point matching

Point features can be used to find a sparse set of corresponding locations in different images.

There are two main approaches to finding feature points and their correspondences:

  1. The first is to find features in one image that can be accurately tracked using a local search technique such as correlation or least squares; -more suitable when images are taken from nearby viewpoints or in rapid succession (e.g., video sequences)
  2. The second is to independently detect features in all the images under consideration and then match features based on their local appearance – more suitable when a large amount of motion or appearance change is expected, e.g., in stitching together panoramas

keypoint detection and matching pipeline four separate stages:

  1. feature detection (extraction) stage – each image is searched for locations that are likely to match well in other images
  2. second feature description stage – each region around detected keypoint locations in converted into a more compact and stable (invariant) descriptor that can be matched against other descriptors
  3. third feature matching stage – efficiently searches for likely matching candidates in other images
  4. fourth feature tracking stage – an alternative to the third stage that only searches a small neighborhood around each detected feature and is therefore more suitable for video processing

Two steps:

  1. point detection – finds points or patches in the image that have saliency – interest points
  2. point description – assigns a feature vector to each point

The NNs of a point in one image are found in another image:



There are many existing point detection and description algorithms, SIFT return not only the location of the points, but also the scale and orientation.

Point matching as classification – instead of computing point feature vectors and finding the NNs, each point in the ‘training’ image is a class.

Why corner?

– junctions of the contours

more stable features over the changes of viewpoint

large variations in the neighbourhood of the point in all directions

– Corner is the good feature to match!

Corner points

Looking at intensity values within a small window, shifting the window in any direction should yield a large change in appearance.

Harris Corner detector

Harris corner detector gives a mathematical approach for determining which case holds:

  • flat region: no change in all directions
  • edge: no change along the edge direction
  • corner: significant change in all directions



Leave a Reply

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

WordPress.com Logo

You are commenting using your WordPress.com 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 WordPress.com site

Jing's Blog

Just another WordPress.com site

Start from here......







Just another WordPress.com 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: