- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Blind Noisy Image Quality Assessment Using Sub-Band Kurtosis
摘要： Noise that afflicts natural images, regardless of the source, generally disturbs the perception of image quality by introducing a high-frequency random element that, when severe, can mask image content. Except at very low levels, where it may play a purpose, it is annoying. There exist significant statistical differences between distortion-free natural images and noisy images that become evident upon comparing the empirical probability distribution histograms of their discrete wavelet transform (DWT) coefficients. The DWT coefficients of low- or no-noise natural images have leptokurtic, peaky distributions with heavy tails; while noisy images tend to be platykurtic with less peaky distributions and shallower tails. The sample kurtosis is a natural measure of the peakedness and tail weight of the distributions of random variables. Here, we study the efficacy of the sample kurtosis of image wavelet coefficients as a feature driving an extreme learning machine which learns to map kurtosis values into perceptual quality scores. The model is trained and tested on five types of noisy images, including additive white Gaussian noise, additive Gaussian color noise, impulse noise, masked noise, and high-frequency noise from the LIVE, CSIQ, TID2008, and TID2013 image quality databases. The experimental results show that the trained model has better quality evaluation performance on noisy images than existing blind noise assessment models, while also outperforming general-purpose blind and full-reference image quality assessment methods.
关键词： sub-band,discrete wavelet transform (DWT),extreme learning machine (ELM),kurtosis,Blind noisy image quality assessment
更新于2025-09-23 15:23:52
-
[IEEE 2018 IEEE 3rd International Conference on Signal and Image Processing (ICSIP) - Shenzhen, China (2018.7.13-2018.7.15)] 2018 IEEE 3rd International Conference on Signal and Image Processing (ICSIP) - A New Image Denoising Method Based on Wavelet Multi-scale Registration Fusion
摘要： Image denoising is an eternal research topic. In this paper, a new image denoising method based on wavelet multi-scale registration fusion is proposed to solve the problem that it is easy to lose the edge and texture details of the image in the denoising process. First of all, we can get multiple sets of wavelet coefficients by using different wavelet bases to decompose the same noisy image. Then, the obtained wavelet coefficients are processed by the improved wavelet threshold shrink to get multiple denoising images of the same noisy image. At last, we use the fusion registration algorithm proposed in this paper to fuse the edge feature of multiple denoising images to get the final denoising image. The experiments prove that this method not only can effectively overcome the pseudo gibbs phenomenon caused by the hard threshold method, but also can overcome the image distortion phenomenon caused by the soft threshold method. More importantly, compared with existing methods, this method can effectively preserve the edge detail and texture features of the image and the image has a better visual effect after fusion registration. Therefore, it has a better application value.
关键词： wavelet multi-scale registration fusion,wavelet transform,improved wavelet threshold shrink,image denoising
更新于2025-09-23 15:22:29
-
[IEEE 2018 25th International Conference on Mechatronics and Machine Vision in Practice (M2VIP) - Stuttgart, Germany (2018.11.20-2018.11.22)] 2018 25th International Conference on Mechatronics and Machine Vision in Practice (M2VIP) - Secure and Robust Color Image Watermarking for Copyright Protection Based on Lifting Wavelet Transform
摘要： This paper presents a secure and robust color image watermarking algorithm for copyright protection. This method uses lifting wavelet transform (LWT) to decompose both the host image and the watermark into different sub-bands and performs watermark embedding in the transform domain. A security key is introduced in the algorithm for security purpose. Two color images are used to test the performance of the proposed algorithm. Results show that the scheme not only has good imperceptibility and but also are robust to various geometric and image processing attacks.
关键词： image processing,watermarking,robust and secure,lifting wavelet transform
更新于2025-09-23 15:22:29
-
[IEEE 2018 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET) - Chennai (2018.3.22-2018.3.24)] 2018 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET) - Automatic Segmentation of Exudates in Retinal Images
摘要： This paper presents a new technique for segmentation of exudates in fundus images. This technique is based on Discrete Wavelet Transform (DWT) and histogram based thresholding procedure. In this work, Optic Disc (OD) is eliminated using DWT from original green component image prior segmentation of exudates. This step aids to avoid the misclassification of exudates region. Histogram based threshold calculation procedure is introduced for segmentation of bright regions in green component image. Hard exudates are obtained after masking the OD region in segmented bright regions of the green component image. This technique was evaluated on images from DIARETDB0 and DIARETDB1 databases. The average sensitivity, specificity and accuracy achieved by proposed method are 0.7890, 0.9972 and 0.9964 respectively. Comparison with existing methods offered in the literature shows that the performance of proposed approach is significant.
