Low-level feature extraction (including edge detection) - Feature Extraction and Image Processing - page 130

(a) Original image (b) First order (c) Prewitt (d) Sobel

(e) Laplacian (f) Marr-Hildreth (g) Canny (h) Spacek

Figure 4.31 Comparison of edge detection operators

The results for all edge operators have been generated using hysteresis thresholding
where the thresholds were selected manually for best performance. The basic first-order
operator, Figure 4.31 (b), responds rather nicely to the noise and it is difficult to select a
threshold which reveals a major part of the pitus border. Some is present in the Prewitt and
Sobel operators' results, Figure 4.31 (c) and Figure 4.31 (d), respectively, but there is still
much noise in the processed image, though there is less in the Sobel. The Laplacian
operator, Figure 4.31 (e), gives very little information indeed, which is to be expected with
such noisy imagery. However, the more advanced operators can be used to good effect. The
Marr-Hildreth approach improves matters, Figure 4.31 (f), but suggests that it is difficult to
choose a LoG operator of appropriate size to detect a feature of these dimensions in such
noisy imagery. However, the Canny and Spacek operators can be used to good effect, as
shown in Figures 4.31 (g) and (h), respectively. These reveal much of the required information,
together with data away* from the pitus itself. In an automated analysis system, for this
application, the extra complexity of the more sophisticated operators would clearly be
warranted.

4.6 Detecting image curvature

Edges are perhaps the low-level image features that are most obvious to human vision.
They preserve significant features, so we can usually recognise what an image contains
from its edge-detected version. However, there are other low-level features that can be
used in computer vision. One important feature is curvature . Intuitively, we can consider
curvature as the rate of change in edge direction. This rate of change characterises the
points in a curve; points where the edge direction changes rapidly are corners , whereas
points where there is little change in edge direction correspond to straight lines. Such