Search results for "pattern"

showing 10 items of 4203 documents

An Improved Skew Angle Detection and Correction Technique for Historical Scanned Documents Using Morphological Skeleton and Progressive Probabilistic…

2017

International audience; Skew detection is a crucial step for document analysis systems. Indeed, it represents one of the basic challenges, especially in case of historical documents analysis. In this paper, we propose a novel robust skew angle detection and correction technique. Morphological Skeleton is introduced to significantly reduce the amount of data to treat by removing the redundant pixels and keeping only the central curves of the image components. The proposed method then uses Progressive Probabilistic Hough Transform (PPHT) to identify image lines. A special procedure is finally applied in order to estimate the global skew angle of the document image from these detected lines. E…

Computer science[SPI] Engineering Sciences [physics]ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONDocument image analysis02 engineering and technology01 natural sciencesElectronic mail[SPI]Engineering Sciences [physics]Robustness (computer science)HistogramOrientation0103 physical sciencesMorphological skeleton0202 electrical engineering electronic engineering information engineering010306 general physicsMorphological SkeletonProbabilistic hough transformPixelbusiness.industrySkewProbabilistic logicPattern recognitionProgressive Probabilistic Hough Transform[SPI.TRON] Engineering Sciences [physics]/Electronics[SPI.TRON]Engineering Sciences [physics]/ElectronicsSkew correctionAlgorithmImages020201 artificial intelligence & image processingArtificial intelligencebusinessSkew angle detection
researchProduct

Wi-Sense: a passive human activity recognition system using Wi-Fi and convolutional neural network and its integration in health information systems

2021

AbstractA human activity recognition (HAR) system acts as the backbone of many human-centric applications, such as active assisted living and in-home monitoring for elderly and physically impaired people. Although existing Wi-Fi-based human activity recognition methods report good results, their performance is affected by the changes in the ambient environment. In this work, we present Wi-Sense—a human activity recognition system that uses a convolutional neural network (CNN) to recognize human activities based on the environment-independent fingerprints extracted from the Wi-Fi channel state information (CSI). First, Wi-Sense captures the CSI by using a standard Wi-Fi network interface car…

Computer sciencebusiness.industry010401 analytical chemistry020206 networking & telecommunicationsPattern recognition02 engineering and technology01 natural sciencesConvolutional neural network0104 chemical sciencesActivity recognitionData setNetwork interface controllerChannel state informationVDP::Teknologi: 500::Medisinsk teknologi: 620Principal component analysis0202 electrical engineering electronic engineering information engineeringSpectrogramNoise (video)Artificial intelligenceElectrical and Electronic Engineeringbusiness
researchProduct

Stress Detection from Speech Using Spectral Slope Measurements

2018

Automatic detection of emotional stress is an active research domain, which has recently drawn increasing attention, mainly in the fields of computer science, linguistics, and medicine. In this study, stress is automatically detected by employing speech-derived features. Related studies utilize features such as overall intensity, MFCCs, Teager Energy Operator, and pitch. The present study proposes a novel set of features based on the spectral tilt of the glottal source and of the speech signal itself. The proposed features rely on the Probability Density Function of the estimated spectral slopes, and consist of the three most probable slopes from the glottal source, as well as the correspon…

Computer sciencebusiness.industry020206 networking & telecommunicationsProbability density functionPattern recognition02 engineering and technologyFundamental frequencySignalRandom forestEnergy operatorSpectral slopeClassifier (linguistics)0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligencebusinessWord (computer architecture)
researchProduct

Class Noise and Supervised Learning in Medical Domains: The Effect of Feature Extraction

2006

Inductive learning systems have been successfully applied in a number of medical domains. It is generally accepted that the highest accuracy results that an inductive learning system can achieve depend on the quality of data and on the appropriate selection of a learning algorithm for the data. In this paper we analyze the effect of class noise on supervised learning in medical domains. We review the related work on learning from noisy data and propose to use feature extraction as a pre-processing step to diminish the effect of class noise on the learning process. Our experiments with 8 medical datasets show that feature extraction indeed helps to deal with class noise. It clearly results i…

Computer sciencebusiness.industryActive learning (machine learning)Supervised learningFeature extractionMulti-task learningPattern recognitionSemi-supervised learningMachine learningcomputer.software_genreNoiseUnsupervised learningArtificial intelligenceInstance-based learningbusinesscomputer19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06)
researchProduct

Feature selection with Ant Colony Optimization and its applications for pattern recognition in space imagery

