scene sketch – color drawings

hand drawing reflecting an image scene by color, sketch is more a cartoon-like drawing


Extract a multi-resolution wavelet fingerprint of the complete image comparing color and shape. 20 compression coefficients allows efficient retrieval.

shape sketch – line drawings

this kind of hand drawings provide the most natural extension of a language based word-level query, which is just a rough outline of an object focusing entirely on the shape.

  • Sketch is a thin line drawing focusing on shape, no appearance info, may contain one to many line stokes, define a valuable stroke point ordering.
  • Contour is a connected sequence of points, which may come from the input sketch
  • Contour fragment is a connected subset of a contour. an ordered list of points
  • Chord is a line joining two points of a region boundary, some could be used as shape descriptor:
    • histogram of distribution of chord lengths and angels
    • relative orientations between specifically chosen chords
    • used in Geometric hashing

user stroke and image edges may be over fragmented, and broken into multiple contours- so partial matching, e.g. The PArtial Contour and Efficient Matching (PACEM)


efficient image retrieval in large database by modeling object of interest using a sketch of the object shape.

Core idea:

a bag of local fragment codewords, which are fragment prototypes that are obtained from edges in image database.

use these fragment shape(codewords) to describe both the sketch query and images

painting as query
it is limited by perceptual error in both shape and color, as well as by the artistic prowess and patience of the user.

Painted Scanned Target

Wavelet Transform

similar to the Fourier transform, but encodes both frequency and spacial information.

most used in area of image compression – saving the few largest wavelet coefficients for an image, throwing away all of the smaller coefficients, it is possible to recover a fairly accurate representation of image.

        20 coeffs                               100 coeffs                      400 coeffs       Original (16,000 coeffs)

by collecting 20 coefficients for each color channel, we distill a small signature for each of these images, save these signature and


Fast Multiresolution Image Querying  please see the paper.
retrieval by shape-sketch






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 )

Twitter picture

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

Facebook photo

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

Google+ photo

You are commenting using your Google+ 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: