- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
A Novel Patch Variance Biased Convolution Neural Network for No-Reference Image Quality Assessment
摘要： Deep Convolutional Neural Networks (CNNs) have been successfully applied on no-reference image quality assessment (NR-IQA) with respect to human perception. Most of these methods deal with small image patches and use the average score of the test patches for predicting the whole image quality. We discovered that image patches from homogenous regions are unreliable for both neural network training and final image quality score estimation. In addition, image patches with complex structures have much higher chances to achieve better image quality prediction. Based on these findings, we enhanced the conventional CNN-based NR-IQA algorithm to avoid homogenous patches for the network training and quality score estimation. Moreover, we also use a variance-based weighting average to bias the final image quality score to the patches with complex structure. Experimental results show that this simple approach can achieve state-of-the-art performance as compared with well-known NR-IQA algorithms.
关键词： deep learning,no-reference image quality assessment,convolution neural network
更新于2025-09-23 15:22:29
-
[IEEE ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Calgary, AB (2018.4.15-2018.4.20)] 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - No-Reference Hdr Image Quality Assessment Method Based on Tensor Space
摘要： The full-reference image quality assessment (IQA) method are limited in practical applications. Here we propose a no-reference quality assessment method for high dynamic range (HDR) images based on tensor space. First, the tensor decomposition is used to generate three feature maps of an HDR image, considering color and structure information of the HDR image. Second, for a given HDR image, the corresponding multi-scale manifold structure features are extracted from the first feature map. For the second and third feature maps of the HDR image, multi-scale contrast features are extracted. Finally, the extracted features are aggregated by support vector regression to obtain the objective quality score of the HDR image. Experimental results show that the proposed method is superior to some representative full and no-reference methods, and even superior to the full-reference HDR IQA method, HDR-VDP-2.2, on the Nantes database. The proposed method has a higher consistency with human visual perception.
关键词： high dynamic range,feature maps,No-reference,image quality assessment,tensor space
更新于2025-09-23 15:22:29
-
No-reference image quality assessment using gradient magnitude and wiener filtered wavelet features
摘要： No-reference image quality assessment (NR-IQA) aims to evaluate the perceived quality of distorted images without prior knowledge of pristine version of the images. The quality score is predicted based on the features extracted from the distorted image, which needs to correlate with the mean opinion score. The prediction of an image quality score becomes a trivial task, if the noise affecting the quality of an image can be modeled. In this paper, gradient magnitude and Wiener filtered discrete wavelet coefficients are utilized for image quality assessment. In order to reconstruct an estimated noise image, Wiener filter is applied to discrete wavelet coefficients. The estimated noise image and the gradient magnitude are modeled as conditional Gaussian random variables. Joint adaptive normalization is applied to the conditional random distribution of the estimated noise image and the gradient magnitude to form a feature vector. The feature vector is used as an input to a pre-trained support vector regression model to predict the image quality score. The proposed NR-IQA is tested on five commonly used image quality assessment databases and shows better performance as compared to the existing NR-IQA techniques. The experimental results show that the proposed technique is robust and has good generalization ability. Moreover, it also shows good performance when training is performed on images from one database and testing is performed on images from another database.
关键词： Wiener filtering,Gradient magnitude,Discrete wavelet transform,No-reference image quality assessment
更新于2025-09-23 15:21:21
-
Multi-Pooled Inception Features for No-Reference Image Quality Assessment
摘要： Image quality assessment (IQA) is an important element of a broad spectrum of applications ranging from automatic video streaming to display technology. Furthermore, the measurement of image quality requires a balanced investigation of image content and features. Our proposed approach extracts visual features by attaching global average pooling (GAP) layers to multiple Inception modules of on an ImageNet database pretrained convolutional neural network (CNN). In contrast to previous methods, we do not take patches from the input image. Instead, the input image is treated as a whole and is run through a pretrained CNN body to extract resolution-independent, multi-level deep features. As a consequence, our method can be easily generalized to any input image size and pretrained CNNs. Thus, we present a detailed parameter study with respect to the CNN base architectures and the effectiveness of different deep features. We demonstrate that our best proposal—called MultiGAP-NRIQA—is able to outperform the state-of-the-art on three benchmark IQA databases. Furthermore, these results were also confirmed in a cross database test using the LIVE In the Wild Image Quality Challenge database.
