Deep learning speckle de-noising algorithms for coherent metrology: a review and a phase-shifted iterative scheme [Invited]

Intra-block pyramid cross-scale network for thermal radiation effect correction of uncooled infrared images

Thermal radiation effects can greatly degrade the image quality of uncooled infrared focal plane array detection systems. In this paper, we propose a thermal radiation effect correction network based on intra-block pyramid cross-scale feature extraction and fusion. First, an intra-block pyramid residual attention module is introduced to obtain fine-grained features from long-range IR images by extracting cross-scale local features within the residual block. Second, we propose a cross-scale gated fusion module to efficiently integrate the shallow and abstract features at multiple scales of the encoder and decoder through gated linear units. Finally, to ensure accurate correction of thermal radiation effects, we add double-loss constraints in the spatial-frequency domain and construct a single-input, multi-output network with multiple supervised constraints. The experimental results demonstrate that our proposed method outperforms state-of-the-art correction methods in terms of both visual quality and quantitative evaluation metrics.

Deep learning-based image enhancement in optical coherence tomography by exploiting interference fringe

Optical coherence tomography (OCT), an interferometric imaging technique, provides non-invasive, high-speed, high-sensitive volumetric biological imaging in vivo. However, systemic features inherent in the basic operating principle of OCT limit its imaging performance such as spatial resolution and signal-to-noise ratio. Here, we propose a deep learning-based OCT image enhancement framework that exploits raw interference fringes to achieve further enhancement from currently obtainable optimized images. The proposed framework for enhancing spatial resolution and reducing speckle noise in OCT images consists of two separate models: an A-scan-based network (NetA) and a B-scan-based network (NetB). NetA utilizes spectrograms obtained via short-time Fourier transform of raw interference fringes to enhance axial resolution of A-scans. NetB was introduced to enhance lateral resolution and reduce speckle noise in B-scan images. The individually trained networks were applied sequentially. We demonstrate the versatility and capability of the proposed framework by visually and quantitatively validating its robust performance. Comparative studies suggest that deep learning utilizing interference fringes can outperform the existing methods. Furthermore, we demonstrate the advantages of the proposed method by comparing our outcomes with multi-B-scan averaged images and contrast-adjusted images. We expect that the proposed framework will be a versatile technology that can improve functionality of OCT.

Deep Learning Network for Speckle De-Noising in Severe Conditions

Digital holography is well adapted to measure any modifications related to any objects. The method refers to digital holographic interferometry where the phase change between two states of the object is of interest. However, the phase images are corrupted by the speckle decorrelation noise. In this paper, we address the question of de-noising in holographic interferometry when phase data are polluted with speckle noise. We present a new database of phase fringe images for the evaluation of de-noising algorithms in digital holography. In this database, the simulated phase maps present characteristics such as the size of the speckle grains and the noise level of the fringes, which can be controlled by the generation process. Deep neural network architectures are trained with sets of phase maps having differentiated parameters according to the features. The performances of the new models are evaluated with a set of test fringe patterns whose characteristics are representative of severe conditions in terms of input SNR and speckle grain size. For this, four metrics are considered, which are the PSNR, the phase error, the perceived quality index and the peak-to-valley ratio. Results demonstrate that the models trained with phase maps with a diversity of noise characteristics lead to improving their efficiency, their robustness and their generality on phase maps with severe noise.