Infrared Image Denoising Research Articles

Lightweight Infrared Image Denoising Method Based on Adversarial Transfer Learning.

A lightweight infrared image denoising method based on adversarial transfer learning is proposed. The method adopts a generative adversarial network (GAN) framework and optimizes the model through a phased transfer learning strategy. In the initial stage, the generator is pre-trained using a large-scale grayscale visible light image dataset. Subsequently, the generator is fine-tuned on an infrared image dataset using feature transfer techniques. This phased transfer strategy helps address the problem of insufficient sample quantity and variety in infrared images. Through the adversarial process of the GAN, the generator is continuously optimized to enhance its feature extraction capabilities in environments with limited data. Moreover, the generator structure incorporates structural reparameterization technology, edge convolution modules, and progressive multi-scale attention block (PMAB), significantly improving the model's ability to recognize edge and texture features. During the inference stage, structural reparameterization further optimizes the network architecture, significantly reducing model parameters and complexity and thereby improving denoising efficiency. The experimental results of public and real-world datasets demonstrate that this method effectively removes additive white Gaussian noise from infrared images, showing outstanding denoising performance.

SwinDenoising: A Local and Global Feature Fusion Algorithm for Infrared Image Denoising

Infrared image denoising is a critical task in various applications, yet existing methods often struggle with preserving fine details and managing complex noise patterns, particularly under high noise levels. To address these limitations, this paper proposes a novel denoising method based on the Swin Transformer architecture, named SwinDenoising. This method leverages the powerful feature extraction capabilities of Swin Transformers to capture both local and global image features, thereby enhancing the denoising process. The proposed SwinDenoising method was tested on the FLIR and KAIST infrared image datasets, where it demonstrated superior performance compared to state-of-the-art methods. Specifically, SwinDenoising achieved a PSNR improvement of up to 2.5 dB and an SSIM increase of 0.04 under high levels of Gaussian noise (50 dB), and a PSNR increase of 2.0 dB with an SSIM improvement of 0.03 under Poisson noise (λ = 100). These results highlight the method’s effectiveness in maintaining image quality while significantly reducing noise, making it a robust solution for infrared image denoising.

Thermal fault diagnosis of complex electrical equipment based on infrared image recognition

This paper realizes infrared image denoising, recognition, and semantic segmentation for complex electrical equipment and proposes a thermal fault diagnosis method that incorporates temperature differences. We introduce a deformable convolution module into the Denoising Convolutional Neural Network (DeDn-CNN) and propose an image denoising algorithm based on this improved network. By replacing Gaussian wrap-around filtering with anisotropic diffusion filtering, we suggest an image enhancement algorithm that employs Weighted Guided Filtering (WGF) with an enhanced Single-Scale Retinex (Ani-SSR) technique to prevent strong edge halos. Furthermore, we propose a refined detection algorithm for electrical equipment that builds upon an improved RetinaNet. This algorithm incorporates a rotating rectangular frame and an attention module, addressing the challenge of precise detection in scenarios where electrical equipment is densely arranged or tilted. We also introduce a thermal fault diagnosis approach that combines temperature differences with DeeplabV3 + semantic segmentation. The improved RetinaNet's recognition results are fed into the DeeplabV3 + model to further segment structures prone to thermal faults. The accuracy of component recognition in this paper achieved 87.23%, 86.54%, and 90.91%, with respective false alarm rates of 7.50%, 8.20%, and 7.89%. We propose a comprehensive method spanning from preprocessing through target recognition to thermal fault diagnosis for infrared images of complex electrical equipment, providing practical insights and robust solutions for future automation of electrical equipment inspections.

A Novel Adaptive Group Sparse Representation Model Based on Infrared Image Denoising for Remote Sensing Application

Infrared (IR) Image preprocessing is aimed at image denoising and enhancement to help with small target detection. According to the sparse representation theory, the IR original image is low rank, and the coefficient shows a sparse character. The low rank and sparse model could distinguish between the original image and noise. The IR images lack texture and details. In IR images, the small target is hard to recognize. Traditional denoising methods based on nuclear norm minimization (NNM) treat all eigenvalues equally, which blurs the concrete details. They are unable to achieve a good denoising performance. Deep learning methods necessitate a large number of train images, which are difficult to obtain in IR image denoising. It is difficult to perform well under high noise in IR image denoising. Tracking and detection would not be possible without a proper denoising method. This article fuses the weighted nuclear norm minimization (WNNM) with an adaptive similar patch, searching based on the group sparse representation for infrared images. We adaptively selected similar structural blocks based on certain computational criteria, and we used the K-nearest neighbor (KNN) cluster to constitute more similar groups, which is helpful in recovering the complex background with high Gaussian noise. Then, we shrank all eigenvalues with different weights in the WNNM model to solve the optimization problem. Our method could recover more detailed information in the images. The algorithm not only obtains good denoising results in common image denoising but also achieves good performance in infrared image denoising. The target in IR images attains a high signal for the clutter in IR detection systems for remote sensing. Under common data sets and real infrared images, it has a good noise suppression effect with a high peak signal-to-noise ratio (PSNR) and structural similarity index measurement (SSIM), with higher noise and a much more complex background.

