| 王 标,周雅兰,王永红.改进型 Faster R-CNN 网络在电子元件
LED 气泡缺陷检测中的应用[J].电子测量与仪器学报,2021,35(9):136-143 |
| 改进型 Faster R-CNN 网络在电子元件
LED 气泡缺陷检测中的应用 |
| Application of improved faster R-CNN network in bubblesdefect detection of electronic component LED |
| |
| DOI： |
| 中文关键词: 缺陷检测 Faster R-CNN 深度学习 电子元件 LED 瑕疵 |
| 英文关键词:defect detection faster R-CNN deep learning electronic component LED defects |
| 基金项目:国家重点研发计划（2016YFF0101803）项目资助 |
|
|
|
|
| 摘要点击次数: 734 |
| 全文下载次数: 1170 |
| 中文摘要: |
| 电子元件 LED 缺陷当前主要检测方法是通过效率低下的人工目检,而传统机器视觉检测速度慢,且识别精度通常难以
满足实际应用要求。 为了克服这些缺点,提出了一种改进的 Faster R-CNN 网络为框架的电子元件气泡缺陷检测方法。 为了提
高网络的鲁棒性和泛化能力,对数据集以添加噪声、改变亮度的方式进行扩充。 以 Resnet50 和 FPN 网络作为主干网络提取图
像特征,并根据其特征金字塔不同特征预测层的特性调整 anchor 的尺度,构建网络进行训练。 最后在数据集上通过对试验结果
定量分析表明,该方法对 LED 元件气泡缺陷的总体准确率达到了 95. 6%,召回率提高 20. 8%,单幅图片检测时间约为 100 ms,
满足生产中自动化检测的要求。 |
| 英文摘要: |
| Nowadays, the mainstream method of LED defects detection is low-efficiency manual visual inspection. And the traditional
machine visual detection cannot meet its application’s standard with its low precision. To deal with these issues, a LED defects detection
method is proposed based on improved faster R-CNN network framework. In order to improve the robustness and generalization capability
of the network, the dataset is expanded by adding noise and changing the brightness. Resnet50 and FPN network are the backbone
network to extract the characteristics, and the anchor scale is adjusted according to the characteristics of its different feature prediction
layers of the feature pyramid, to construct and train the network. Eventually, the quantitative analysis of the test results on the dataset
testing shows that the method of LED bubble-like defects detection can achieve an overall accuracy of 95. 6%, and the recall rate has a
20. 8% increase. Single-picture detection time is about 100 ms. It can be affirmed that this method can meet the needs of the automatic
detection in manufacture. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
