000			nam a22 7a 4500
999			_c29156 _d29156
008			190205b xxu||||| |||| 00| 0 eng d
020			_a9781681730233
082			_a006.37 _bFEL
100			_aFelsberg, Michael
245			_aProbabilistic and biologically inspired feature representations
260			_aS.L. : _bMorgan & Claypool Publishers, _c2018
300			_axiii, 89p. ; _biil. : _c25 cm.
365			_aUSD _b44.95
440			_aSynthesis lectures on computer vision ; Number 16
520			_aThis text collects a substantial amount of work on the topic of channel representations. Channel representations are a biologically motivated, wavelet-like approach to visual feature descriptors: they are local and compact, they form a computational framework, and the represented information can be reconstructed. The first property is shared with many histogram- and signature-based descriptors, the latter property with the related concept of population codes.
650			_aChannel representation
650			_aChannel-coded feature
650			_aMap feature descriptor
650			_aSignature
942			_2ddc _cBK