- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[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 Lightweight Quality Assessment of Screen Content Images using Directional Derivative Filters
摘要： In this paper, we present a lightweight visual quality assessment of screen content image (SCI) based on the local luminance edge directions and gradient magnitude. First, we use directional derivative filters (DDFs) to extract the edge direction feature which is one of the main characteristics of SCIs. To obtain the perceptual quality measures, we separately extract the edge direction and gradient magnitude for the similarity computation between the reference and distorted SCIs. Finally, considering the computational complexity, we incorporate the DDF-based feature map with the gradient magnitude map together to generate a new visual quality metric. Experimental results have demonstrated that the proposed method is able to adapt better to the human visual system than 12 representative methods based on the screen image quality assessment database (SIQAD).
关键词： screen content images,directional derivatives,Image quality assessment (IQA),human visual system
更新于2025-09-23 15:22:29
-
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
-
PET Counting Response Variability Depending on Tumor Location, Activity, and Patient Obesity: A Feasibility Study of Solitary Pulmonary Nodule Using Monte Carlo
摘要： We aim to investigate the counting response variations of Positron Emission Tomography (PET) scanners with different detector configurations in the presence of Solitary Pulmonary Nodule (SPN). Using experimentally validated Monte Carlo simulations, the counting performance of four different scanner models with varying tumor activity, location, and patient obesity is represented using NECR (Noise Equivalent Count Rate). NECR is a well-established quantitative metric which has positive correlation with clinically perceived image quality. The combined effect of tumor displacement and increased activity shows a linear ascending trend for NECR with slope ranges of (12.5–18.2)*10-3 (kBq/cm3)-1 for three-ring (3R) scanners and (15.3–21.5)*10-3 (kBq/cm3)-1 for four-ring (4R). The trend for the combined effect of tumor displacement and patient obesity is exponential decay with 3R configurations weakly dependent on the patient obesity if the tumor is located at the center of the field-of-view with exponent’s range of (6.6-33.8)*10-2 cm-1. The dependency is stronger for 4R scanners (9.6–38.5)*10 -2 cm-1. The analysis indicates that quantitative PET data from the same SPN patient possibly examined in different time points (e.g. during staging or for the evaluation of treatment response) are affected by the different detector configurations and need to be normalized with patient weight, activity, and tumor location to reduce unwanted bias of the diagnosis. Our work provides also with a proof of concept for the ability of properly tuned simulations to provide additional insights into the counting response variability especially in tumor types where often borderline decisions have to be made regarding their characterization.
关键词： image quality assessment,nuclear imaging,lung
更新于2025-09-23 15:22:29
-
Local Feature Descriptor and Derivative Filters for Blind Image Quality Assessment
摘要： In this letter, a novel Blind Image Quality Assessment (BIQA) technique is introduced to provide an automatic and reproducible evaluation of distorted images. In the approach, the information carried by image derivatives of different orders is captured by local features and used for the image quality prediction. Since a typical local feature descriptor is designed to ensure a robust image patch representation, in this letter, a novel descriptor which additionally highlights local differences enhanced by the filtering is proposed. Furthermore, a set of derivative kernels is introduced. Finally, the support vector regression (SVR) technique is used to map statistics of described features into subjective scores, providing an objective quality score for an image. Extensive experimental validation on popular IQA image datasets reveals that the proposed method outperforms the state-of-the-art hand-crafted and deep learning BIQA measures.
关键词： Local features,Feature descriptor,Support vector regression,Derivative filters,Blind image quality assessment
更新于2025-09-23 15:22:29
-
Rectangular-Normalized Superpixel Entropy Index for Image Quality Assessment
摘要： Image quality assessment (IQA) is a fundamental problem in image processing that aims to measure the objective quality of a distorted image. Traditional full-reference (FR) IQA methods use fixed-size sliding windows to obtain structure information but ignore the variable spatial configuration information. In order to better measure the multi-scale objects, we propose a novel IQA method, named RSEI, based on the perspective of the variable receptive field and information entropy. First, we find that consistence relationship exists between the information fidelity and human visual of individuals. Thus, we reproduce the human visual system (HVS) to semantically divide the image into multiple patches via rectangular-normalized superpixel segmentation. Then the weights of each image patches are adaptively calculated via their information volume. We verify the effectiveness of RSEI by applying it to data from the TID2008 database and denoise algorithms. Experiments show that RSEI outperforms some state-of-the-art IQA algorithms, including visual information fidelity (VIF) and weighted average deep image quality measure (WaDIQaM).
关键词： image quality assessment,superpixel segmentation,mutual information
更新于2025-09-23 15:22:29
-
A comparative study of superimposition techniques for enhancing the projector resolution: Simulations and experiments
摘要： Among the techniques developed to enhance the resolution of a projector beyond its native resolution, a number of techniques use sequential superimposition of low resolution images with sub-pixel shift to produce a resulting high-resolution image on the wall. This work investigates different low-resolution subframe image generation techniques used for this purpose. Along with that, two new subframe generation techniques have been developed with the aim to prioritize darker and/or bright pixels in an image. We have also extended a Single-subframe iterative technique to Two-subframe iterative technique to evaluate its full potential. Detailed simulations, visual image quality analysis, image quality metric assessment and measurement results of the existing and the newly developed methods have been carried out. A comparative study of the techniques suggests that iterative sub-frame generation techniques give the best overall image quality, but their high computational cost could make them less practical.
