Rethinking text rectification for scene text recognition

Ke, Wenjun; Wei, Jianguo; Hou, Qingzhi; Hong, Feng

doi:10.1016/j.eswa.2023.119647

Cited by 4 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By predicting the offset of the input image, the multi-objective correction network 12) is able to correct irregular text effectively. Zhan et al designed the Line-Fitting Transformation and iteratively used the TPS correction module to achieve the correction 13) . However, these increasingly complex modules extend the inference speed of the network and increase memory consumption.…”

Section: Non-segmentation-based Character Recognitionmentioning

confidence: 99%

Recognition of Hot-Cast Billet Numbers Based on ICRNN

Yi,

Liu,

Huang

et al. 2024

ISIJ Int.

View full text Add to dashboard Cite

In steel production, the recognition of hot-cast billet numbers suffers from low efficiency and susceptibility to misjudgment. This paper proposes a novel method for identifying hot-cast billet numbers on the basis of improved Convolutional Recurrent Neural Network (ICRNN). Although the existing CRNN has achieved acceptable results in text recognition and music symbol recognition, it is not effective in recognizing industrial characters that are blurred or low-contrast. Based on the theoretical framework of CRNN, the Grayscale Spatial Transformation Network (GSTN) is added before character recognition to rectify the skew caused by shooting angles. The backbone network for feature extraction is changed to ResNet50. Moreover, the Efficient Channel Attention (ECA) module is added to construct the Res-ECA network, which extracts more features of the billet number characters. In the sequence modeling stage, the Bidirectional Gated Recurrent Unit (BiGRU) is used to reduce the risk of overfitting and accelerate convergence. After experimental comparison on a self-made billet number dataset, the put forward ICRNN has faster recognition speed and higher accuracy, with a recognition accuracy of 99.49%, which is 4.8% higher than that of the CRNN. The result fully demonstrates that ICRNN meets the requirements of accuracy and speed for billet number recognition.

show abstract

Section: Non-segmentation-based Character Recognitionmentioning

confidence: 99%