Abstract: Image processing system (I1, . . . In), including a main neural network (2) and, upstream thereof, a preprocessing module (3) including several neural networks (R1, . . . , Rn) working in parallel to process several starting images of the same object and configured to generate, by fusing the outputs of these networks, a representation (D) of the object improving the performance of the main neural network, the learning of the neural networks of the preprocessing module (3) being performed at least partly simultaneously with the one of the main neural network (2).

Abstract: System for processing images including a main neural network, preferably convolution-based (CNN), and at least one preprocessing neural network, preferably convolution-based, upstream of the main neural network, for carrying out before processing by the main neural network at least one parametric transformation f, differentiable with respect to its parameters, this transformation being applied to at least part of the pixels of the image and being of the form p?=f(V(p),?) where p is a processed pixel of the original image or of a decomposition of this image, p? the pixel of the transformed image or of its decomposition, V(p) is a neighborhood of the pixel p, and ? a vector of parameters, the preprocessing neural network having at least part of its learning which is performed simultaneously with that of the main neural network.

Abstract: A method for enhancing local contrast of an image. The method comprises receiving a component of an image, computing a wavelets decomposition of the received component into wavelet coefficients, determining at least three subsets of wavelets coefficients based on a first threshold, a second threshold and computed wavelet coefficients, modifying the determined at least three subsets by applying at least a sharpening transformation on wavelet coefficients of at least one subset in said at least three subsets, recombining the at least three subsets into final wavelet coefficients, and reconstructing a new component based on the final wavelet coefficients.

Abstract: The present invention relates to a method for determining noise levels in a subband of an image. The method comprises receiving the subband of the image, defining block regions in the at least two space domains of the subband, for each defined block region, identifying first wavelet coefficients associated with coordinate values in the at least two space domains in the defined block region, computing a correlation matrix between identified wavelet coefficients to determine the correlation between first wavelet coefficients according to the at least one color domain, computing second wavelet coefficients, the computation of second wavelet coefficients being based on the correlation matrix and the first wavelet coefficients, computing at least one noise level, the noise level computation being based on at least one second wavelet coefficient and providing the at least one noise level.

Abstract: A method for enhancing local contrast of an image. The method comprises receiving a component of an image, computing a wavelets decomposition of the received component into wavelet coefficients, determining at least three subsets of wavelets coefficients based on a first threshold, a second threshold and computed wavelet coefficients, modifying the determined at least three subsets by applying at least a sharpening transformation on wavelet coefficients of at least one subset in said at least three subsets, recombining the at least three subsets into final wavelet coefficients, and reconstructing a new component based on the final wavelet coefficients.

Abstract: A method for determining noise levels in a subband of an image. The method comprises receiving the subband of the image, defining block regions in at least two space domains of the subband, for each defined block region, identifying first wavelet coefficients associated with coordinate values in the at least two space domains in the defined block region, computing a correlation matrix between identified wavelet coefficients to determine the correlation between first wavelet coefficients according to the at least one color domain, computing second wavelet coefficients, the computation of second wavelet coefficients being based on the correlation matrix and the first wavelet coefficients, computing at least one noise level, the noise level computation being based on at least one second wavelet coefficient and providing the at least one noise level.

Abstract: A method for determining noise levels in a subband of an image. The method comprises receiving the subband of the image, defining block regions in at least two space domains of the subband, for each defined block region, identifying first wavelet coefficients associated with coordinate values in the at least two space domains in the defined block region, computing a correlation matrix between identified wavelet coefficients to determine the correlation between first wavelet coefficients according to the at least one color domain, computing second wavelet coefficients, the computation of second wavelet coefficients being based on the correlation matrix and the first wavelet coefficients, computing at least one noise level, the noise level computation being based on at least one second wavelet coefficient and providing the at least one noise level.