SEMANTIC SEGMENTATION OF BRAZILIAN SAVANNA VEGETATION USING HIGH SPATIAL RESOLUTION SATELLITE DATA AND U-NET [PDF]
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2020 Large-scale mapping of the Brazilian Savanna (Cerrado) vegetation using remote sensing images is still a challenge due to the high spatial variability and spectral similarity of the different characteristic vegetation types (physiognomies). In this paper,
A. K. Neves +7 more
doaj +1 more source
Alignment of color discrimination in humans and image segmentation networks
Frontiers in PsychologyThe experiments allowed by current machine learning models imply a revival of the debate on the causes of specific trends of human visual psychophysics.
Pablo Hernández-Cámara +3 more
doaj +1 more source
Physics-aware nonparametric regression models for Earth data analysis
Environmental Research Letters, 2022 Process understanding and modeling is at the core of scientific reasoning. Principled parametric and mechanistic modeling dominated science and engineering until the recent emergence of machine learning (ML).
Jordi Cortés-Andrés +9 more
doaj +1 more source
Riemannian Geometric Statistics in Medical Image Analysis
, 2019 International audienceOver the past 15 years, there has been a growing need in the medical image computing community for principled methods to process nonlinear geometric data.
Sommer, Stephan +2 more
core +1 more source
Learning midlevel image features for natural scene and texture classification [PDF]
, 2007 This paper deals with coding of natural scenes in order to extract semantic information. We present a new scheme to project natural scenes onto a basis in which each dimension encodes statistically independent information.
O'Connor, Noel E. +4 more
core +1 more source
Observer efficiency in free-localization tasks with correlated noise
Frontiers in Psychology, 2014 The efficiency of visual tasks involving localization has traditionally been evaluated using forced choice experiments that capitalize on independence across locations to simplify the performance of the ideal observer.
Craig eAbbey, Miguel P. Eckstein
doaj +1 more source
Image Authentication By Statistical Analysis
, 2013 This paper investigates the discrimination between Photographic Images (PIM) and Computer Generated (CG) images. The proposed method exploits traces of Color Filter Array (CFA) interpolation, present in PIM images, together with the use of hypothesis testing theory.
Qiao, Tong +2 more
openaire +5 more sources
Discriminating natural image statistics from neuronal population codes. [PDF]
PLoS ONE, 2010 The power law provides an efficient description of amplitude spectra of natural scenes. Psychophysical studies have shown that the forms of the amplitude spectra are clearly related to human visual performance, indicating that the statistical parameters ...
Satohiro Tajima, Masato Okada
doaj +1 more source
Blind image quality assessment using joint statistics of gradient magnitude and laplacian features
, 2014 Blind image quality assessment (BIQA) aims to evaluate the perceptual quality of a distorted image without information regarding its reference image.
Xue, WF +4 more
core +1 more source
A Cerebral Basis for Visual Discomfort and Visual Stress
VisionVisual discomfort or visual stress is an uncomfortable subjective experience that occurs in response to specific visual stimuli. It affects a large proportion of the population to various degrees, disproportionately impacting those with heightened ...
Paul B. Hibbard +31 more
doaj +1 more source