Image-free multi-character recognition

TL;DR

This paper introduces a novel image-free sensing method using a CRNN with bidirectional LSTM for multi-character recognition, achieving high accuracy and speed in license plate detection without relying on traditional imaging.

Contribution

The work presents the first application of image-free sensing for multi-target recognition using a CRNN with bidirectional LSTM, enabling simultaneous prediction of multiple characters.

Findings

Achieved 87.60% recognition accuracy on license plates.

Operates at over 100 FPS with only 5% sampling rate.

Successfully recognizes multiple characters in real-time.

Abstract

The recently developed image-free sensing technique maintains the advantages of both the light hardware and software, which has been applied in simple target classification and motion tracking. In practical applications, however, there usually exist multiple targets in the field of view, where existing trials fail to produce multi-semantic information. In this letter, we report a novel image-free sensing technique to tackle the multi-target recognition challenge for the first time. Different from the convolutional layer stack of image-free single-pixel networks, the reported CRNN network utilities the bidirectional LSTM architecture to predict the distribution of multiple characters simultaneously. The framework enables to capture the long-range dependencies, providing a high recognition accuracy of multiple characters. We demonstrated the technique's effectiveness in license plate detection, which achieved 87.60% recognition accuracy at a 5% sampling rate with a higher than 100 FPS refresh rate.