Visual object classifcation and detection are major problems in contemporary com- puter vision. State-of-art algorithms allow thousands of visual objects to be learned and recognized, under a wide range of variations including lighting changes, occlusion and point of view etc. However, only a small fraction of the literature addresses the problem of variation in depictive styles (photographs, drawings, paintings etc.). This is a challenging gap but the ability to process images of all depictive styles and not just photographs has potential value across many applications. This thesis aims to narrow this gap. Our studies begin with primitive shapes. We provide experimental evidence that primitives shapes such as `triangle', `square', or `circle' can be found and used to fit regions in segmentations. These shapes corresponds to those used by artists as they draw. We then assume that an object class can be characterised by the qualitative shape of object parts and their structural arrangement. Hence, a novel hierarchical graph representation labeled with primitive shapes is proposed. The model is learnable and is able to classify over a broad range of depictive styles. However, as more depictive styles join, how to capture the wide variation in visual appearance exhibited by visual objects across them is still an open question. We believe that the use of a graph with multi-labels to represent visual words that exists in possibly discontinuous regions of a feature space can be helpful.
| Identifer | oai:union.ndltd.org:bl.uk/oai:ethos.bl.uk:646137 |
| Date | January 2015 |
| Creators | Wu, Qi |
| Contributors | Hall, Peter |
| Publisher | University of Bath |
| Source Sets | Ethos UK |
| Detected Language | English |
| Type | Electronic Thesis or Dissertation |
Page generated in 0.0119 seconds