关键词： Resolution enhancement,Image quality metric,Superimposition,Digital micro-mirror device (DMD)
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
-
[ACM Press the 3rd International Conference - Seoul, Republic of Korea (2018.08.22-2018.08.24)] Proceedings of the 3rd International Conference on Biomedical Signal and Image Processing - ICBIP '18 - Noise and Resolution Performance Evaluation for Statistical and Non-Statistical Iterative CBCT Reconstruction Methods
摘要： Non-statistical iterative and statistical iterative reconstruction (SIR) methods establish different models for Cone-beam computed tomography (CBCT) image reconstruction, which possibly produce different performance outcomes in reconstructed images. This paper presents a method to evaluate the noise and resolution properties of statistical and non-statistical iterative conditions. An algorithms EGSnrc/BEAMnrc Monte Carlo (MC) system was built for generating CBCT projections of a digital water phantom. SIR based OSC-TV (ordered subsets convex via total variation minimization) algorithm was selected to compare with non-statistical ASD-POCS (adaptive steepest descent-projection onto convex sets) algorithm and conventional FDK algorithm. The results demonstrate that ASD-POCS algorithm achieved a higher modulation transfer function than SIR based OSC-TV algorithm at the price of a higher image noise, while OSC-TV algorithm yielded best noise equivalent quanta performance among the three algorithms. The results of our study could guide a better evaluation and optimization of reconstruction algorithms for CBCT imaging.
关键词： Noise equivalent quanta,Image quality assessment,Noise power spectrum,Modulation transfer function,Computed tomography
更新于2025-09-23 15:22:29
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Visual-Quality-Driven Learning for Underwater Vision Enhancement
摘要： The image processing community has witnessed remarkable advances in enhancing and restoring images. Nevertheless, restoring the visual quality of underwater images remains a great challenge. End-to-end frameworks might fail to enhance the visual quality of underwater images since in several scenarios it is not feasible to provide the ground truth of the scene radiance. In this work, we propose a CNN-based approach that does not require ground truth data since it uses a set of image quality metrics to guide the restoration learning process. The experiments showed that our method improved the visual quality of underwater images preserving their edges and also performed well considering the UCIQE metric.
关键词： Image Restoration,Underwater Vision,Deep Learning,Image Quality Metrics
更新于2025-09-23 15:21:21
-
256-Slice Coronary Computed Tomography Angiography Using Low Tube Voltage of 100 KV
摘要： Purpose: To evaluate the image quality and radiation dose of 100 kV with 1000 mAs retrospective electrocardiography (ECG)-gated CCTA protocol, compared to the standard protocol of 120 kV with 800 mAs retrospective ECG-gated CCTA. Material and Methods: We divided 70 patients into two, a reduced dose group with 35 patients (18 M, 17 F; Mean age 56.94 ± 11.51 years) were examined by 100-kV with 1000 mAs retrospective ECG-gated CCTA, and another as a standard group of 35 patients (21, 14 F; Mean age 54.03 ± 9.81 years) were examined by 120-kV with 800 mAs retrospective ECG-gated CCTA. The two blinded radiologists analyzed the image quality of the coronary arteries independently and they accessed subjective and objective image quality. The radiation dose was also measured as effective radiation dose [ED] and was calculated using CT dose volume index [CTDIvol.], dose-length product [DLP] and conversion coefficient for chest (conversion factor k=0.014 mSv mGy-1cm-1). Results: Although the objective image quality of the 100-kV with 1000 mAs was significantly better than the 120-kV with 800 mAs (mean SNR, 36.65 ± 2.95 vs. 33.47 ± 3.86, P<0.0001; mean CNR, 34.27 ± 2.92 vs. 30.62 ± 3.90, P<0.0001). There was no significant variation in the subjective image quality between two groups (mean image score, 4.54 ± 0.37 vs. 4.56 ± 0.25 for radiologist 1, P = 0.781; 4.52 ± 0.25 vs. 4.56 ± 0.25 for radiologist 2, P=0.486). The radiation dose was found to be reduced by 28% with the 100-kV/1000 mAs protocol than with the 120-kV/800 mAs retrospective ECG-gated CCTA (7.87 ± 0.59 vs. 10.95 ± 1.67 mSv, P<0.0001). Conclusion: The protocol of low tube voltage CCTA using 100 kV/1000 mAs retrospective ECG-gated shows significant reduction of the radiation dose without disturbing the subjective image quality of CCTA.
关键词： Coronary CT angiography,Image quality,Radiation dose
更新于2025-09-23 15:21:21