Search results for "convolution"
showing 10 items of 334 documents
Visual spike-based convolution processing with a Cellular Automata architecture
2010
this paper presents a first approach for implementations which fuse the Address-Event-Representation (AER) processing with the Cellular Automata using FPGA and AER-tools. This new strategy applies spike-based convolution filters inspired by Cellular Automata for AER vision processing. Spike-based systems are neuro-inspired circuits implementations traditionally used for sensory systems or sensor signal processing. AER is a neuromorphic communication protocol for transferring asynchronous events between VLSI spike-based chips. These neuro-inspired implementations allow developing complex, multilayer, multichip neuromorphic systems and have been used to design sensor chips, such as retinas an…
Classification of diabetes-related retinal diseases using a deep learning approach in optical coherence tomography
2019
Background and objectives: Spectral Domain Optical Coherence Tomography (SD-OCT) is a volumetric imaging technique that allows measuring patterns between layers such as small amounts of fluid. Since 2012, automatic medical image analysis performance has steadily increased through the use of deep learning models that automatically learn relevant features for specific tasks, instead of designing visual features manually. Nevertheless, providing insights and interpretation of the predictions made by the model is still a challenge. This paper describes a deep learning model able to detect medically interpretable information in relevant images from a volume to classify diabetes-related retinal d…
Fast nonstationary preconditioned iterative methods for ill-posed problems, with application to image deblurring
2013
We introduce a new iterative scheme for solving linear ill-posed problems, similar to nonstationary iterated Tikhonov regularization, but with an approximation of the underlying operator to be used for the Tikhonov equations. For image deblurring problems, such an approximation can be a discrete deconvolution that operates entirely in the Fourier domain. We provide a theoretical analysis of the new scheme, using regularization parameters that are chosen by a certain adaptive strategy. The numerical performance of this method turns out to be superior to state-of-the-art iterative methods, including the conjugate gradient iteration for the normal equation, with and without additional precondi…
Modified Gaussian models applied to the description and deconvolution of peaks in chiral liquid chromatography.
2020
Abstract The description of the profiles of chromatographic peaks has been studied extensively, with a large number of proposed mathematical functions. Among them, the accuracy achieved with modified Gaussian models that describe the deviation of an ideal Gaussian peak as a change in the peak variance or standard deviation over time, has been highlighted. These models are, in fact, a family of functions of different complexity with great flexibility to adjust chromatographic peaks over a wide range of asymmetries and shapes. However, an uncontrolled behaviour of the signal may occur outside the region being fitted, forcing the use of different strategies to overcome this problem. In this wo…
Writer identification for historical handwritten documents using a single feature extraction method
2020
International audience; With the growth of artificial intelligence techniques the problem of writer identification from historical documents has gained increased interest. It consists on knowing the identity of writers of these documents. This paper introduces our baseline system for writer identification, tested on a large dataset of latin historical manuscripts used in the ICDAR 2019 competition. The proposed system yielded the best results using Scale Invariant Feature Transform (SIFT) as a single feature extraction method, without any preprocessing stage. The system was compared against four teams who participated in the competition with different feature extraction methods: SRS-LBP, SI…
<title>Deconvolution of the mercury 253.7 nm spectral line shape for the use in absorption spectroscopy</title>
2008
In this work we present measurement and results of the deconvolution of the Hg 253.7 nm spectral line shapes, emitted from the mercury isotope high-frequency electrodeless discharge lamps, made at the Institute of Atomic Physics and Spectroscopy for the use in Zeeman Atomic Absorption Spectrometry. The emission line profiles of 254 nm Hg resonance line have been measured by means of a Zeeman scanning spectrometer at the mercury cold spot temperature value at 20 C. Then the deconvolution procedure or solving of this ill-posed inverse problem by means of the Tikhonov's regularization method [1] was performed to obtain the real spectral line shape.© (2008) COPYRIGHT SPIE--The International Soc…
Design of a Real-time face detection parallel architecture using High-Level Synthesis
2008
Abstract We describe a High-Level Synthesis implementation of a parallel architecture for face detection. The chosen face detection method is the well-known Convolutional Face Finder (CFF) algorithm, which consists of a pipeline of convolution operations. We rely on dataflow modelling of the algorithm and we use a high-level synthesis tool in order to specify the local dataflows of our Processing Element (PE), by describing in C language inter-PE communication, fine scheduling of the successive convolutions, and memory distribution and bandwidth. Using this approach, we explore several implementation alternatives in order to find a compromise between processing speed and area of the PE. We …
Consistent estimates of the mode of the probability density function in nonparametric deconvolution problems
2000
International audience
Evaluation of the areal material distribution of paper from its optical transmission image
2011
International audience; The goal of this study was to evaluate the areal mass distribution (defined as the X-ray transmission image) of paper from its optical transmission image. A Bayesian inversion framework was used in the related deconvolution process so as to combine indirect optical information with a priori knowledge about the type of paper imaged. The a priori knowledge was expressed in the form of an empirical Besov space prior distribution constructed in a computationally effective way using the wavelet transform. The estimation process took the form of a large-scale optimization problem, which was in turn solved using the gradient descent method of Barzilai and Borwein. It was de…
A Deep Learning Model for Automatic Sleep Scoring using Multimodality Time Series
2021
Sleep scoring is a fundamental but time-consuming process in any sleep laboratory. Automatic sleep scoring is crucial and urgent to help address the increasing unmet need for sleep research. Therefore, this paper aims to develop an end-to-end deep learning architecture using raw polysomnographic recordings to automate sleep scoring. The proposed model adopts two-dimensional convolutional neural networks (2D-CNN) to automatically learn features from multi-modality signals, together with a "squeeze and excitation" block for recalibrating channel-wise feature responses. The learnt representations are finally fed to a softmax classifier to generate predictions for each sleep stage. The model pe…