DETECTING MULTIPLE OBJECTS USING TREE BASED CONTEXT MODEL

Object recognition is the study of machines that can observe the environment and make reasonable decisions about the categories of patterns. In object recognition, contextual information is exploited to detect and localize multiple object categories in an image. A context model can rule out some unlikely combinations or location of objects and guide detectors to produce semantically coherent interpretation of a scene. The contextual information enables coherent understanding of natural scene and images. The project Sun 09 dataset is used with images that contain many instances of different object categories and output of local detectors into one probabilistic framework. It is used for leveraging contextual information. The coherent structure among object categories models the object co-occurrences and spatial relation1ships using tree structured graphical model. The context model improves object recognition performance and provides coherent interpretation of scene, enables reliable image querying system by multiple object categories. Boosted Random Field is introduced to combine Boosting and Conditional Random field for improving the accuracy and speed. Boosted Random Field provides better performance and requires fewer computations. Boosted Random Field searches objects in an image and detects stuff things in an office.