关键词： deep learning,no-reference image quality assessment,convolutional neural networks
更新于2025-09-23 15:19:57
-
Generating Image Distortion Maps Using Convolutional Autoencoders with Application to No Reference Image Quality Assessment
摘要： We present two contributions in this work: (i) a reference-free image distortion map generating algorithm for spatially localizing distortions in a natural scene, and (ii) no reference image quality assessment (NRIQA) algorithms derived from the generated distortion map. We use a convolutional autoencoder (CAE) for distortion map generation. We rely on distortion maps generated by the SSIM image quality assessment (IQA) algorithm as the “ground truth” for training the CAE. We train the CAE on a synthetically generated dataset composed of pristine images and their distorted versions. Specifically, the dataset was created by applying standard distortions such as JPEG compression, JP2K compression, Additive White Gaussian Noise (AWGN) and blur to the pristine images. SSIM maps are then generated on a per distorted image basis for each of the distorted images in the dataset and are in turn used for training the CAE. We first qualitatively demonstrate the robustness of the proposed distortion map generation algorithm over several images with both traditional and authentic distortions. We also demonstrate the distortion map’s effectiveness quantitatively on both standard distortions and authentic distortions by deriving three different NRIQA algorithms. We show that these NRIQA algorithms deliver competitive performance over traditional databases like LIVE Phase II, CSIQ, TID 2013, LIVE MD and MDID 2013, and databases with authentic distortions like LIVE Wild and KonIQ-10K. In summary, the proposed method generates high quality distortion map that are used to design robust NRIQA algorithms. Further, the CAE based distortion maps generation method can easily be modified to work with other ground truth distortion maps.
关键词： Convolutional neural network,no reference image quality assessment (IQA),human visual system (HVS),autoencoders
更新于2025-09-11 14:15:04
-
Unified No-Reference Quality Assessment of Singly and Multiply Distorted Stereoscopic Images
摘要： A challenging problem in no-reference quality assessment of multiply distorted stereoscopic images (MDSIs) is to simulate the monocular and binocular visual properties under a mixed type of distortions. Due to the joint effects of multiple distortions in MDSIs, the underlying monocular and binocular visual mechanisms have different manifestations with those of singly distorted stereoscopic images (SDSIs). This paper presents a unified no-reference quality evaluator for SDSIs and MDSIs by learning monocular and binocular local visual primitives (MB-LVPs). The main idea is to learn MB-LVPs to characterize the local receptive field properties of the visual cortex in response to SDSIs and MDSIs. Furthermore, we also consider that the learning of primitives should be performed in a task-driven manner. For this, two penalty terms including reconstruction error and quality inconsistency are jointly minimized within a supervised dictionary learning framework, generating a set of quality-oriented MB-LVPs for each single and multiple distortion modality. Given an input stereoscopic image, feature encoding is performed using the learned MB-LVPs as codebooks, resulting in the corresponding monocular and binocular responses. Finally, responses across all the modalities are fused with probabilistic weights which are determined by the modality-specific sparse reconstruction errors, yielding the final monocular and binocular features for quality regression. The superiority of our method has been verified on several SDSI and MDSI databases.
关键词： multiply distorted,singly distorted,receptive field,monocular and binocular vision,stereoscopic image,local visual primitive,No-reference image quality assessment
更新于2025-09-09 09:28:46
-
Full-Reference Image Quality Assessment by Combining Features in Spatial and Frequency Domains
摘要： Objective employs mathematical and computational theory to objectively assess the quality of output images based on the human visual system (HVS). In this paper, a novel approach based on multifeature extraction in the spatial and frequency domains is proposed. We combine the gradient magnitude and phase congruency maps to generate a local structure (LS) map, which can perceive local structural distortions. The LS matches well with HVS and highlights differences with details. For complex visual information, such as texture and contrast sensitivity, we deploy the log-Gabor filter, and spatial frequency, respectively, to effectively capture their variations. Moreover, we employ the random forest (RF) to overcome the limitations of existing pooling methods. Compared with support vector regression, RF can obtain better prediction results. Extensive experimental results on the five benchmark databases indicate that the proposed method precedes all the state-of-the-art image quality assessment metrics in terms of prediction accuracy. In addition, the proposed method is in compliance with the subjective evaluations.
