Oregon State University

We’d like your feedback: Calendar User Survey – Event Creator Survey



Event Details

MS Final Examination – Yaofei Feng

Friday, May 31, 2013 1:00 PM - 3:00 PM

Fine-Grained Detection and Localization of Objects in Images
Object recognition is a fundamental problem in computer vision. Recognition is required by many applications. This thesis presents a distance based approach to recognize objects. The objects belong to very similar classes, where each class has large variations. This problem is called fine-grained object recognition. Given a set of training images our approach identifies a sparse number of image patches in the training set which cover the most parts of the target object in the test image. We use Hungarian algorithm to match the image patches, based on a linear combination of appearance and geometric image features. We also specify a voting scheme for each possible location of the target object in the test image. The location which is close to the training image center is more likely to be the object center in the test image. Our results on the challenging benchmark datasets are promising. This suggests that our approach is suitable to effectively address fine-grained object recognition.

Major Advisor: Sinisa Todorovic
Committee: Xiaoli Fern
Committee: Ron Metoyer
GCR: Cindy Grimm

Kelley Engineering Center (campus map)
Nicole Thompson
1 541 737 3617
Nicole.Thompson at oregonstate.edu
Sch Elect Engr/Comp Sci
This event appears on the following calendars: