SuperOCR: A Conversion from Optical Character Recognition to Image Captioning
arXiv:2012.02033
Abstract
Optical Character Recognition (OCR) has many real world applications. The existing methods normally detect where the characters are, and then recognize the character for each detected location. Thus the accuracy of characters recognition is impacted by the performance of characters detection. In this paper, we propose a method for recognizing characters without detecting the location of each character. This is done by converting the OCR task into an image captioning task. One advantage of the proposed method is that the labeled bounding boxes for the characters are not needed during training. The experimental results show the proposed method outperforms the existing methods on both the license plate recognition and the watermeter character recognition tasks. The proposed method is also deployed into a low-power (300mW) CNN accelerator chip connected to a Raspberry Pi 3 for on-device applications.
8 pages, 2 figures, 2 tables
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge
- A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector
- An Efficient and Layout-Independent Automatic License Plate Recognition System Based on the YOLO detector
- License Plate Detection and Recognition Using Deeply Learned Convolutional Neural Networks
- MRAM Co-designed Processing-in-Memory CNN Accelerator for Mobile and IoT Applications
- SuperCaptioning: Image Captioning Using Two-dimensional Word Embedding