Search results for "Feature extraction"

showing 10 items of 275 documents

Approximate 3D Partial Symmetry Detection Using Co-occurrence Analysis

2015

This paper addresses approximate partial symmetry detection in 3D point clouds, a classical and foundational tool for analyzing geometry. We present a novel, fully unsupervised method that detects partial symmetry under significant geometric variability, and without constraints on the number and arrangement of instances. The core idea is a matching scheme that finds consistent co-occurrence patterns in a frame-invariant way. We obtain a canonical partition of the input shape into building blocks and can handle ambiguous data by aggregating co-occurrence information across both all building block instances and the area they cover. We evaluate our method on several benchmark data sets and dem…

Noise measurementMatching (graph theory)business.industryFeature extractionPoint cloudGeometryCover (topology)Partition (number theory)Noise (video)Artificial intelligencebusinessAlgorithmMathematicsBlock (data storage)2015 International Conference on 3D Vision
researchProduct

Signal-to-noise ratio in reproducing kernel Hilbert spaces

2018

This paper introduces the kernel signal-to-noise ratio (kSNR) for different machine learning and signal processing applications}. The kSNR seeks to maximize the signal variance while minimizing the estimated noise variance explicitly in a reproducing kernel Hilbert space (rkHs). The kSNR gives rise to considering complex signal-to-noise relations beyond additive noise models, and can be seen as a useful signal-to-noise regularizer for feature extraction and dimensionality reduction. We show that the kSNR generalizes kernel PCA (and other spectral dimensionality reduction methods), least squares SVM, and kernel ridge regression to deal with cases where signal and noise cannot be assumed inde…

Noise model02 engineering and technologySNR010501 environmental sciences01 natural sciencesKernel principal component analysisSenyal Teoria del (Telecomunicació)Signal-to-noise ratioArtificial Intelligence0202 electrical engineering electronic engineering information engineeringHeteroscedastic0105 earth and related environmental sciencesMathematicsNoise (signal processing)Dimensionality reductionKernel methodsSignal classificationSupport vector machineKernel methodKernel (statistics)Anàlisi funcionalSignal ProcessingFeature extraction020201 artificial intelligence & image processingSignal-to-noise ratioComputer Vision and Pattern RecognitionAlgorithmSoftwareImatges ProcessamentReproducing kernel Hilbert spaceCausal inference
researchProduct

A Comparative Analysis of Residual Block Alternatives for End-to-End Audio Classification

2020

Residual learning is known for being a learning framework that facilitates the training of very deep neural networks. Residual blocks or units are made up of a set of stacked layers, where the inputs are added back to their outputs with the aim of creating identity mappings. In practice, such identity mappings are accomplished by means of the so-called skip or shortcut connections. However, multiple implementation alternatives arise with respect to where such skip connections are applied within the set of stacked layers making up a residual block. While residual networks for image classification using convolutional neural networks (CNNs) have been widely discussed in the literature, their a…

Normalization (statistics)General Computer ScienceComputer scienceFeature extractionESC02 engineering and technologycomputer.software_genreResidualConvolutional neural networkconvolutional neural networks0202 electrical engineering electronic engineering information engineeringGeneral Materials Scienceurbansound8kAudio signal processingBlock (data storage)Contextual image classificationGeneral EngineeringAudio classification020206 networking & telecommunications113 Computer and information sciences020201 artificial intelligence & image processinglcsh:Electrical engineering. Electronics. Nuclear engineeringData mininglcsh:TK1-9971computerresidual learningIEEE Access
researchProduct

Identifying the primary site of origin of MRI brain metastases from lung and breast cancer following a 2D radiomics approach

2017

Detection of brain metastases in patients with undiagnosed primary cancer is unusual but still an existing phenomenon. In these cases, identifying the cancer site of origin is non-feasible by visual examination of magnetic resonance (MR) images. Recently, radiomics has been proposed to analyze differences among classes of visually imperceptible imaging characteristics. In this study we analyzed 46 T1-weighted MR images of brain metastases from 29 patients: 29 of lung and 17 of breast origin. A total of 43 radiomics texture features were extracted from the metastatic lesions. Support vector machine (SVM) and k-nearest neighbors (k-NN) classifiers were implemented to evaluate the classificati…

Pathologymedicine.medical_specialtyLungmedicine.diagnostic_testbusiness.industryFeature extractionCancerMagnetic resonance imagingmedicine.disease030218 nuclear medicine & medical imagingSupport vector machine03 medical and health sciences0302 clinical medicineBreast cancermedicine.anatomical_structureRadiomicsmedicineRadiologybusinessQuantization (image processing)030217 neurology & neurosurgery2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
researchProduct

Comparative Study of Face and Person Detection algorithms: Case Study of tramway in Lyon

2019

Moving object detection is one of the most important and challenging task in video surveillance and computer vision applications. Applying it in an industrial context requires taking into account parameters that are not necessarily considered in a theoretical context. We present here a brief review of numerous face and object detection algorithms and techniques that could be applied in our crowded application context. The chosen solution was embedded into the tramway.