关键词： Optic Disc,Retinal image,Segmentation,Exudates,Discrete Wavelet Transform
更新于2025-09-23 15:22:29
-
Dual tree complex wavelet transform incorporating SVD and bilateral filter for image denoising
摘要： In recent years massive production of digital images increased the need for image denoising. The effect of noise can be removed by using spatial and frequency domain approaches. Discrete Wavelet Transforms (DWT) is a frequency domain approach, which removes the noise by shrinking the wavelet coefficients using simple threshold value. Even though wavelet transform is popularly used in image processing applications, shift variance and poor directional selectivity are the two noteworthy limitations. In order to overcome these limitations, Dual Tree Complex Wavelet Transform (DTCWT) is used for perfect reconstruction of noisy image. A DTCWT incorporating Singular Value Decomposition (SVD) with Frobenius energy correcting factor and bilateral filter for image denoising using bivariate shrinkage function for thresholding the image is proposed in this paper. The denoising performance of the proposed method in terms of PSNR and it indicates that the proposed method outperforms over other existing techniques.
关键词： bilateral filter,SVD,bivariate shrinkage,thresholding technique,wavelet transform,DTCWT,image denoising
更新于2025-09-23 15:22:29
-
Infrared super-resolution imaging using multi-scale saliency and deep wavelet residuals
摘要： Infrared (IR) imaging systems with low-density focal plane arrays produce images with poor spatial resolution. To address this limitation, super-resolution (SR) algorithms can be applied on IR-low resolution (LR) images. In this paper, we present a new SR technique based on the multi-scale saliency detection and the residuals learned by the deep convolutional neural network (CNN) in the wavelet domain (DWCNN). The input LR image is processed in the transformed domain by applying 2D discrete wavelet transform. It decomposes an image into its low-frequency and high-frequency subbands. The multi-scale saliency detection is used to extract small scale and large scale salient feature maps from the bicubic upscaled LR image. These maps are incorporated in the high-frequency subbands of the LR image. Furthermore, the low-frequency and high-frequency subands are re?ned using the residuals learned by the DWCNN in training phase. The proposed algorithm is compared with the conventional and state-of-the-art SR methods. Results indicate that our method yields good reconstruction quality with high peak signal to ratio, structural similarity and low blur indices. Besides, our method requires less computational time.
关键词： Infrared imaging,Convolutional neural network,Discrete wavelet transform,Multi-scale saliency,Super-resolution
更新于2025-09-23 15:22:29
-
Achieving Super-Resolution Remote Sensing Images via the Wavelet Transform Combined With the Recursive Res-Net
摘要： Deep learning (DL) has been successfully applied to single image super-resolution (SISR), which aims at reconstructing a high-resolution (HR) image from its low-resolution (LR) counterpart. Different from most current DL-based methods, which perform reconstruction in the spatial domain, we use a scheme based in the frequency domain to reconstruct the HR image at various frequency bands. Further, we propose a method that incorporates the wavelet transform (WT) and the recursive Res-Net. The WT is applied to the LR image to divide it into various frequency components. Then, an elaborately designed network with recursive residual blocks is used to predict high-frequency components. Finally, the reconstructed image is obtained via the inverse WT. This paper has three main contributions: 1) an SISR scheme based on the frequency domain is proposed under a DL framework to fully exploit the potential to depict images at different frequency bands; 2) recursive block and residual learning in global and local manners are adopted to ease the training of the deep network, and the batch normalization layer is removed to increase the flexibility of the network, save memory, and promote speed; and 3) the low-frequency wavelet component is replaced by an LR image with more details to further improve performance. To validate the effectiveness of the proposed method, extensive experiments are performed using the NWPU-RESISC45 data set, and the results demonstrate that the proposed method outperforms state-of-the-art methods in terms of both objective evaluation and subjective perspective.
