Object Recognition by Scene Alignment

Current object recognition systems can only recognize a limited number of object categories; scaling up to many categories is the next challenge. We seek to build a system to recognize and localize many different object categories in complex scenes. We achieve this through a simple approach: by matching the input image, in an appropriate representation, to images in a large training set of labeled images. Due to regularities in object identities across similar scenes, the retrieved matches provide hypotheses for object identities and locations. We build a probabilistic model to transfer the labels from the retrieval set to the input image. We demonstrate the effectiveness of this approach and study algorithm component contributions using held-out test sets from the LabelMe database.

• Type: Conference
• Year: 2007
• Where: NIPS
• Authors: Bryan C. Russell, Antonio Torralba, Ce Liu, Robert Fergus, William T. Freeman
• Keywords: Current Object Recognition, Information Technology, NIPS 2007, Object Categories, Object Identities