Two-stage convolutional neural network for joint removal of sensor noise and background interference in lock-in thermography

Lock-in thermography provides a fast, low-cost, and accurate non-destructive testing for subsurface defect detection in materials. However, there is serious sensor noise and background interference presented in the infrared images captured by lock-in thermography. In this paper, we set up lock-in thermography experiments to analyze the characteristics of sensor noise and background interference. Based on their different characteristics, we design a two-stage CNN model for the joint removal of sensor noise and background interference. This model consists of a number of multi-direction feature extraction blocks (MDFEBs) to extract local features in different directions for pixel-level sensor noise removal, and an encoder–decoder architecture with large receptive fields to extract global features for background interference correction. Experimental results demonstrate that our proposed method outperforms the well-established infrared image denoising and non-uniform background correction techniques on specimens made of different materials and at various excitation frequencies. The proposed two-stage CNN model provides high-quality input of infrared images for the following subsurface defect detection task in lock-in thermography.

Denoising and Restoring of Infrared Image of Power Equipment Based on l2-relaxed l0 Sparse Analysis Priors

Background: The infrared image of electrical equipment often contains snow or is blurred, which makes it difficult to detect and analyze its state. Methods: A prior infrared image denoising and restoring method based on L2-relaxation L0 analysis is proposed. Through the prior image estimation, the problem of image de-blurring and denoising is transformed into the problem of solving the maximum entropy of a posteriori probability, and then the parameters are jointly optimized to widely degrade the image, so that the image is locally sparse from the strip and edge to the linear predictable texture, and the target object to be extracted is obtained by using the alternative iterative solution, to achieve the purpose of denoising and restoring of the original fuzzy infrared image with noise. Two kinds of infrared images with different brightness levels in a 220kV booster station are used for the experiments. Results: Compared with BM3D, TwIST, TVL1C, TVL2C, the experimental results show that the denoising and restoration effect of the proposed method is clearly better than the four methods. The PSNR, ISNR, and SSIM of the proposed method are greater than the others, and the calculation time is shorter. Conclusion: This method can not only enhance the sparsity of the infrared image target and improve the estimation accuracy, but also has the advantages of minimum image distortion, fast convergence speed, and preserving the target detail edge. This method can provide a new idea for other types of infrared image denoising and restoration.

Infrared image impulse noise suppression using tensor robust principal component analysis and truncated total variation.

Infrared image denoising is an essential inverse problem that has been widely applied in many fields. However, when suppressing impulse noise, existing methods lead to blurred object details and loss of image information. Moreover, computational efficiency is another challenge for existing methods when processing infrared images with large resolution. An infrared image impulse-noise-suppression method is introduced based on tensor robust principal component analysis. Specifically, we propose a randomized tensor singular-value thresholding algorithm to solve the tensor kernel norm based on the matrix stochastic singular-value decomposition and tensor singular-value threshold. Combined with the image blocking, it can not only ensure the denoising performance but also greatly improve the algorithm's efficiency. Finally, truncated total variation is applied to improve the smoothness of the denoised image. Experimental results indicate that the proposed algorithm outperforms the state-of-the-art methods in computational efficiency, denoising effect, and detail feature preservation.

A novel method of infrared image denoising and edge enhancement

Infrared images are characterized by small signal-to-noise ratio and low contrast thus making it much difficult to achieve infrared image denoising and edge enhancement. The paper proposes a novel method based on wavelet diffusion, which reduces noise in infrared images while enhancing and preserving edges. First, wavelet modulus and local singularity are combined into a joint conditional model to build an elementary edge map, then the edge map are updated with geometric consistency for better discrimination of edges. To enhancing edges simultaneously, forward and backward diffusion technique is introduced into wavelet diffusion. Finally, the equation of forward and backward diffusion is redesigned according to the new edge map. Experimental results demonstrate that the new proposed method can effectively realize infrared image denoising and edge enhancement.