Iterative Super-resolution Reconstruction Research Articles

Infrared fiber bundle image super-resolved based on computational imaging

As the representative of flexibility in optical imaging media, in recent years, fiber bundles have emerged as a promising architecture in the development of compact visual systems. Dedicated to tackling the problems of universal honeycomb artifacts and low signal-to-noise ratio (SNR) imaging in fiber bundles, the iterative super-resolution reconstruction network based on a physical model is proposed. Under the constraint of solving the two subproblems of data fidelity and prior regular term alternately, the network can efficiently “regenerate” the lost spatial resolution with deep learning. By building and calibrating a dual-path imaging system, the real-world dataset where paired low resolution (LR) - high resolution (HR) images on the same scene can be obtained simultaneously. Numerical results on both USAF target and complex target objects demonstrate that the algorithm can restore high contrast images without pixilated noise. On the basis of super-resolution reconstruction, compound eye image composition based on fiber bundle is also realized in this paper for the actual imaging requirements. The proposed work is the first to apply a physical model-based network structure to fiber bundle imaging in the long-wave infrared band, effectively promoting the engineering application of thermal radiation detection.

Model-based deep learning for fiber bundle infrared image restoration

As the representative of flexibility in optical imaging media, in recent years, fiber bundles have emerged as a promising architecture in the development of compact visual systems. Dedicated to tackling the problems of universal honeycomb artifacts and low signal-to-noise ratio (SNR) imaging in fiber bundles, the iterative super-resolution reconstruction network based on a physical model is proposed. Under the constraint of solving the two subproblems of data fidelity and prior regularization term alternately, the network can efficiently “regenerate” the lost spatial resolution with deep learning. By building and calibrating a dual-path imaging system, the real-world dataset where paired low-resolution (LR) - high-resolution (HR) images on the same scene can be generated simultaneously. Numerical results on both the United States Air Force (USAF) resolution target and complex target objects demonstrate that the algorithm can restore high-contrast images without pixilated noise. On the basis of super-resolution reconstruction, compound eye image composition based on fiber bundle is also embedded in this paper for the actual imaging requirements. The proposed work is the first to apply a physical model-based deep learning network to fiber bundle imaging in the infrared band, effectively promoting the engineering application of thermal radiation detection.

The Influence on Image Reconstruction Methods on Digital Breast Tomosynthesis Guided Vacuum-assisted Biopsy for Clustered Microcalcifications

In this study, we verified the targeting time and coordinates of stereotactic vacuum-assisted biopsy (STVAB) and digital breast tomosynthesis-guided vacuum-assisted biopsy (DBTVAB). We used 23 fabricated phantom samples that consisted of small round, amorphous, and pleomorphic clustered microcalcifications, and two types of image reconstruction methods: filtered back projection (FBP) and iterative super-resolution reconstruction (ISR). Regarding targeting time, DBTVAB tended to be shorter than STVAB in the two image reconstruction methods and the targeting time was significantly shorter for the amorphous and pleomorphic calcifications using DBTVAB with FBP compared to that using STVAB (p=0.022 for amorphous, p=0.041 for pleomorphic). The targeting time for small round calcifications was longer using DBTVAB with ISR compared to that using STVAB (p=0.013). For targeting coordinates, using DBTVAB with FBP showed a significant difference only for pleomorphic calcifications but using DBTVAB with ISR showed no significance. The findings of this study suggest that FBP is more suitable than ISR to be used as an image reconstruction method, and DBTVAB can shorten the targeting time compared to STVAB.

