Contour detection algorithms which operate directly on an image are greatly affected by small magnitude transformations to the image. A contour detection method is developed which takes advantage of the Curvature Scale Space representation.  This method improves detection performance by increasing the detector invariance to affine transformations including: scaling, rotation, and translation.  Invariance to noise is also demonstrated.  The addition of a histogram matching criterion further improves performance by sanity-checking the results of the Curvature Scale Space detection. The combination of the two techniques produces a robust detector well-suited for object detection in noisy images and video.

In the above example, we see two images. First, a silhouette of Sherlock Holmes' face. Next, a rotated and scaled version of the same image. While these two images differ significantly in the pixel domain, their Curvature Scale Space (CS²) representations, which are shown below each image, are identical down to a small translation.