ConVeS: a context verification framework for object recognition system

Context is a vital element in both biological as well as synthetic vision systems. It is essential for deriving meaningful explanation of an image. Unfortunately, there is a lack of consensus in the computer vision community on what context is and how it should be represented. In this paper context is defined generally as "any and all information that is not directly derived from the object of interest but helps in explaining it". Furthermore, a description of context is provided in terms of its three major aspects namely scope, source and type. As an application of context in improving object detection results a Context Verification System (ConVeS) is proposed. ConVeS incorporates semantic and spatial context with an external knowledgebase to verify object detection results provided by state-of-the-art machine learning algorithms such as support vector machine or artificial neural network. ConVeS is presented as a simple framework that can be effectively applied to a wide range of computer vision applications such as medical image, surveillance video, and natural imagery.

[1]  Tat-Seng Chua,et al.  A learning-based approach for annotating large on-line image collection , 2004, 10th International Multimedia Modelling Conference, 2004. Proceedings..

[2]  Bernhard Schölkopf,et al.  Efficient Approximations for Support Vector Machines in Object Detection , 2004, DAGM-Symposium.

[3]  A. Torralba,et al.  The role of context in object recognition , 2007, Trends in Cognitive Sciences.

[4]  Clement T. Yu,et al.  Using semantic contents and WordNet in image retrieval , 1997, SIGIR '97.

[5]  M. A. Fischler,et al.  Context-based vision: Recognition of natural scenes , 1989, Twenty-Third Asilomar Conference on Signals, Systems and Computers, 1989..

[6]  Eric O. Postma,et al.  Context-based object detection in still images , 2006, Image Vis. Comput..

[7]  Henrik I. Christensen,et al.  Object detection using background context , 2004, ICPR 2004.

[8]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[9]  Marius Otesteanu,et al.  Neural network based object recognition using color block matching , 2007 .

[10]  R. S. J. Frackowiak,et al.  Human brain activity during spontaneously reversing perception of ambiguous figures , 1998, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[11]  Graeme Hirst,et al.  Context as a Spurious Concept , 1997, ArXiv.

[12]  Eugene Charniak,et al.  Bayesian Networks without Tears , 1991, AI Mag..

[13]  Andrea Vedaldi,et al.  Objects in Context , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[14]  Sung-Bae Cho,et al.  Context-Based Scene Recognition Using Bayesian Networks with Scale-Invariant Feature Transform , 2006, ACIVS.

[15]  Lior Wolf,et al.  A Critical View of Context , 2006, International Journal of Computer Vision.

[16]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[17]  Bernt Schiele,et al.  Using Local Context To Improve Face Detection , 2003, BMVC.

[18]  Antonio Torralba,et al.  Contextual Priming for Object Detection , 2003, International Journal of Computer Vision.

[19]  M. Tarr,et al.  Unraveling mechanisms for expert object recognition: bridging brain activity and behavior. , 2002, Journal of experimental psychology. Human perception and performance.

[20]  Antonio Torralba,et al.  Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes , 2003, NIPS.

[21]  R. Zemel,et al.  Multiscale conditional random fields for image labeling , 2004, CVPR 2004.

[22]  Gustavo Carneiro,et al.  Pruning local feature correspondences using shape context , 2004, ICPR 2004.

[23]  M. Bar.  Visual objects in context , 2004, Nature Reviews Neuroscience.

[24]  Nando de Freitas,et al.  A Statistical Model for General Contextual Object Recognition , 2004, ECCV.

[25]  Yiannis Kompatsiaris,et al.  Knowledge-Assisted Image Analysis Based on Context and Spatial Optimization , 2006, Int. J. Semantic Web Inf. Syst..

[26]  S. Ullman,et al.  Spatial Context in Recognition , 1996, Perception.

[27]  Anthony Hoogs,et al.  Object Boundary Detection in Images using a Semantic Ontology , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[28]  Isabelle Bloch,et al.  Using relative spatial relationships to improve individual region recognition , 2005 .