Comparative Experimental Exploration of Robust Norm Functions for Iterative Super Resolution Reconstructions under Noise Surrounding

In DIP (Digital Image Processing) research society, the multi-frame SRR (Super Resolution Reconstruction) algorithm has grown to be the momentous theme in the last ten years because of its cost effectiveness and its superior spectacle. Consequently, for a multi-frame SRR algorithm which is commonly comprised of a Bayesian ML (Maximum Likelihood) approach and a regularization technique into the unify SRR framework, numerous robust norm functions (which have both redescending and non-redescending influence functions) have been commonly comprised in the unify SRR framework for increasingly against noise or outlier. First, this paper presents the mathematical model of several iterative SRR based on Bayesian ML (Maximum Likelihood) approach and a regularization technique. Three groups of robust norm functions (a zero-redescending influence function (Tukey’s Biweight, Andrew’s Sine and Hampel), a nonzero-redescending influence function (Lorentzian, Leclerc, Geman&McClure, Myriad and Meridian) and a non-redescending influence function (Huber)) are mathematically incorporated into the SRR framework. The close form solutions of the SRR framework based on these robust norm functions have been concluded. Later, the experimental section utilizes two standard images of Lena and Susie (40th) for pilot studies and fraudulent noise patterns of noiseless, AWGN, Poisson, Salt&Pepper, and Speckle of several magnitudes are used to contaminate these two standard images. In order to acquire the maximum PSNR, the comparative experimental exploration has been done by comprehensively tailoring all experimental parameters such as step-size, regularization parameter, norm constant parameter.

Super-resolution Techniques based on Temporal Recursion using Optimal and Real Parameters

The major goal of a super-resolution image reconstruction method is to construct a single in-depth high-resolution image from a group of numerous low-resolution images of the scene taken from diverse positions. Since every low-resolution image retains a different view of the scene, it is possible to reconstruct an in-depth high-resolution image. Thus image super-resolution is a key to overcoming the material precincts of hardware competence. An enormous amount of video is still in traditional formats or at an even lower resolution. Some also has relentless coding artifacts. Hence, there is a need for techniques that can improve video quality and that show all the traditional and low-resolution videos on panels with high-resolution grids. Iterative super-resolution reconstruction algorithms can accomplish this exigent chore by using internal image models and an incorporated feedback loop to control output quality, thereby improving resolution and lessening artifacts. This article portrays the prospects of iterative reconstruction algorithms and establishes a new super-resolution algorithm that is computationally very strong and efficient against motion estimation errors.

Super-Resolution of License Plate Images using Algebraic Reconstruction Technique

In this paper, an iterative super-resolution reconstruction method is introduced for license plate recognition. A high-resolution image of the license plate is reconstructed by fusing the information derived from a set of subpixel shifted low-resolution images. The reconstruction problem is formulated as a system of linear equations that is solved by using the simultaneous algebraic reconstruction technique (SIRT). Simulation experiments show that SIRT can reconstruct a HR image with superior quality compared to conventional super-resolution reconstruction methods. 

Video Enhancement Based on A Robust Hampel Iterative SRR with a General Observation Model

This paper proposes a novel robust Super Resolution Reconstruction (SRR) framework that can enhance a real complex video sequence and is applicable to any noise models. Although SRR algorithms have received considerable attention within the traditional research community, these algorithms are typically very sensitive to their assumed model of data and noise, which limits their utility. The real noise models that corrupt the measured sequence are unknown; consequently, SRR algorithms using L1 or L2 norm may degrade the image sequence rather than enhance it therefore the robust norm applicable to several noise and data models is desired in SRR algorithms. This paper proposes a SRR framework based on the stochastic regularization technique of Bayesian MAP estimation by minimizing a cost function. In order to tolerate to any noise models, the Hampel norm is used for measuring the difference between the projected estimate of the high-resolution image and each low resolution image, and removing outliers in the data. Tikhonov regularization is used to remove artifacts from the final result and improve the rate of convergence. Moreover, in order to cope with real video sequences and complex motion sequences, this paper proposes a SRR General Observation Model (GOM or a±ne block-based transform) devoted to the case of nonisometric inter-frame motion. In the experimental section, the proposed framework can enhance real complex motion sequences, such as Suzie and Foreman sequence, and con¯rm the effectiveness of our algorithm and demonstrate its superiority to other SRR algorithms based on L1 and L2 norm for several noise models (such as AWGN, Poisson noise, Salt & Pepper noise and Speckle noise) at several noise power.