arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2105.07795cs.CV
收藏

STRIDE:设备内场景文本识别

STRIDE : Scene Text Recognition In-Device

Samsung R&D Institute Bangalore(三星研发研究院班加罗尔)

Rachit S Munjal, Arun D Prabhu, Nikhil Arora, Sukumar Moharana, Gopi Ramena

摘要:

光学字符识别(OCR)系统已广泛用于从图像提取语义信息的各种应用中。为了让用户更好地控制自己的隐私,需要一个设备上的解决方案。当前最先进的模型太重且太复杂,无法在设备上部署。我们开发了一个高效的轻量级场景文本识别(STR)系统,它只有0.88M的参数,并执行实时文本识别。注意力模块往往会提高STR网络的准确性,但通常速度很慢,并且没有针对设备推理进行优化。因此,我们提出将卷积注意力模块用于文本识别网络,旨在通过增加非常小的计算成本为LSTM模块提供通道和空间注意力信息。它将我们在ICDAR 13数据集上的单词准确率提高了近2%。我们还引入了一个新的方向分类器模块,支持同时识别水平和垂直的文本。与领先的商业和其他开源OCR引擎相比,所提出的模型超越了推理时间和内存占用的设备指标,并实现了相当的准确性。我们在Exynos 990芯片组设备上以2.44 ms/字的推理速度部署了该系统,并在ICDAR-13数据集上实现了88.4%的准确率。

英文摘要:

Optical Character Recognition (OCR) systems have been widely used in various applications for extracting semantic information from images. To give the user more control over their privacy, an on-device solution is needed. The current state-of-the-art models are too heavy and complex to be deployed on-device. We develop an efficient lightweight scene text recognition (STR) system, which has only 0.88M parameters and performs real-time text recognition. Attention modules tend to boost the accuracy of STR networks but are generally slow and not optimized for device inference. So, we propose the use of convolution attention modules to the text recognition networks, which aims to provide channel and spatial attention information to the LSTM module by adding very minimal computational cost. It boosts our word accuracy on ICDAR 13 dataset by almost 2\%. We also introduce a novel orientation classifier module, to support the simultaneous recognition of both horizontal and vertical text. The proposed model surpasses on-device metrics of inference time and memory footprint and achieves comparable accuracy when compared to the leading commercial and other open-source OCR engines. We deploy the system on-device with an inference speed of 2.44 ms per word on the Exynos 990 chipset device and achieve an accuracy of 88.4\% on ICDAR-13 dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