Conditional Random Fields for Scene Labeling
Ifeoma Nwogu and Venu Govindaraju, Department of Computer Science and Engineering, University at Buffalo, SUNY, Buffalo, NY 14260, USA, inwogu@buffalo.edu govind@buffalo.edu
Abstract
High-level, or holistic, scene understanding involves reasoning about objects, regions, the 3D relationships between them, etc. Scene labeling underlies many of these problems in computer vision. Reasoning about scene images requires the decomposition into semantically meaningful regions over which a graphical model can be imposed. Typically, representational models, learned from data, are defined in terms of a unified energy function over the appearance and structure of the scene-under-investigation. In this ...
Get Handbook of Statistics now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
