Adrian Galdran

Automatic Red-Channel underwater image restoration

New methodology to estimate the depth map in an underwater degraded scene.Novel method to handle the presence of artificial illumination in underwater images.Performance evaluation on images with different illumination and color predominancies. Underwater images typically exhibit color distortion and low contrast as a result of the exponential decay that light suffers as it travels. Moreover, colors associated to different wavelengths have different attenuation rates, being the red wavelength the one that attenuates the fastest. To restore underwater images, we propose a Red Channel method, where colors associated to short wavelengths are recovered, as expected for underwater images, leading to a recovery of the lost contrast. The Red Channel method can be interpreted as a variant of the Dark Channel method used for images degraded by the atmosphere when exposed to haze. Experimental results show that our technique handles gracefully artificially illuminated areas, and achieves a natural color correction and superior or equivalent visibility improvement when compared to other state-of-the-art methods.

Enhanced Variational Image Dehazing

Images obtained under adverse weather conditions, such as haze or fog, typically exhibit low contrast and faded colors, which may severely limit the visibility within the scene. Unveiling the image structure under the haze layer and recovering vivid colors out of a single image remains a challenging task, since the degradation is depth-dependent and conventional methods are unable to overcome this problem. In this work, we extend a well-known perception-inspired variational framework for single image dehazing. Two main improvements are proposed. First, we replace the value used by the framework for the gray-world hypothesis by an estimation of the mean of the clean image. Second, we add a set of new terms to the energy functional for maximizing the interchannel contrast. Experimental results show that the proposed enhanced variational image dehazing (EVID) method outperforms other state-of-the-art methods both qualitatively and quantitatively. In particular, when the illuminant is uneven, our EVID method ...

Fusion-Based Variational Image Dehazing

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.

End-to-End Adversarial Retinal Image Synthesis

In medical image analysis applications, the availability of the large amounts of annotated data is becoming increasingly critical. However, annotated medical data is often scarce and costly to obtain. In this paper, we address the problem of synthesizing retinal color images by applying recent techniques based on adversarial learning. In this setting, a generative model is trained to maximize a loss function provided by a second model attempting to classify its output into real or synthetic. In particular, we propose to implement an adversarial autoencoder for the task of retinal vessel network synthesis. We use the generated vessel trees as an intermediate stage for the generation of color retinal images, which is accomplished with a generative adversarial network. Both models require the optimization of almost everywhere differentiable loss functions, which allows us to train them jointly. The resulting model offers an end-to-end retinal image synthesis system capable of generating as many retinal images as the user requires, with their corresponding vessel networks, by sampling from a simple probability distribution that we impose to the associated latent space. We show that the learned latent space contains a well-defined semantic structure, implying that we can perform calculations in the space of retinal images, e.g., smoothly interpolating new data points between two retinal images. Visual and quantitative results demonstrate that the synthesized images are substantially different from those in the training set, while being also anatomically consistent and displaying a reasonable visual quality.

Automatic 3D model-based method for liver segmentation in MRI based on active contours and total variation minimization

Abstract Liver cancer is one of the leading causes of cancer-related mortality worldwide. Non-invasive techniques of medical imaging such as Computerized Tomography (CT) and Magnetic Resonance Imaging (MRI) are often used by radiologists for diagnosis and surgery planning. With the aim of assuring the most reliable intervention planning to surgeons, new accurate methods and tools must be provided to locate and segment the regions of interest. Automated liver segmentation is a challenging problem for which promising results have been achieved mostly for CT. However, MRI is required by radiologists, since it offers better information for diagnosis purposes. MRI liver segmentation represents a challenge due to the presence of characteristic artifacts, such as partial volumes, noise, low contrast and poorly defined edges of the liver in relation to adjacent organs. In this paper, we present a method for MRI automatic 3D liver segmentation by means of an active contour model extended to 3D and minimized by total variation dual approach that has also been extended to 3D. A new approach to enhance the contrast in the input MRI image is proposed and it allows more accurate segmentation. The proposed methodology allows replacing the input image by a probability map obtained by means of a previously generated statistical model of the liver. An Accuracy of 98.89 and Dice Similarity Coefficient of 90.19 are in line with other state-of-the-art methodologies.

