Abstract

The recently developed image-free sensing technique decouples semantic information directly from compressed measurements without image reconstruction, which maintains the advantages of both the light hardware and software. However, the existing attempts have failed to classify multi-semantic information with multiple targets in the practical fieldof-view. In this Letter, we report a novel image-free sensing technique to tackle the multi-target recognition challenge for the first time, to the best of our knowledge. Different from the convolutional layer stack of image-free single-pixel networks, the reported convolutional recurrent neural network (CRNN) uses the bidirectional LSTM architecture to predict the distribution of multiple characters simultaneously. The framework enables capture of the long-range dependencies, providing a high recognition accuracy of multiple characters. We demonstrate the technique’s effectiveness in license plate detection, which achieves a recognition accuracy of 87.60% at a sampling rate of 5% with a refresh rate higher than 100 FPS.

© 2022 Optica Publishing Group

Weighted sampling-adaptive single-pixel sensing

Xinrui Zhan, Chunli Zhu, Jinli Suo, and Liheng Bian
Opt. Lett. 47(11) 2838-2841 (2022)

Image-free single-pixel object detection

Lintao Peng, Siyu Xie, Tong Qin, Lu Cao, and Liheng Bian
Opt. Lett. 48(10) 2527-2530 (2023)

Text detection and recognition based on a lensless imaging system

Yinger Zhang, Zhouyi Wu, Peiying Lin, Yuting Wu, Lusong Wei, Zhengjie Huang, and Jiangtao Huangfu
Appl. Opt. 61(14) 4177-4186 (2022)

Ultrahigh-security single-pixel semantic encryption

Xinrui Zhan, Chunli Zhu, Zhijie Gao, Shuai Wang, Qiang Jiao, and Liheng Bian
Opt. Lett. 47(23) 6169-6172 (2022)

Multi-class GAN for generating multi-class images in object recognition

Bingxu Wang, Jinhui Lan, and Jiangjiang Gao
J. Opt. Soc. Am. A 39(5) 897-906 (2022)