Abstract
We propose a novel image-dehazing technique based on the minimization of two energy functionals and a fusion scheme to combine the output of both optimizations. The proposed fusion-based variational image-dehazing (FVID) method is a spatially varying image enhancement process that first minimizes a previously proposed variational formulation that maximizes contrast and saturation on the hazy input. The iterates produced by this minimization are kept, and a second energy that shrinks faster intensity values of well-contrasted regions is minimized, allowing to generate a set of difference-of-saturation (DiffSat) maps by observing the shrinking rate. The iterates produced in the first minimization are then fused with these DiffSat maps to produce a haze-free version of the degraded input. The FVID method does not rely on a physical model from which to estimate a depth map, nor it needs a training stage on a database of human-labeled examples. Experimental results on a wide set of hazy images demonstrate that FVID better preserves the image structure on nearby regions that are less affected by fog, and it is successfully compared with other current methods in the task of removing haze degradation from faraway regions.

Abstract
Exploring the seas and the oceans is essential for industrial and environmental applications. Given the fact that the seas cover 72% of the surface of the Earth and are home to 90% of all life found on it, underwater imaging has become an active research area in recent years. Due to the high absorption of electromagnetic waves by water, sonar is currently the exemplary choice used in underwater imaging. Yet, underwater images acquired with sonars suffer from various degradations, since the sound signal is affected by the environment and the sonar parameters and geometry. This work proposes an enhancement method that aims at getting close to natural underwater images. The enhanced images can be used in further applications related to seabed mapping and underwater computer vision. The enhancement aims at reducing the echo-decay and some effects of the receiver gain.

Abstract

Abstract

Abstract
Given a retinal image, can we automatically determine whether it is of high quality (suitable for medical diagnosis)? Can we also explain our decision, pinpointing the region or regions that led to our decision? Images from human retinas are vital for the diagnosis of multiple health issues, like hypertension, diabetes, and Alzheimer's; low quality images may force the patient to come back again for a second scanning, wasting time and possibly delaying treatment. However, existing retinal image quality assessment methods are either black boxes without explanations of the results or depend heavily on feature engineering or on complex and error-prone anatomical structures' segmentation. Therefore, we propose EyeQual, that solves exactly this problem. EyeQual is novel, fast for inference, accurate and explainable, pinpointing low-quality regions on the image. We evaluated EyeQual on two real datasets where it achieved 100% accuracy taking just 36 milliseconds for each image.

Abstract
A recurrent problem in the industrial sector is the quality control and surface inspection of reflecting pieces with non-planar surfaces. This is an extended and non-solved problem because it is related not only to the material itself but also to the coating. This problem appears in a wide spectrum of industrial sectors such as automation, aeronautics or orthopaedics. In recent years, a new imaging technology called deflectometry has been introduced in the field of surface inspection for industrial applications. This technology features a high resolution camera and a dedicated illumination system based on displaying fringe patterns in a monitor-allowing the detection of irregularities in surfaces. However, the introduction of this technology into automated quality control systems remains a challenging task, due to the wide range of defects and shapes that can appear. It becomes thus necessary to characterize different types of errors and their associated detection setups. In this paper we propose a novel methodology to define and analyse the best setup for each pattern. We also explore an efficient technique to maximize the number of different pieces inspected without modifying the setup of the acquisition system. Experimental results show that the presented methodology defines an inspection method that can be installed in an automatic quality control device for non-planar surfaces analysis of manufactured products.