000 03974nam a22005175i 4500
001 978-3-031-01817-6
003 DE-He213
005 20240730163723.0
007 cr nn 008mamaa
008 220601s2017 sz | s |||| 0|eng d
020 _a9783031018176
_9978-3-031-01817-6
024 7 _a10.1007/978-3-031-01817-6
_2doi
050 4 _aTA1501-1820
050 4 _aTA1634
072 7 _aUYT
_2bicssc
072 7 _aCOM016000
_2bisacsh
072 7 _aUYT
_2thema
082 0 4 _a006
_223
100 1 _aScheirer, Walter J.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_980180
245 1 0 _aExtreme Value Theory-Based Methods for Visual Recognition
_h[electronic resource] /
_cby Walter J. Scheirer.
250 _a1st ed. 2017.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2017.
300 _aXV, 115 p.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aSynthesis Lectures on Computer Vision,
_x2153-1064
505 0 _aPreface -- Acknowledgments -- Figure Credits -- Extrema and Visual Recognition -- A Brief Introduction to Statistical Extreme Value Theory -- Post-recognition Score Analysis -- Recognition Score Normalization -- Calibration of Supervised Machine Learning Algorithms -- Summary and Future Directions -- Bibliography -- Author's Biography.
520 _aA common feature of many approaches to modeling sensory statistics is an emphasis on capturing the "average." From early representations in the brain, to highly abstracted class categories in machine learning for classification tasks, central-tendency models based on the Gaussian distribution are a seemingly natural and obvious choice for modeling sensory data. However, insights from neuroscience, psychology, and computer vision suggest an alternate strategy: preferentially focusing representational resources on the extremes of the distribution of sensory inputs. The notion of treating extrema near a decision boundary as features is not necessarily new, but a comprehensive statistical theory of recognition based on extrema is only now just emerging in the computer vision literature. This book begins by introducing the statistical Extreme Value Theory (EVT) for visual recognition. In contrast to central-tendency modeling, it is hypothesized that distributions near decision boundaries form a more powerful model for recognition tasks by focusing coding resources on data that are arguably the most diagnostic features. EVT has several important properties: strong statistical grounding, better modeling accuracy near decision boundaries than Gaussian modeling, the ability to model asymmetric decision boundaries, and accurate prediction of the probability of an event beyond our experience. The second part of the book uses the theory to describe a new class of machine learning algorithms for decision making that are a measurable advance beyond the state-of-the-art. This includes methods for post-recognition score analysis, information fusion, multi-attribute spaces, and calibration of supervised machine learning algorithms.
650 0 _aImage processing
_xDigital techniques.
_94145
650 0 _aComputer vision.
_980181
650 0 _aPattern recognition systems.
_93953
650 1 4 _aComputer Imaging, Vision, Pattern Recognition and Graphics.
_931569
650 2 4 _aComputer Vision.
_980182
650 2 4 _aAutomated Pattern Recognition.
_931568
710 2 _aSpringerLink (Online service)
_980183
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783031006890
776 0 8 _iPrinted edition:
_z9783031029455
830 0 _aSynthesis Lectures on Computer Vision,
_x2153-1064
_980184
856 4 0 _uhttps://doi.org/10.1007/978-3-031-01817-6
912 _aZDB-2-SXSC
942 _cEBK
999 _c84913
_d84913