Sökning: "feature extraction"

Visar resultat 1 - 5 av 79 avhandlingar innehållade orden feature extraction.

  1. 1. Feature Extraction for Low-Frequency Signal Classification

    Detta är en avhandling från Stockholm : KTH

    Författare :José Chilo; Högskolan i Gävle.; KTH.; [2008]
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; TECHNOLOGY Electrical engineering; electronics and photonics Electronics; TEKNIKVETENSKAP Elektroteknik; elektronik och fotonik Elektronik; Infrasound; feature extraction; wavelets; data acquisition; NATURAL SCIENCES Physics Atomic and molecular physics Atomic physics; NATURVETENSKAP Fysik Atom- och molekylfysik Atomfysik; infrasound; seismic signals; fingerprints; mining; multimodal data space;

    Sammanfattning : The development of the International Monitoring System (IMS) for the verification of the Comprehensive Nuclear-Test-Ban Treaty Organization (CTBTO) has led to a rapid revival of interest in infrasound. Furthermore, the installation of low-frequency sensors at seismic sites has increased in recent years, providing researchers with large and heterogeneous data-sets in near real-time. LÄS MER

  2. 2. Symmetry Filters Applied to Fingerprints : Representation, Feature extraction and Registration

    Detta är en avhandling från Göteborg : Chalmers tekniska högskola

    Författare :Kenneth Nilsson; Högskolan i Halmstad.; [2005]
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TECHNOLOGY; TEKNIKVETENSKAP; fingerprint recognition; symmetry filters; orientation field; multiscale filtering; singular points; orientation radiograms; registration; multiexpert;

    Sammanfattning : A common framework for feature extraction in fingerprints is proposed by use of certain symmetries. The proposal includes representation, filters, and filtering techniques for common features including minutiae points, singular points and the ridge and valley patterns. LÄS MER

  3. 3. New directions in non-porous membrane extraction

    Detta är en avhandling från Department of Analytical Chemistry, Lund University

    Författare :Eddie Thordarson; Lunds universitet.; Lund University.; [2000]
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; extracting syringe; solvent-free; miniaturisation; micro-porous membrane liquid-liquid extraction; polymeric membrane extraction; Non-porous membrane extraction; supported liquid extraction; integration; automation; Analytical chemistry; Analytisk kemi;

    Sammanfattning : Popular Abstract in Swedish Avhandlingen berör membranbaserade tekniker för provupparbetning, vilket enkelt uttryckt innebär att använda membran för att ”skilja agnarna från vetet”. De membran som använts kan designas för att vara selektivt genomsläppliga, d.vs. släppa igenom vissa molekyler och inte andra. LÄS MER

  4. 4. Perceptually motivated speech recognition and mispronunciation detection

    Detta är en avhandling från Stockholm : KTH Royal Institute of Technology

    Författare :Christos Koniaris; KTH.; [2012]
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; feature extraction; feature selection; auditory models; MFCCs; speech recognition; distortion measures; perturbation analysis; psychoacoustics; human perception; sensitivity matrix; pronunciation error detection; phoneme; second language; perceptual assessment;

    Sammanfattning : This doctoral thesis is the result of a research effort performed in two fields of speech technology, i.e., speech recognition and mispronunciation detection. Although the two areas are clearly distinguishable, the proposed approaches share a common hypothesis based on psychoacoustic processing of speech signals. LÄS MER

  5. 5. Feature extraction based on a tensor image description

    Detta är en avhandling från Linköping : Linköping University Electronic Press

    Författare :Carl-Fredrik Westin; Linköpings universitet.; Linköpings universitet.; [1991]
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Image analysis; Representation; Tensor; Hough transform; Möbius strip; Corner detection; TECHNOLOGY; TEKNIKVETENSKAP;

    Sammanfattning : Feature extraction from a tensor based local image representation introduced by Knutsson in [37] is discussed. The tensor representation keeps statements of structure, certainty of statement and energy separate. LÄS MER