- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[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
-
[Advances in Intelligent Systems and Computing] Image Processing and Communications Challenges 10 Volume 892 (10th International Conference, IP&C’2018 Bydgoszcz, Poland, November 2018, Proceedings) || Reliability of Local Ground Truth Data for Image Quality Metric Assessment
摘要： Image Quality Metrics (IQMs) automatically detect di?erences between images. For example, they can be used to ?nd aliasing artifact in the computer generated images. An obvious application is to test if the costly anti-aliasing techniques must be applied so that the aliasing is not visible to humans. The performance of IQMs must be tested based on the ground truth data, which is a set of maps that indicate the location of artifacts in the image. These maps are manually created by people during so called marking experiments. In this work, we evaluate two di?erent techniques of marking. In the side-by-side experiment, people mark di?erences between two images displayed side-by-side on the screen. In the ?ickering experiment, images are displayed at the same location but are exchanged over time. We assess the performance of each technique and use the generated reference maps to evaluate the performance of the selected IQMs. The results reveal the better accuracy of the ?ickering technique.
关键词： Image quality metrics,Aliasing,Ground truth data,Perceptual experiments
更新于2025-09-23 15:21:01
-
[IEEE 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC) - Atlanta, GA (2017.10.21-2017.10.28)] 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC) - SPECT Reconstruction and Analysis for the Inspection of Spent Nuclear Fuel
摘要： A gamma-emission-tomography (GET) system for the inspection of spent nuclear fuel (SNF) has been developed and tested on multiple fuel types. This tool can be used for verification of the integrity of an assembly and consistency with fissile-material content. Parallel-beam line integrals are measured by a discrete array of CdZnTe detectors that view the fuel through a 1.5mm wide by 100mm thick tungsten collimator. Detectors and electronics are on a rotating platform within a watertight stainless steel torus. During operation, the system is underwater and fuel is lowered through the center of the torus and held stationary as data are collected. Tomographic data collection requires a time on the order of minutes. In field experiments, data with count rates in the range of 50kcps to >500kcps per pixel have been recorded. In the reconstructed images, missing or replaced pins in all assembly types can be visually discriminated in the lattice of fuel pins. Automated detection of missing/replaced pins is the metric used for determination of optimal processing steps. Effectiveness of reconstruction and data-processing tools is measured by a tools ability to improve performance on the pin-discrimination task. This paper describes the data preprocessing, image reconstruction, image analysis, and performance evaluation of this system.
关键词： gamma-ray emission tomography,image quality metrics,safeguards,attenuation correction,image reconstruction,spent nuclear fuel
更新于2025-09-09 09:28:46
-
Image Enhancement of Wireless Capsule Endoscopy Frames Using Image Fusion Technique
摘要： Volume restriction, low battery capacity and low focal length camera in Wireless Capsule Endoscopy (WCE) result in images being of lower contrast, darkness, un-even brightness and image degradations. In this paper, a Laplacian pyramid based Image fusion of Contrast Limited Adaptive Histogram Equalization (CLAHE) and Multi-Scale Retinex with Colour Restoration (MSRCR) to integrate information of both techniques have been proposed. The proposed technique combines the information from CLAHE and MSRCR, reduces uncertainties, redundancy and maximizes the information. Experimental evaluation reveals that the proposed method outperforms existing methods in terms of Peak Signal to Noise Ratio and Structural Similarity Index Measure.
关键词： Image enhancement,Image fusion,Image quality metrics,Wireless capsule endoscopy,Retinex,Laplacian pyramid
更新于2025-09-04 15:30:14
-
[ACM Press the 2nd International Conference - Sydney, NSW, Australia (2018.10.06-2018.10.08)] Proceedings of the 2nd International Conference on Graphics and Signal Processing - ICGSP'18 - A Comparative Analysis of Clustering Algorithms for Ultrasound Image Despeckling Applications
摘要： This paper proposes a novel framework for speckle noise suppression and edge preservation using clustering algorithms in ultrasound images. The algorithms considered are K-means clustering, fuzzy C-means clustering, possibilistic C-means, fuzzy possibilistic C-means, and possibilistic fuzzy C-means clustering. This work presents an exhaustive comparative analysis of the above clustering algorithms to consider their suitability for despeckling and identifies the best clustering algorithm. Two types of dataset are considered: medical ultrasound images of the thyroid, and synthetically modelled ultrasound images. The framework consists of several distinct phases - first the edges of the image are identified using the Canny edge operator, and then a clustering algorithm applied on high frequency coefficients extracted using wavelet transform. Finally, the preserved edges are added back to speckle suppressed image. Thus, the proposed clustering method effectively accomplishes both speckle suppression and edge preservation. This paper also presents a quantitative evaluation of results to demonstrate the effectiveness of the clustering approach.
关键词： speckle noise,Image quality metrics,Wavelet transform,Ultrasound image analysis,Canny edge detector,Clustering algorithms
更新于2025-09-04 15:30:14