Abstract

Edge images are often used in computer vision, cellular morphology, and surveillance cameras, and are sufficient to identify the type of object. Single-pixel imaging (SPI) is a promising technique for wide-wavelength, low-light-level measurements. Conventional SPI-based edge-enhanced techniques have used shifting illumination patterns; however, this increases the number of the illumination patterns. We propose two deep neural networks to obtain SPI-based edge images without shifting illumination patterns. The first network is an end-to-end mapping between the measured intensities and entire edge image. The latter comprises two path convolutional layers for restoring horizontal and vertical edges individually; subsequently, both edges are combined to obtain full edge reconstructions, such as in the Sobel filter.

© 2022 Optica Publishing Group

Single-pixel imaging using a recurrent neural network combined with convolutional layers

Ikuo Hoshi, Tomoyoshi Shimobaba, Takashi Kakue, and Tomoyoshi Ito
Opt. Express 28(23) 34069-34078 (2020)

Single-pixel imaging using physics enhanced deep learning

Fei Wang, Chenglong Wang, Chenjin Deng, Shensheng Han, and Guohai Situ
Photon. Res. 10(1) 104-110 (2022)

Steganographic optical image encryption based on single-pixel imaging and an untrained neural network

Shanshan Lin, Xiaogang Wang, Angang Zhu, Jidong Xue, and Bijun Xu
Opt. Express 30(20) 36144-36154 (2022)

Single-pixel imaging using discrete Zernike moments

Wenchang Lai, Guozhong Lei, Qi Meng, Dongfeng Shi, Wenda Cui, Pengfei Ma, Yan Wang, and Kai Han
Opt. Express 30(26) 47761-47775 (2022)

DQN based single-pixel imaging

Zhirun Wang, Wenjing Zhao, Aiping Zhai, Peng He, and Dong Wang
Opt. Express 29(10) 15463-15477 (2021)