000 04276nam a22005295i 4500
001 978-1-4471-6735-8
003 DE-He213
005 20200421112235.0
007 cr nn 008mamaa
008 150721s2015 xxk| s |||| 0|eng d
020 _a9781447167358
_9978-1-4471-6735-8
024 7 _a10.1007/978-1-4471-6735-8
_2doi
050 4 _aQ337.5
050 4 _aTK7882.P3
072 7 _aUYQP
_2bicssc
072 7 _aCOM016000
_2bisacsh
082 0 4 _a006.4
_223
100 1 _aCamastra, Francesco.
_eauthor.
245 1 0 _aMachine Learning for Audio, Image and Video Analysis
_h[electronic resource] :
_bTheory and Applications /
_cby Francesco Camastra, Alessandro Vinciarelli.
250 _a2nd ed. 2015.
264 1 _aLondon :
_bSpringer London :
_bImprint: Springer,
_c2015.
300 _aXVI, 561 p. 119 illus.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aAdvanced Information and Knowledge Processing,
_x1610-3947
505 0 _aIntroduction -- Part I: From Perception to Computation -- Audio Acquisition, Representation and Storage -- Image and Video Acquisition, Representation and Storage -- Part II: Machine Learning -- Machine Learning -- Bayesian Theory of Decision -- Clustering Methods -- Foundations of Statistical Learning and Model Selection -- Supervised Neural Networks and Ensemble Methods -- Kernel Methods -- Markovian Models for Sequential Data -- Feature Extraction Methods and Manifold Learning Methods -- Part III: Applications -- Speech and Handwriting Recognition -- Speech and Handwriting Recognition -- Video Segmentation and Keyframe Extraction -- Real-Time Hand Pose Recognition -- Automatic Personality Perception -- Part IV: Appendices -- Appendix A: Statistics -- Appendix B: Signal Processing -- Appendix C: Matrix Algebra -- Appendix D: Mathematical Foundations of Kernel Methods -- Index.
520 _aThis second edition focuses on audio, image and video data, the three main types of input that machines deal with when interacting with the real world. A set of appendices provides the reader with self-contained introductions to the mathematical background necessary to read the book. Divided into three main parts, From Perception to Computation introduces methodologies aimed at representing the data in forms suitable for computer processing, especially when it comes to audio and images. Whilst the second part, Machine Learning includes an extensive overview of statistical techniques aimed at addressing three main problems, namely classification (automatically assigning a data sample to one of the classes belonging to a predefined set), clustering (automatically grouping data samples according to the similarity of their properties) and sequence analysis (automatically mapping a sequence of observations into a sequence of human-understandable symbols). The third part Applications shows how the abstract problems defined in the second part underlie technologies capable to perform complex tasks such as the recognition of hand gestures or the transcription of handwritten data. Machine Learning for Audio, Image and Video Analysis is suitable for students to acquire a solid background in machine learning as well as for practitioners to deepen their knowledge of the state-of-the-art. All application chapters are based on publicly available data and free software packages, thus allowing readers to replicate the experiments.
650 0 _aComputer science.
650 0 _aMultimedia information systems.
650 0 _aImage processing.
650 0 _aPattern recognition.
650 1 4 _aComputer Science.
650 2 4 _aPattern Recognition.
650 2 4 _aImage Processing and Computer Vision.
650 2 4 _aMultimedia Information Systems.
700 1 _aVinciarelli, Alessandro.
_eauthor.
710 2 _aSpringerLink (Online service)
773 0 _tSpringer eBooks
776 0 8 _iPrinted edition:
_z9781447167341
830 0 _aAdvanced Information and Knowledge Processing,
_x1610-3947
856 4 0 _uhttp://dx.doi.org/10.1007/978-1-4471-6735-8
912 _aZDB-2-SCS
942 _cEBK
999 _c58241
_d58241