A Variational Framework for Single Image Dehazing

Images captured under adverse weather conditions, such as haze or fog, typically exhibit low contrast and faded colors, which may severely limit the visibility within the scene. Unveiling the image structure under the haze layer and recovering vivid colors out of a single image remains a challenging task, since the degradation is depth-dependent and conventional methods are unable to handle this problem.

3D active surfaces for liver segmentation in multisequence MRI images

Biopsies for diagnosis can sometimes be replaced by non-invasive techniques such as CT and MRI. Surgeons require accurate and efficient methods that allow proper segmentation of the organs in order to ensure the most reliable intervention planning. Automated liver segmentation is a difficult and open problem where CT has been more widely explored than MRI. MRI liver segmentation represents a challenge due to the presence of characteristic artifacts, such as partial volumes, noise and low contrast. In this paper, we present a novel method for multichannel MRI automatic liver segmentation. The proposed method consists of the minimization of a 3D active surface by means of the dual approach to the variational formulation of the underlying problem. This active surface evolves over a probability map that is based on a new compact descriptor comprising spatial and multisequence information which is further modeled by means of a liver statistical model. This proposed 3D active surface approach naturally integrates volumetric regularization in the statistical model. The advantages of the compact visual descriptor together with the proposed approach result in a fast and accurate 3D segmentation method. The method was tested on 18 healthy liver studies and results were compared to a gold standard made by expert radiologists. Comparisons with other state-of-the-art approaches are provided by means of nine well established quality metrics. The obtained results improve these methodologies, achieving a Dice Similarity Coefficient of 98.59.

Illumination Correction by Dehazing for Retinal Vessel Segmentation

Assessment of retinal vessels is fundamental for the diagnosis of many disorders such as heart diseases, diabetes and hypertension. The imaging of retina using advanced fundus camera has become a standard in computer-assisted diagnosis of opthalmic disorders. Modern cameras produce high quality color digital images, but during the acquisition process the light reflected by the retinal surface generates a luminosity and contrast variation. Irregular illumination can introduce severe distortions in the resulting images, decreasing the visibility of anatomical structures and consequently demoting the performance of the automated segmentation of these structures. In this paper, a novel approach for illumination correction of color fundus images is proposed and applied as preprocessing step for retinal vessel segmentation. Our method builds on the connection between two different phenomena, shadows and haze, and works by removing the haze from the image in the inverted intensity domain. This is shown to be equivalent to correct the nonuniform illumination in the original intensity domain. We tested the proposed method as preprocessing stage of two vessel segmentation methods, one unsupervised based on mathematical morphology, and one supervised based on deep learning Convolutional Neural Networks (CNN). Experiments were performed on the publicly available retinal image database DRIVE. Statistically significantly better vessel segmentation performance was achieved in both test cases when illumination correction was applied.

Image processing applications through a variational perceptually-based color correction related to Retinex

Comunicacio presentada al IS&T International Symposium on Electronic Imaging, celebrat del 14 al 18 de febrer de 2016 a San Francisco (CA, USA) i organitzat per la Society for Imaging Science and Technology.

Pectoral Muscle Segmentation in Mammograms Based on Cartoon-Texture Decomposition

Pectoral muscle segmentation on medio-lateral oblique views of mammograms represents an important preprocessing step in many mammographic image analysis tasks. Although its location can be perceptually obvious for a human observer, the variability in shape, size, and intensities of the pectoral muscle boundary turns its automatic segmentation into a challenging problem. In this work we propose to decompose the input mammogram into its textural and structural components at different scales prior to dynamically thresholding it into several levels. The resulting segmentations are refined with an active contour model and merged together by means of a simple voting scheme to remove possible outliers. Our method performs well compared to several other state-of-the-art techniques. An average DICE similarity coefficient of \(0.91\) and mean Hausdorff distance of \(3.66 \pm 3.23\) mm. validate our approach.