how to get the correct SC descriptor – edge detection

The first step is to find the correct contour, then sample 100 points on the contour.

edgemaps – produced by the excellent Berkeley ‘natural boundary detector
Using this advanced edge detector instead of the standard Canny, resulted in a significant improvement in object detection performance.

Object annotations are included in files <image>_<class>.groundtruth, Each line in the file encodes the bounding-box of an instance of <class> in <image>

The coordinates of the bounding-box appear in the following format

top_left_x top_left_y bottom_right_x bottom_right_y

Binary mask

The shapes are defined by a binary mask outlining the objects.


The ETHZ Shape Classes dataset

  • created by Vittorio Ferrari, first experiment on them is:

Vittorio Ferrari, Tinne Tuytelaars and Luc Van Gool, Object Detection by Contour Segment Networks, ECCV 2006, Graz, Austria

    • ETHZ shape dataset consists of 5 object classes and a total of 255 images. The challenges it offers are clutter, intra-class shape variability, and scale changes. 
    • Several images where the object comprises only a rather small portion of the image, and we made an effort to include objects appearing at a wide range of scales.
    • The objects are mostly unoccluded and are all taken from approximately the same viewpoint (the side).
  • The code by Ferrari contains samples splits and routines for randomly creating train and test splits.
  • binary mask and alternative bounding-box annotations by Xavier Giro
    • These are useful for algorithms requiring a solid mask as input or for evaluation, rather than a contour.
    • manually add the pixels necessary to close the open contours:
      • Some Contours of the annotated objects are not closed
      • In the region-based approach, the basic work unit is the region which is surrounded by a closed contour.
    • Consistent file name scheme:
    • Obtain the binary mask of the object: segment the closed contours, select a set of regions of the segmented contour image
    • mapped the mask on the image segments that had been automatically generated: The measure that determine if a partially overlapped region was to be considered was based now on the Jaccard index

The ETHZ shape dataset has been used for object detection in various forms including

  • shape only detection,
  • complex features detection,
  • transfer learning and segmentation.
  • Hayko Riemenschneider created a pixel-accurate segmentation annotation.

The ETHZ Extended Shape classes dataset

from Konrad Schindler is larger dataset of shape categories, created by merging ETHZ shape classes with Konrad Schindler’s closed shapes. It now consists of 7 shape classes each with 50 images.

Vittorio Ferrari, Tinne Tuytelaars and Luc Van Gool, Object Detection by Contour Segment Networks, ECCV 2006, Graz, Austria

hand-drawn model

detecting objects in real images given a single hand-drawn example as ‘model’


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s




Just another site

Jing's Blog

Just another site

Start from here......







Just another site

Where On Earth Is Waldo?

A Project By Melanie Coles

the Serious Computer Vision Blog

A blog about computer vision and serious stuff

Cauthy's Blog

paper review...

Cornell Computer Vision Seminar Blog

Blog for CS 7670 - Special Topics in Computer Vision


Life through nerd-colored glasses

Luciana Haill

Brainwaves Augmenting Consciousness



Dr Paul Tennent

and the university of nottingham

turn off the lights, please

A bunch of random, thinned and stateless thoughts around the Web

%d bloggers like this: