A Stochastic Grammar of Images
A stochastic Grammar of Image is the first book to provide a foundational review and perspective of grammatical approaches to computer vision in its quest for a stochastic and context sensitive grammar of images, if is intended to serve as a unified frame work of representation leaming and recognition for a large number of object categories.
It starts out by addressing he historic trends in the area and overviewing the main concepts such as the and or graph the parse graphs the dictionary and goes on to learning issues, semantic gaps between symbols and pixels dataset for for learning and algorithms. The proposal grammar presented integrates three prominent representations in the literature stochastic grammar for composition. Markev (or graphical) models for contexts, and sparse coding with primitives (wavelets). It also combines the structure-based and appearance based methods in the vision literature. At the end of the review three case studies are presented to illustrate the proposed grammar.
A Stochastic Grammar of Images is an important contribution to the literature on structured statistical models in computer vision.
What people are saying - Write a review
We haven't found any reviews in the usual places.
algorithm And-node And–Or graph And–Or tree arrows attributes augmented bike bottom-up brieﬂy child nodes classiﬁcation clock Closed lists composed computation connected context dataset deﬁned Deﬁnition detection dictionary diﬀerent edges example ﬁnd ﬁrst ﬁve Gand−or graphical graphlets histogram image grammar image parsing image patch image primitives inference algorithm input image instances language large number layer leaf nodes learning Lotus Hill machine learning Markov random ﬁeld matching Microsoft Research non-terminal nodes number of conﬁgurations object categories occluded open bonds Open lists Or-nodes overlap parameters parse graph pg parse tree pixels posterior probability primal sketch production rules recognition reconﬁgurable rectangles recursive represented reusable sampling scale SCFG semantic shown in Figure shows signiﬁcant sketch graph sparse coding speciﬁc statistical stochastic grammar structures synthesized T”-junctions template terminal nodes textons texture tion top-down prediction top-down process unsupervised learning valid conﬁgurations vision visual vocabulary
Page 106 - H. Murase and SK Nayar. Visual learning and recognition of 3D objects from appearance.
Page 107 - S. Ullman, E. Sali, and M. Vidal-Naquet, "A fragment-based approach to object representation and classification," in Proceedings of 4th International Workshop on Visual Form, Capri, Italy, 2001.
Page 106 - Freeman, WT: LabelMe: a database and webbased tool for image annotation...
Page 107 - Image parsing: Unifying segmentation, detection, and recognition," International Journal of Computer Vision, vol.
Page 107 - From information scaling laws of natural images to regimes of statistical models," Quarterly of Applied Mathematics, 2007 (To appear).  ZJ Xu, H. Chen, and SC Zhu, "A high resolution grammatical model for face representation and sketching," in Proceedings of IEEE Conference on CVPR, San Diego, June 2005.
Page 106 - The role of thalamus in the flow of information to cortex," Philosophical Transactions of Royal Society London (Biology), vol.