You Only Look Once Version 3) model is proposed. To develop this algorithm, the K-means clustering algorithm is used to determine the target prior frame for adapting to different sizes of defects. The YOLOV3 model is then pretrained to obtain the weight parameters, and the scaling factor γ is used in the batch normalization layer to evaluate the weight of each convolution kernel. The convolution kernel with weight value lower than the threshold is clipped to obtain the S-YOLOV3 model to achieve compression and acceleration. Finally, the pruned network is fine-tuned to improve the model detection accuracy. Experiment results reveal that the proposed model provides accurate detection of fabrics with different complex textures (average precision of 94%). After pruning, the detection speed is increased to 55 FPS. The obtained accuracy and real-time can meet the actual demand of industry.

周君, 景军锋, 张缓缓, 王震, 黄汉林. 基于S-YOLOV3模型的织物实时缺陷检测算法[J]. 激光与光电子学进展, 2020, 57(16): 161001. Jun Zhou, Junfeng Jing, Huanhuan Zhang, Zhen Wang, Hanlin Huang. Real-time Fabric Defect Detection Algorithm Based on S-YOLOV3 Model[J]. Laser & Optoelectronics Progress, 2020, 57(16): 161001.

本文已被 7 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!