Full-reference image quality assessment based on image segmentation with edge feature

Image quality assessment (IQA) is a field that focuses on evaluating the quality of images, playing a crucial role in various image processing and/or computer vision applications. Traditional full-reference (FR) IQA algorithms struggle with an accurate perceptual quality evaluation due in part to their reliance on handcrafted features and simple mathematical functions to calculate the elementwise distance between the reference and distorted images. Although deep-learning-based FR IQA methods have shown advantages in providing a certain degree of tolerance to texture resampling, their performances are still limited by the redundant model parameters and ineffective quality-aware feature extraction/representation. To address this issue, in this paper, we propose a multi-modal dual-attention FR IQA algorithm based on combining a global-and-local image structure analysis with text information interpreted by the widely used large language model. Specifically, the proposed multi-modal dual-attention network consists of four modules. First, a global-and-local feature extraction module was employed to extract the quality-aware features from the reference and distorted images, which were then realigned along the spatial and channel dimensions by a feature fusion module. To take into account both the channel and spatial attentions and thus increase the model capacity in representing long-range dependencies among different image areas, a feature enhancement module was designed to encode the spatial information along two directions, based on which the direction-aware attention maps with position information were generated. Finally, the text prior knowledge interpreted by the contrastive language-image pre-training (CLIP) model was embedded to assist the attention-based prediction module for quality estimation. Experimental results on four benchmark datasets demonstrate the effectiveness of our model as compared with other state-of-the-art FR IQA methods. The code is available at https://vinelab.jp/m2da/.

Screen content image quality assessment based on convolutional neural networks

In the process of substation inspection, it is challenging to handle a large number of image quality assessments efficiently. Given that substation equipment has a fine structure, traditional methods are difficult to accurately capture local texture distortions, and complex backgrounds can easily lead to global semantic confusion. Additionally, subjective quality assessment is costly, and the pre-training of no-reference quality assessment is time-consuming. This paper proposes a full-reference image quality assessment method based on a ranking-aware and attention-guided fusion network. This method first uses a dual-branch network constructed by Vision Transformer (ViT) and Convolutional Neural Network (CNN) to extract the global semantic features and local texture features of the image respectively. On this basis, a ranking-aware sorting module is designed to calculate the image structure distortion through feature magnitude ranking and cosine similarity. Meanwhile, a statistical attention mechanism is introduced to generate an attention map through random projection and difference calculation, guiding the model to focus on local perception-sensitive regions. Finally, the ranking-aware score and the attention-guided features are fused, and the quality score is output through a regressor. The experimental results show that this method outperforms most mainstream full-reference image quality assessment (FR-IQA) methods. In the future, it can be extended to practical application scenarios such as power grid inspection.

Objective image quality assessment (IQA) models have been developed by effective features to imitate the characteristics of human visual system (HVS). Actually, HVS is extremely sensitive to color degradation and complex texture changes. In this paper, we firstly reveal that many existing full reference image quality assessment (FR-IQA) methods can hardly measure the image quality with contrast and masking texture changes. To solve this problem, considering texture masking effect, we proposed a novel FR-IQA method, called Texture and Color Quality Index (TCQI). The proposed method considers both in the masking effect texture and color visual perceptual threshold, which adopts three kinds of features to reflect masking texture, color difference and structural information. Furthermore, random forest (RF) is used to address the drawbacks of existing pooling technologies. Compared with other traditional learning-based tools (support vector regression and neural network), RF can achieve the better prediction performance. Experiments conducted on five large-scale databases demonstrate that our approach is highly consistent with subjective perception, outperforms twelve the state-of-the-art IQA models in terms of prediction accuracy and keeps a moderate computational complexity. The cross database validation also validates our approach achieves the ability to maintain high robustness.

Quality assessment of images with multiple distortions based on phase congruency and gradient magnitude

Hierarchical degradation-aware network for full-reference image quality assessment

An optimized CNN-based quality assessment model for screen content image

Although a great number of objective methods for assessing perceptual image quality have been proposed, their performances on different distortion types are still unsatisfactory. It is a great challenge for image quality assessment (IQA) that distorted images may have similar visual perception even if their distortion types and magnitudes are totally different, because some structural changes caused by distortions are visually imperceptible. In this paper, we propose a novel full-reference IQA (FR-IQA) scheme based on multiscale fuzzy gradient similarity deviation (MFGSD), where fuzzy inference system is introduced to reduce the negative impact of imperceptible distortions, and the standard deviation of fuzzy gradient similarity is utilized to measure their quality distinction. Extensive experiments are conducted on two publicly available image databases, and compared with many existing state-of-art FR-IQA schemes, and the proposed MFGSD has a better performance on different distortion types and strengths.

