Material Detail

Object Recognition and Segmentation by Association

Object Recognition and Segmentation by Association

This video was recorded at Carnegie Mellon Machine Learning Lunch seminar. Many object recognition systems train a different classifier for each object category and use the sliding window approach to classify image regions. In this talk, we pose the object recognition problem as data association where a novel object is explained solely in terms of a small set of exemplar objects to which it is visually similar. We learn a different distance function for each exemplar such that the returned distances can be interpreted to detect the presence of an object. Our exemplars are represented as image regions and the learned distances capture the relative importance of shape, color, texture, and position features for that region. We use the distance functions to detect and segment objects in novel... Show More

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.