We seek to discover the object categories depicted in a set of unlabelled images. We achieve this using a model developed in the statistical text literature: probabilistic latent semantic analysis (pLSA). In text analysis, this is used to discover topics in a corpus using the bag-of-words document representation. Here we treat object categories as topics, so that an image containing instances of several categories is modeled as a mixture of topics. The model is applied to images by using a visual analogue of a word, formed by vector quantizing SIFT-like region descriptors. The topic discovery approach successfully translates to the visual domain: for a small set of objects, we show that both the object categories and their approximate spatial layout are found without supervision. Performance of this unsupervised method is compared to the supervised approach of Fergus et al. (2003) on a set of unseen images containing only one object per image. We also extend the bag-of-words vocabulary to include 'doublets' which encode spatially local co-occurring regions. It is demonstrated that this extended vocabulary gives a cleaner image segmentation. Finally, the classification and segmentation methods are applied to a set of images containing multiple objects per image. These results demonstrate that we can successfully build object class models from an unsupervised analysis of images.
Discovering objects and their location in images
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 1 ; 370-377 Vol. 1
2005-01-01
5892354 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Discovering Objects and their Localization in Images
British Library Conference Proceedings | 2005
|CORRESPONDENCE - On discovering maritime objects
Online Contents | 2007
|Discovering hierarchical object models from captioned images
British Library Online Contents | 2012
|Material Vernaculars : Objects, Images, and Their Social Worlds
TIBKAT | 2016
|Machine Vision in Autonomous Systems of Detection and Location of Objects in Digital Images
Springer Verlag | 2013
|