Tremendous advances of information technology provide a large role for digital images for delivering information quickly and accurately. However, digital images are exposed to distortions and imperfect quality during acquisition, compression, transmission, processing and reproduction. Therefore, the development of effectively image quality assessment (IQA) is crucial in order to identify and measure the distortion in image quality. Perception by human observers (manually) as the ultimate receiver of the visual information contained in an image and most reliable to assess the quality of image. However, manual subjective assessment method is considered costly and time consuming. This lead to the development of proposed automatic method to measure image quality as accurately as the manual method. The goal of objective image quality assessment is to develop a computational model that can accurately and automatically predict the perceptual image quality. An ideal objective IQA method should be able to imitate the quality predictions of an average human observer. Full-reference image quality assessment is a method where image with perfect quality provided as a reference image for guiding the IQA system. This paper presents the study and comparison between two full-reference method that frequently used in IQA system that is method based on the properties of human visual system (HVS) and method based on principle of image structure. Both of this method is proven can be used to measure digital images quality accurately and depends on distortion types that occurred on measured images.

An intelligent vehicle image segmentation and quality assessment model

Objective image quality assessment (IQA) is imperative in the current multimedia-intensive world, in order to assess the visual quality of an image at close to a human level of ability. Many parameters such as color intensity, structure, sharpness, contrast, presence of an object, etc., draw human attention to an image. Psychological vision research suggests that human vision is biased to the center area of an image and display screen. As a result, if the center part contains any visually salient information, it draws human attention even more and any distortion in that part will be better perceived than other parts. To the best of our knowledge, previous IQA methods have not considered this fact. In this paper, we propose a full reference image quality assessment (FR-IQA) approach using visual saliency and contrast; however, we give extra attention to the center by increasing the sensitivity of the similarity maps in that region. We evaluated our method on three large-scale popular benchmark databases used by most of the current IQA researchers (TID2008, CSIQ and LIVE), having a total of 3345 distorted images with 28 different kinds of distortions. Our method is compared with 13 state-of-the-art approaches. This comparison reveals the stronger correlation of our method with human-evaluated values. The prediction-of-quality score is consistent for distortion specific as well as distortion independent cases. Moreover, faster processing makes it applicable to any real-time application. The MATLAB code is publicly available to test the algorithm and can be found online at.

Perceptual quality assessment for fine-grained compressed images

To improve data transmission efficiency, image compression is a commonly used method with the disadvantage of accompanying image distortion. There are many image restoration (IR) algorithms, and one of the most advanced algorithms is the generative adversarial network (GAN)-based method with a high correlation to the human visual system (HVS). To evaluate the performance of GAN-based IR algorithms, we proposed an ensemble image quality assessment (IQA) called ATDIQA (Auxiliary Transformer with DISTS IQA) to give weights on multiscale features global self-attention transformers and local features of convolutional neural network (CNN) IQA of DISTS. The result not only performed better on the perceptual image processing algorithms (PIPAL) dataset with images by GAN IR algorithms but also has good model generalization over LIVE and TID2013 as traditional distorted image datasets. The ATDIQA ensemble successfully demonstrates its performance with a high correlation with the human judgment score of distorted images.

This study focuses on improving the objective alignment of image quality assessment (IQA) algorithms with human visual perception. Existing methodologies, predominantly those based on the Laplacian of Gaussian (LoG) filter, often neglect the impact of color channels on human visual perception. Consequently, we propose a full-reference IQA method that integrates multi-channel visual information in color images. The methodology begins with converting red, green, blue (RGB) images into the luminance (L), red–green opponent color channel (M), blue–yellow opponent color channel (N) or LMN color space. Subsequently, the LoG filter is separately applied to the L, M, and N channels. The convoluted components are then fused to generate a contrast similarity map using the root-mean-square method, while the chromaticity similarity map is derived from the color channels. Finally, multi-channel LoG filtering, contrast, and chromaticity image features are connected. The standard deviation method is then used for sum pooling to create a full-reference IQA computational method. To validate the proposed method, distorted images from four widely used image databases were tested. The evaluation, based on four criteria, focused on the method’s prediction accuracy, computational complexity, and generalizability. The Pearson linear correlation coefficient (PLCC) values, recorded from the databases, ranged from 0.8822 (TID2013) to 0.9754 (LIVE). Similarly, the Spearman rank-order correlation coefficient (SROCC) values spanned from 0.8606 (TID2013) to 0.9798 (LIVE). In comparison to existing methods, the proposed IQA method exhibited superior visual correlation prediction accuracy, indicating its promising potential in the field of image quality assessment.

No-reference screen content image quality assessment based on multi-region features