Search results for "ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION"
showing 10 items of 982 documents
An interactive evolutionary approach for content based image retrieval
2009
Content Based Image Retrieval (CBIR) systems aim to provide a means to find pictures in large repositories without using any other information except its contents usually as low-level descriptors. Since these descriptors do not exactly match the high level semantics of the image, assessing perceptual similarity between two pictures using only their feature vectors is not a trivial task. In fact, the ability of a system to induce high level semantic concepts from the feature vector of an image is one of the aspects which most influences its performance. This paper describes a CBIR algorithm which combines relevance feedback, evolutionary computation concepts and ad-hoc strategies in an attem…
Machine Learning-Based View Synthesis in Fourier Lightfield Microscopy
2022
Current interest in Fourier lightfield microscopy is increasing, due to its ability to acquire 3D images of thick dynamic samples. This technique is based on simultaneously capturing, in a single shot, and with a monocular setup, a number of orthographic perspective views of 3D microscopic samples. An essential feature of Fourier lightfield microscopy is that the number of acquired views is low, due to the trade-off relationship existing between the number of views and their corresponding lateral resolution. Therefore, it is important to have a tool for the generation of a high number of synthesized view images, without compromising their lateral resolution. In this context we investigate h…
Combining fuzzy C-mean and normalized convolution for cloud detection in IR images
2009
An important task for the cloud monitoring in several frameworks is providing maps of the cloud coverage. In this paper we present a method to detect cloudy pixels for images taken from ground by an infra-red camera. The method is a three-steps algorithm mainly based on a Fuzzy C-Mean clustering, that works on a feature space derived from the original image and the output of the reconstructed image obtained via normalized convolution. Experiments, run on several infra-red images acquired under different conditions, show that the cloud maps returned are satisfactory. © 2009 Springer Berlin Heidelberg.
Computational imaging with a balanced detector
2016
Single-pixel cameras allow to obtain images in a wide range of challenging scenarios, including broad regions of the electromagnetic spectrum and through scattering media. However, there still exist several drawbacks that single-pixel architectures must address, such as acquisition speed and imaging in the presence of ambient light. In this work we introduce balanced detection in combination with simultaneous complementary illumination in a single-pixel camera. This approach enables to acquire information even when the power of the parasite signal is higher than the signal itself. Furthermore, this novel detection scheme increases both the frame rate and the signal-to-noise ratio of the sys…
Generalized Dimension Distortion under Mappings of Sub-Exponentially Integrable Distortion
2010
We prove a dimension distortion estimate for mappings of sub-exponentially integrable distortion in Euclidean spaces, which is essentially sharp in the plane.
Microscopic and macroscopic 3D imaging and display by integral imaging
2011
Integral imaging is a rising 3D imaging technique that can be considered the incoherent version of holography. In integral imaging the multiperspective information of 3D scenes is stored in a 2D picture. Such picture, composed by a set of elemental images, is obtained through a 2D array of microlenses. The elemental-images set can be used for many purposes. One is the display of 3D color scenes to audiences or much more than one person. Other is the 3D display, with full parallax, in personal monitors, like the screen of a smartphone, a tablet, or the monitor used by a surgeon in an endoscopic operation. Other important types of applications are connected with the topographic reconstruction…
Extended View Angle Integral Imaging 3D Display using Smart Pseudoscopic-to-orthoscopic Conversion with Head Tracking
2016
We overview a head tracking integral imaging display using the smart pseudoscopic-to-orthoscopic conversion method. The crosstalk for a large viewing angle in integral imaging is eliminated by generating a new set of elemental images.
Head Tracking Three-Dimensional Integral Imaging Display Using Smart Pseudoscopic-to-Orthoscopic Conversion
2016
A novel head tracking three-dimensional (3D) integral imaging display is presented. By means of proper application of the smart pseudoscopic-to-orthoscopic conversion (SPOC) method, our display allows an extended viewing angle accommodated to the viewer's position which is obtained by a head/eye tracking system. Using the SPOC, new sets of elemental images are calculated and adapted to any specific viewing position. Additionally, the crosstalk which is typical in conventional integral imaging, is eliminated for a large viewing angle. By performing the rotation transformation in the simulated display, viewing a 3D scene with head rotation can be realized for robust display. Experimental resu…
Towards 3D Television Through Fusion of Kinect and Integral-Imaging Concepts
2015
We report a new procedure for the capture and processing of light proceeding from 3D scenes of some cubic meters in size. Specifically we demonstrate that with the information provided by a kinect device it is possible to generate an array of microimages ready for their projection onto an integral-imaging monitor. We illustrate our proposal with some imaging experiment in which the final result are 3D images displayed with full parallax.
Automatic target recognition using 3D passive sensing and imaging with independent component analysis
2009
We present an overview of a method using Independent Component Analysis (ICA) and 3D Integral Imaging (II) technique to recognize 3D objects at different orientations. This method has been successfully applied to the recognition and classification of 3D scenes.