This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Groups of Adjacent Contour Segments for Object Detection

V. Ferrari, L. Fevrier, F. Jurie, and C. Schmid
IEEE Transactions on Pattern Analysis and Machine Intelligence
Vol. 30, No. 1, pp. 36-51, January 2008


We present a family of scale-invariant local shape features formed by chains of k connected, roughly straight contour segments (kAS), and their use for object class detection. kAS are able to cleanly encode pure fragments of an object boundary, without including nearby clutter. Moreover, they offer an attractive compromise between information content and repeatability, and encompass a wide variety of local shape structures. We also define a translation and scale invariant descriptor encoding the geometric configuration of the segments within a kAS, making kAS easy to reuse in other frameworks, for example as a replacement or addition to interest points. Software for detecting and describing kAS is released on We demonstrate the high performance of kAS within a simple but powerful sliding-window object detection scheme. Through extensive evaluations, involving eight diverse object classes and more than 1400 images, we 1) study the evolution of performance as the degree of feature complexity k varies and determine the best degree; 2) show that kAS substantially outperform interest points for detecting shape-based classes; 3) compare our object detector to the recent, state-of-the-art system by Dalal and Triggs [4].

Download in pdf format
  author = {V. Ferrari and L. Fevrier and F. Jurie and and C. Schmid},
  title = {Groups of Adjacent Contour Segments for Object Detection},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2008},
  month = {January},
  pages = {36-51},
  volume = {30},
  number = {1},
  keywords = {local features, shape descriptors, object detection}