Person detectionComputer scienceFace (geometry)Feature extractionContext (language use)Face detectionFacial recognition systemAlgorithmObject detectionTask (project management)2019 International Conference on Advanced Systems and Emergent Technologies (IC_ASET)
researchProduct

Real-time low level feature extraction for on-board robot vision systems

2006

Robot vision systems notoriously require large computing capabilities, rarely available on physical devices. Robots have limited embedded hardware, and almost all sensory computation is delegated to remote machines. Emerging gigascale integration technologies offer the opportunity to explore alternative computing architectures that can deliver a significant boost to on-board computing when implemented in embedded, reconfigurable devices. This paper explores the mapping of low level feature extraction on one such architecture, the Georgia Tech SIMD Pixel Processor (SIMPil). The Fast Boundary Web Extraction (fBWE) algorithm is adapted and mapped on SIMPil as a fixed-point, data parallel imple…

PixelComputer sciencebusiness.industryComputationvision systems real-timeFeature extractionNull (SQL)Computer architectureEmbedded systemRobotSIMDArchitectureUnconventional computingbusiness
researchProduct

Unsupervised deep feature extraction of hyperspectral images

2014

This paper presents an effective unsupervised sparse feature learning algorithm to train deep convolutional networks on hyperspectral images. Deep convolutional hierarchical representations are learned and then used for pixel classification. Features in lower layers present less abstract representations of data, while higher layers represent more abstract and complex characteristics. We successfully illustrate the performance of the extracted representations in a challenging AVIRIS hyperspectral image classification problem, compared to standard dimensionality reduction methods like principal component analysis (PCA) and its kernel counterpart (kPCA). The proposed method largely outperforms…

PixelComputer sciencebusiness.industryDimensionality reductionFeature extractionHyperspectral imagingPattern recognitionDiscriminative modelKernel (image processing)Principal component analysisComputer visionArtificial intelligencebusinessFeature learning2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)
researchProduct

Improving SIFT-based descriptors stability to rotations

2010

Image descriptors are widely adopted structures to match image features. SIFT-based descriptors are collections of gradient orientation histograms computed on different feature regions, commonly divided by using a regular Cartesian grid or a log-polar grid. In order to achieve rotation invariance, feature patches have to be generally rotated in the direction of the dominant gradient orientation. In this paper we present a modification of the GLOH descriptor, a SIFT-based descriptor based on a log-polar grid, which avoids to rotate the feature patch before computing the descriptor since predefined discrete orientations can be easily derived by shifting the descriptor vector. The proposed des…

PixelSettore INF/01 - Informaticabusiness.industryOrientation (computer vision)GLOHInformationSystems_INFORMATIONSTORAGEANDRETRIEVALFeature extractionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-invariant feature transformPattern recognitionComputingMethodologies_PATTERNRECOGNITIONdescriptors SIFT sGLOH sGLOH+ computer vision.Robustness (computer science)Feature (computer vision)Computer Science::Computer Vision and Pattern RecognitionHistogramComputer Science::MultimediaComputer visionArtificial intelligencebusinessMathematics
researchProduct

Meta-Tracking for Video Scene Understanding

2013

International audience; This paper presents a novel method to extract dominant motion patterns (MPs) and the main entry/exit areas from a surveillance video. The method first computes motion histograms for each pixel and then converts it into orientation distribution functions (ODFs). Given these ODFs, a novel particle meta-tracking procedure is launched which produces meta-tracks, i.e. particle trajectories. As opposed to conventional tracking which focuses on individual moving objects, meta-tracking uses particles to follow the dominant flow of the traffic. In a last step, a novel method is used to simultaneously identify the main entry/exit areas and recover the predominant MPs. The meta…

Pixelbusiness.industryComputer scienceOrientation (computer vision)Feature extractionChaotic[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]020207 software engineering02 engineering and technologyTracking (particle physics)[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Video trackingHistogramMotion estimation0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingComputer visionArtificial intelligencebusiness
researchProduct

Multi-objective DSE algorithms' evaluations on processor optimization

2013

Very complex micro-architectures, like complex superscalar/SMT or multicore systems, have lots of configurations. Exploring this huge design space and trying to optimize multiple objectives, like performance, power consumption and hardware complexity is a real challenge. In this paper, using the multi-objective design space exploration tool FADSE, we tried to optimize the hardware parameters of the complex superscalar Grid ALU Processor. We compared how different heuristic algorithms handle the DSE optimization. Three of these algorithms are taken from the jMetal library (NSGAII, SPEA2 and SMPSO) while the other two, CNSGAII and MOHC were implemented by us. We show that in this huge design …

Power consumptionComputer scienceHeuristic (computer science)Design space explorationFeature extractionProcess (computing)Feature selectionParallel computingGridDesign spaceAlgorithm2013 IEEE 9th International Conference on Intelligent Computer Communication and Processing (ICCP)
researchProduct