期刊
SIGNAL IMAGE AND VIDEO PROCESSING
卷 14, 期 1, 页码 67-75出版社
SPRINGER LONDON LTD
DOI: 10.1007/s11760-019-01525-1
关键词
Detonator coded character; Text spotting; Convolutional neural network; Fully convolutional network; Jaccard loss function
资金
- National Natural Science Foundation of China [61001179]
- Key Project of Industry-University-Research Collaborative Innovation in Guangzhou, China [201802020010]
To facilitate the management of detonators, an automatic spotting system is proposed for detonator coded characters based on convolutional neural networks. The system contains a multi-scale detection network, a multi-label recognition network and a post-processing layer. An improved fully convolution network (FCN) is designed as the multi-scale detection network to obtain the accurate response map of the detonator image. Two subnetworks are parallel integrated into the FCN to perform a coarse-to-fine detection. An improved Jaccard loss function with a regularization term is defined to train the FCN. The region of interest (ROI) of the detonator image is achieved when the response map is post-processed by the post-processing layer. Finally, a modified multi-label network is used to recognize the detonator coded characters in the ROI. The experimental results indicate that the proposed system achieves a better spotting performance for detonator coded characters than the state-of-the-art text spotting methods in terms of accuracy and efficiency.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据