2016

This paper presents a feature selection (FS) algorithm using Ant Colony Optimization (ACO). It is inspired by the particular behavior of real ants, namely by the fact that they are capable of finding the shortest path between a food source and the nest. There are considered two ACO-FS model applications for pattern recognition in remote sensing imagery: ACO Band Selection (ACO-BS) and ACO Training Label Purification (ACO-TLP). The ACO-BS reduces dimensionality of an input multispectral image data by selecting the “best” subset of bands to accomplish the classification task. The ACO-TLP selects the most informative training samples from a given set of labeled vectors in order to optimize the…

Computer sciencebusiness.industryAnt colony optimization algorithmsMultispectral imageFeature selectionPattern recognition02 engineering and technologyStatistical classification020204 information systemsPrincipal component analysisShortest path problem0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligencebusinessClassifier (UML)Curse of dimensionality2016 International Conference on Communications (COMM)
researchProduct

Mean sets for building 3D probabilistic liver atlas from perfusion MR images

2012

This paper is concerned with liver atlas construction. One of the most important issues in the framework of computational abdominal anatomy is to define an atlas that provides a priori information for common medical task such as registration and segmentation. Unlike other approaches already proposed so far (to our knowledge), in this paper we propose to use the concept of random compact mean set to build probabilistic liver atlases. To accomplish this task a two-tier process was carried out. First a set of 3D images was manually segmented by a physician. We see the different 3D segmented shapes as a realization of a random compact set. Secondly, elements of two known definitions of mean set…

Computer sciencebusiness.industryAtlas (topology)Probabilistic logicImage registrationPattern recognitionImage segmentationSet (abstract data type)medicine.anatomical_structureAtlas (anatomy)medicineSegmentationComputer visionArtificial intelligencebusinessPerfusion2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)
researchProduct

A Comparative Study to Analyze the Performance of Advanced Pattern Recognition Algorithms for Multi-Class Classification

2021

This study aims to implement the following four advanced pattern recognition algorithms, such as “optimal Bayesian classifier,” “anti-Bayesian classifier,” “decision trees (DTs),” and “dependence trees (DepTs)” on both artificial and real datasets for multi-class classification. Then, we calculated the performance of individual algorithms on both real and artificial data for comparison. In Sect. 1, a brief introduction is given about the study. In the second section, the different types of datasets used in this study are discussed. In the third section, we compared the classification accuracies of Bayesian and anti-Bayesian methods for both the artificial and real-life datasets. In the four…

Computer sciencebusiness.industryBayesian probabilityDecision treePattern recognitionMulticlass classificationNaive Bayes classifierBayes' theoremComputingMethodologies_PATTERNRECOGNITIONSection (archaeology)Classifier (linguistics)Pattern recognition (psychology)Artificial intelligencebusinessAlgorithm
researchProduct

New systems for extracting 3-D shape information from images

1993

Neural architectures may offer an adequate way to deal with early vision since they are able to learn shape features or classify unknown shapes, generalising the features of a few meaningful examples, with a low computational cost after the training phase. Two different neural approaches are proposed by the authors: the first one consists of a cascaded architecture made up by a first stage named BWE (Boundary Webs Extractor) which is aimed to extract a brightness gradient map from the image, followed by a backpropagation network that estimates the geometric parameters of the object parts present in the perceived scene. The second approach is based on the extraction of the boundary webs map …

Computer sciencebusiness.industryBoundary (topology)Pattern recognitionObject (computer science)BackpropagationExtractorImage (mathematics)SuperquadricsComputer visionArtificial intelligenceD-ShapeBrightness gradientbusiness
researchProduct

An Optical Remote Sensor for Fingerprint Identification using Speckle Pattern

2017

The implementation of a simple, inexpensive optical device for remote fingerprint identification is presented. The sensor is based on temporal tracking of back-reflected secondary speckle patterns generated while illuminating a finger with a laser.

Computer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologyLaserTracking (particle physics)law.inventionSpeckle pattern020210 optoelectronics & photonicsOptical sensinglaw0202 electrical engineering electronic engineering information engineeringBeam expanderComputer visionArtificial intelligenceSpeckle imagingbusinessLaser beamsRemote sensingConference on Lasers and Electro-Optics
researchProduct

A combined analysis to extract objects in remote sensing images

1999

Abstract This paper describes an object recognition system to extract shape information from remote sensing images. One of the goals is to determine if towers and power lines can be seen on one-meter imagery and how much ground conditions can influence the resolution power of the recognition algorithms. To this end, an integrated analysis system has been implemented inside the Remote Sensing Imaging System (RSIS). The methodology consists in the combination of statistical and structural information. It has been tested on real images and it will be integrated in an automatic system for the assessment of post storm damage.

Computer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONCognitive neuroscience of visual object recognitionMathematical morphologyReal imagePower (physics)Artificial IntelligenceRemote sensing (archaeology)Signal ProcessingComputer visionComputer Vision and Pattern RecognitionArtificial intelligencebusinessSoftwareRemote sensingPattern Recognition Letters
researchProduct