Fourier single pixel imaging (FSPI) is well known for reconstructing high quality images but only at the cost of long imaging time. For real-time applications, FSPI relies on under-sampled reconstructions, failing to provide high quality images. In order to improve imaging quality of real-time FSPI, a fast image reconstruction framework based on deep learning (DL) is proposed. More specifically, a deep convolutional autoencoder network with symmetric skip connection architecture for real time 96 × 96 imaging at very low sampling rates (5–8%) is employed. The network is trained on a large image set and is able to reconstruct diverse images unseen during training. The promising experimental results show that the proposed FSPI coupled with DL (termed DL-FSPI) outperforms conventional FSPI in terms of image quality at very low sampling rates.

Undersampling in Fourier single pixel imaging (FSI) is often employed to reduce imaging time for real-time applications. However, the undersampled reconstruction contains ringing artifacts (Gibbs phenomenon) that occur because the high-frequency target information is not recorded. Furthermore, by employing 3-step FSI strategy (reduced measurements with low noise suppression) with a low-grade sensor (i.e., photodiode), this ringing is coupled with noise to produce unwanted artifacts, lowering image quality. To improve the imaging quality of real-time FSI, a fast image reconstruction framework based on deep convolutional autoencoder network (DCAN) is proposed. The network through context learning over FSI artifacts is capable of deringing, denoising, and recovering details in 256 × 256 images. The promising experimental results show that the proposed deep-learning-based FSI outperforms conventional FSI in terms of image quality even at very low sampling rates (1-4%).

Fourier single-pixel imaging (FSI) uses a digital projector to illuminate the target with Fourier basis patterns, and captures the back-scattered light with a photodetector to reconstruct a high-quality target image. Like other single-pixel imaging (SPI) schemes, FSI requires the projector to be focused on the target for best performance. In case the projector lens is defocused, the projected patterns are blurred and their interaction with the target produces a low-quality image. To address this problem, we propose a fast, adaptive, and highly-scalable deep learning (DL) approach for projector defocus compensation in FSI. Specifically, we employ a deep convolutional neural network (DCNN), which learns to offset the effects of projector defocusing through training on a large image set reconstructed with varying defocus parameters. The model is further trained on experimental data to make it robust against system bias. Experimental results demonstrate the efficacy of our method in reconstructing high-quality images at high projector defocusing. Comparative results indicate the superiority of our method over conventional FSI and existing projector defocus rectification method. The proposed work can also be extended to other SPI methods influenced by projector defocusing, and open avenues for applying DL to correct optical anomalies in SPI.

Visibility restoration of an underwater image degraded by turbid water (due to scattering, absorption, and reflection) is a challenging task which requires careful design of computational imaging methods. The fundamental problems which limit image restoration are random diffusion and absorption of light in turbid water. Recently, the red-channel underwater image restoration method has emerged as an effective approach for visibility restoration under turbid water. However, this method fails to restore the visibility in a degraded image captured under non-uniform turbid water. The method fails due to its reliance on single transmission which cannot correctly express light propagation in an underwater environment. To overcome these problems, we propose a novel image restoration method based on adaptive color compensation and dual transmission estimation (ACDTE) to restore the visibility of underwater images degraded by non-uniform turbid water. The proposed method uses color-tone adaption to determine the hue of underwater images, and estimates global water light with quadtree decomposition. The method estimates dual transmission in the media through coefficient modification for R/G/B channels. Simulation and experimental results show that the proposed method can correct color deviations and has the advantage of visibility restoration of underwater images. The proposed method can be used for marine exploration, underwater rescue, and environmental monitoring.

Visibility restoration of an image degraded by scattering media (such as haze, fog, smog) is a challenging task which requires careful design of computational methods. The fundamental problem which limits clear image reconstruction is the random diffusion of light in the scattering medium. Recently, the dark channel prior method has emerged as a powerful approach for haze removal under adverse weather conditions. However, this method requires high computational time, and fails to achieve haze-free image in the sky region. To overcome these problems, we propose a novel imaging method based on quadtree theory combined with transmission optimization (QTCTO) to restore the visibility of images degraded by scattering medium. The proposed method uses the quadtree theory (for region segmentation) to estimate the global atmospheric light, while the transmission in the media is estimated by coefficient modification for the dark channel. The experimental results show that the proposed method is robust against scattering (under smoke and turbid water conditions) and has the advantage of low computational time. The proposed method can be used for security surveillance, remote sensing, and various military applications.

Inspired by human vision, retina-like imaging has the feature of rotation and scaling invariance, which is beneficial for target tracking and recognition. However, there is a limitation that the center of field of view (FOV) should match with the target centroid. Currently, there is no effective method to quantitatively estimate the effects from this mismatch. To solve the issue, a novel evaluation method is proposed by applying the log-polar transform and Fourier transform. Then reconstruct the target image by exchanging magnitude and phase information between the target image and its rotated or scaled counterpart. Using two current methods of digital image processing, scale-invariant feature transform (SIFT) and biaxial projection similarity analysis (BPS), as evaluation criteria, the proposed method performs efficiently for all eccentric angles. Simulation results show that for a specific target, the invariance of rotation and scaling works effectively for a value above 0.69.