Abstract:The information-based material tracking of domestic steel production plants all relies on steel plate numbers. Due to the high complexity of production process, there is an urgent need for online plate number recognition with high accuracy. The recognition technology of machine spray numbers in natural scenes is relatively mature, but it is difficult to realize automatic recognition of handwriting board numbers in complex scenes. A deep learning algorithm with BiLSTM-Attention as the main structure based on the characteristics of handwritten board number on the surface of steel plate in complex work scenarios was proposed. First, combined with complex scenes, image data was preprocessed to ensure the quality of model input images, then residual neural network (ResNet) was used to extract image features, and Bi-directional Long Short-Term Memory (BiLSTM) was used to extract the sequence features of image. Finally, the attention mechanism (Attention) was based to capture the information flow in the sequence, and the feature of each character was integrated to form a text feature vector to predict the output sequence. After on-site testing, the result showed that the algorithm was feasible and effective, and the accuracy of recognition task of handwritten board number on the surface of steel plate reached 86.15%, which met the actual production needs.
徐萌, 王雪飞. 基于BiLSTM-Attention的钢板表面手写板号识别算法[J]. 中国冶金, 2021, 31(10): 86-93.
XU Meng, WANG Xue-fei. Handwritten board number recognition algorithm on steel plate surface based on BiLSTM-Attention[J]. China Metallurgy, 2021, 31(10): 86-93.
Deng Y,Kanervisto A, Ling J,et al. Image-to-markup generation with coarse-to-fine attention[C]//Proceedings of the 34th International Conference on Machine Learning. Sydney,Australia:PMLR 70,2017:980.
[7]
GAO Yun-ze,CHEN Ying-ying,WANG Jin-qiao,et al. Reading scene text with fully convolutional sequence modeling[J]. Neurocomputing,2019,339:161.
SH Choi,JP Yun,K Koo,et al. Localizing slab identification numbers in factory scene images[J]. Expert Systems with Applications,2012,39(9):7621.
[12]
ZHAO Q J,HUANG C H,KE Z N,et al. Recognition results classification and post-processing methods for painted characters on billet surface[J]. Advances in Manufacturing,2017,5(3):261.
[13]
Matas J,Galambos C,Kittler J.Robust detection of lines using the progressive probabilistic Hough transform[J].Computer Vision and Image Understanding,2000,78(1):119.
[14]
Canny J. A computational approach to edge detection[J].IEEEPAMI,1986:679.
[15]
Montalvo M,Guijarro M,Ribeiro A.A novel threshold to identify plant textures in agricultural images by Otsu and principal component analysis[J].Journal of Intelligent & Fuzzy Systems,2018,34(6):4103.
[16]
ZHANG J,DU J,ZHANG S,et al. Watch,attend and parse:An end-to-end neural network based approach to handwritten mathematical expression recognition[J]. Pattern Recognition,2017,71:196.
[17]
SHI B,BAI X,YAO C. An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2016,39(11):2298.