曾秀云,陆华才,吕禾丰.基于改进 Faster R-CNN 的棉布包装缺陷检测的
方法研究[J].电子测量与仪器学报,2022,36(4):179-186 |
基于改进 Faster R-CNN 的棉布包装缺陷检测的
方法研究 |
Research on cotton packaging defect detection methodbased on improved Faster R-CNN |
|
DOI: |
中文关键词: 缺陷检测 Faster R-CNN 特征金字塔网络 双线性插值改进 |
英文关键词:defect detection Faster R-CNN FPN improvement of bilinear interpolation |
基金项目:安徽省自然科学基金(2108085MF197)项目资助 |
|
|
摘要点击次数: 736 |
全文下载次数: 926 |
中文摘要: |
由于传统检测算法对棉布包装缺陷检测不够准确、对小目标缺陷识别率不够高,所以提出改进的 Faster R-CNN 深度学
习网络,对棉布包装存在的破损、污渍、孔洞、杂质、线头等 5 种缺陷进行检测。 通过对图像进行预处理实现图像增强,然后改进
Faster R-CNN 中的 RPN 和 ROI 结构,为加强小目标缺陷的检测能力,在主干网络中融合特征金字塔网络结构,最后对 ROI 进行
双线性插值以解决多次量化引起的像素偏差问题。 实验表明,改进后的网络对棉布包装表面缺陷检测的平均精度均值 mAP 为
91. 34%,与传统算法相比,mAP 值提高了 9. 08%。 |
英文摘要: |
Because the traditional detection algorithm is not accurate enough to detect cotton packaging defects and the recognition rate of
small target defects is not high enough, an improved Faster R-CNN deep learning network is proposed to detect five defects such as
damage, stain, hole, impurity and thread end in cotton packaging. Image enhancement is realized by preprocessing the image, then the
RPN and ROI structure in Faster R-CNN are improved. In order to strengthen the detection ability of small target defects, the feature
pyramid network structure is fused in the backbone network, and finally the ROI is bilinear interpolated to solve the problem of pixel
deviation caused by multiple quantization. Experiments show that the average accuracy of the improved network for cotton packaging
surface defect detection is 91. 34%, which is 9. 08% higher than the traditional algorithm. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|