关键词： log-Gabor filter,random forest (RF),contrast sensitivity function (CSF),full-reference,Image quality assessment (IQA)
更新于2025-09-09 09:28:46
-
Blind Image Quality Assessment with Semantic Information
摘要： No-reference (NR) image quality assessment (IQA) aims to evaluate the quality of an image without reference image, which is greatly desired in the automatic visual signal processing system. Distortions degrade the visual contents and affect the semantics acquisition during the process of human perception. Although the existing methods evaluate the quality of images based on the structure, texture, or statistical characteristics, and deliver high quality prediction accuracy, they do not take the spatial semantics into account. From the perspective of human perception, distortions decrease the structural semantics that represent the structural information, and disturb the spatial semantics that describe the contents of images. Therefore, we attempt to measure the image quality by its degradation of semantics in an image. To extract the semantics of an image, a semantic network is proposed. The network contains convolutional neural networks (CNN) and Long Short-Term Memory (LSTM) that correspond to structural semantics and spatial semantics, respectively. CNN can be regarded as a coarse imitation of human visual mechanism to obtain the structural information, and LSTM can express the contents of an image. Then, by measuring the degradations of different semantics on images, a novel NR IQA is introduced. The proposed approach is evaluated on the databases of LIVE, CSIQ, TID2013, and LIVE multiply distorted database as well as LIVE in the wild image quality challenge database, and the results show superior performance to other state-of-the-art NR IQA methods. Furthermore, we explore the generalization capability of the proposed approach, and the experimental results indicate the proposed approach has a high robustness.
关键词： spatial semantics,No-reference image quality assessment,structural semantics,human perception,semantic network
更新于2025-09-09 09:28:46
-
[IEEE 2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) - San Diego, CA, USA (2018.7.23-2018.7.27)] 2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) - Quality Assessment for Tone-Mapped HDR Images Using Multi-Scale and Multi-Layer Information
摘要： Tone mapping operators and multi-exposure fusion methods allow us to enjoy the informative contents of high dynamic range (HDR) images with standard dynamic range devices, but also introduce distortions into HDR contents. Therefore methods are needed to evaluate tone-mapped image quality. Due to the complexity of possible distortions in a tone-mapped image, information from different scales and different levels should be considered when predicting tone-mapped image quality. So we propose a new no-reference method of tone-mapped image quality assessment based on multi-scale and multi-layer features that are extracted from a pre-trained deep convolutional neural network model. After being aggregated, the extracted features are mapped to quality predictions by regression. The proposed method is tested on the largest public database for TMIQA and compared to existing no-reference methods. The experimental results show that the proposed method achieves better performance.
关键词： multi-scale and multi-layer,tone-mapped HDR images,no-reference image quality assessment
更新于2025-09-09 09:28:46
-
Blind Image Quality Assessment Using Multiscale Local Binary Patterns
摘要： This article proposes a new no-reference image quality assessment method that is able to blindly predict the quality of an image. The method is based on a machine learning technique that uses texture descriptors. In the proposed method, texture features are computed by decomposing images into texture information using multiscale local binary pattern (MLBP) operators. In particular, the parameters of local binary pattern operators are varied, which generates MLBP operators. The features used for training the prediction algorithm are the histograms of these MLBP channels. The results show that, when compared with other state-of-the-art no-reference methods, the proposed method is competitive in terms of prediction precision and computational complexity.
关键词： MLBP,machine learning,multiscale local binary pattern,texture descriptors,no-reference image quality assessment
更新于2025-09-09 09:28:46