关键词： residual learning,wavelet transform (WT),remote sensing image,super resolution,Recursive network
更新于2025-09-23 15:22:29
-
Evaluating Feature Extractors and Dimension Reduction Methods for Near Infrared Face Recognition Systems
摘要： This study evaluates the performance of global and local feature extractors as well as dimension reduction methods in NIR domain. Zernike moments (ZMs), Independent Component Analysis (ICA), Radon Transform + Discrete Cosine Transform (RDCT), Radon Transform + Discrete Wavelet Transform (RDWT) are employed as global feature extractors and Local Binary Pattern (LBP), Gabor Wavelets (GW), Discrete Wavelet Transform (DWT) and Undecimated Discrete Wavelet Transform (UDWT) are used as local feature extractors. For evaluation of dimension reduction methods Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPDA), Linear Discriminant Analysis + Principal Component Analysis (Fisherface), Kernel Fisher Discriminant Analysis (KFD) and Spectral Regression Discriminant Analysis (SRDA) are used. Experiments conducted on CASIA NIR database and PolyU-NIRFD database indicate that ZMs as a global feature extractor, UDWT as a local feature extractor and SRDA as a dimension reduction method have superior overall performance compared to some other methods in the presence of facial expressions, eyeglasses, head rotation, image noise and misalignments.
关键词： comparative study,undecimated discrete wavelet transform,Face recognition,near infrared,Zernike moments
更新于2025-09-23 15:22:29
-
An improved infrared image processing method based on adaptive threshold denoising
摘要： This paper combines the image adaptive threshold denoising algorithm and performs double threshold mapping processing to the infrared image, which effectively reduces the influence of these phenomena to the infrared image and improves the quality of the image. In this paper, the infrared image denoising technology is studied, and an infrared image denoising method based on the wavelet coefficient threshold processing is proposed. This method is based on the noise distribution characteristics of infrared images, the multiplicative noise in the infrared image is transformed into an additive noise, and the wavelet transform coefficient of the transformed infrared image is processed to denoise the image. On this basis, the advantages and disadvantages of the soft and hard threshold functions are deeply analyzed, and an adaptive threshold function with adjustable parameter is constructed. At the same time, in order to suppress the Gibbs visual distortion caused by the absence of translation invariance of the orthogonal wavelet transform, the two-input wavelet transform with translation invariance is introduced, and a double threshold mapping infrared image processing method based on the adaptive threshold denoising algorithm based on the two-input wavelet transform is formed. Simulation results show that the method proposed in this paper has a better suppression of noise, maintains the integrity of image details, and improves the image quality to a certain extent.
关键词： Threshold function,Double threshold mapping,Image denoising,Binary wavelet transform,Infrared image
更新于2025-09-23 15:22:29
-
GWDWT-FCM: Change Detection in SAR Images Using Adaptive Discrete Wavelet Transform with Fuzzy C-Mean Clustering
摘要： Change detection in remote sensing images turns out to play a significant role for the preceding years. Change detection in synthetic aperture radar (SAR) images comprises certain complications owing to the reality that it endures from the existence of the speckle noise. Hence, to overcome this limitation, this paper intends to develop an improved model for detecting the changes in SAR image. In this model, two SAR images captivated at varied times will be considered as the input for the change detection process. Initially, discrete wavelet transform (DWT) is employed for image fusion, where the coefficients are optimized using improved grey wolf optimization (GWO) called adaptive GWO (AGWO) algorithm. Finally, the fused images after inverse transform are clustered using fuzzy C-means (FCM) clustering technique and a similarity measure is performed among the segmented image and ground truth image. With the use of all these technologies, the proposed model is termed as adaptive grey wolf-based DWT with FCM (AGWDWT-FCM). The similarity measures analyze the relevant performance measures such as accuracy, specificity and F1 score. Moreover, the performance of the AGWDWT-FCM in change detection model is compared to other conventional models, and the improvement is noted.
关键词： Filter coefficient,Adaptive discrete wavelet transform,Grey wolf optimization,Synthetic aperture radar,Fuzzy C-means clustering
更新于2025-09-23 15:21:21