The Method of Contour Detect

Shape Context
Image Dectection is a important research way of Computer Vision.
Two main ways of Image Detection are Contour Dectection and Content Detection.

The main points of these algorithm could be divided into two parts.
One is how to contruct the coordinate to put the point in the histogram.
Another is how to analyse the similarity between two image.

The shape context is intended to be a way of describing shapes that allows for measuring shape similarity and the recovering of point correspondences.The basic idea is to pick n points on the contours of a shape. For each point pi on the shape, consider the n − 1 vectors obtained by connecting pi to all other points. The set of all these vectors is a rich description of the shape localized at that point but is far too detailed. The key idea is that the distribution over relative positions is a robust, compact, and highly discriminative descriptor. So, for the point pi, the coarse histogram of the relative coordinates of the remaining n − 1 points,

is defined to be the shape context of pi. The bins are normally taken to be uniform in log-polar space. The fact that the shape context is a rich and discriminative descriptor can be seen in the figure below, in which the shape contexts of two different versions of the letter “A” are shown.

The difficult point of detecting images is that the orientation and the scale of the image do not fit. We can get two histogram by rotating, scaling the same image, and the computer will affirm the two pictures different.