Contour and Texture for Visual Recognition of Object Categories: Automatic Object Recognition Using Learned Patterns of Contour and Texture - Jamie Shotton - Boeken - VDM Verlag - 9783639019704 - 13 mei 2008
Indien omslag en titel niet overeenkomen, is de titel correct

Contour and Texture for Visual Recognition of Object Categories: Automatic Object Recognition Using Learned Patterns of Contour and Texture

Jamie Shotton

Prijs
€ 62,99

Besteld in een afgelegen magazijn

Verwachte levering 31 jul. - 11 aug.
Voeg toe aan uw iMusic-verlanglijst
Eller

Contour and Texture for Visual Recognition of Object Categories: Automatic Object Recognition Using Learned Patterns of Contour and Texture

The recognition of object categories has become a major topic in computer vision. Accurate automatic visual recognition is central to applications such as image search, robotics, and vehicle safety systems. This book proposes new discriminative learning approaches to three recognition tasks. 'Image classification' aims to determine the presence of an object of a particular category in an image or video frame. 'Object detection' further aims to localize these objects. And 'semantic segmentation' aims to partition an image into coherent regions of particular categories. First, we show that a codebook of learned fragments of object contours is sufficient for accurate recognition. Second, we propose new texture features that simultaneously exploit local appearance, approximate shape and appearance context. The efficacy of the new contour and texture features is tested on a variety of challenging image datasets. Finally, we show how a combination of these two largely orthogonal features improves recognition above that achieved by either feature alone.

Media Boeken     Paperback Book   (Boek met zachte kaft en gelijmde rug)
Vrijgegeven 13 mei 2008
ISBN13 9783639019704
Uitgevers VDM Verlag
Pagina's 152
Afmetingen 213 g
Taal en grammatica Engels