Close Range Photogrammetry and Machine Vision by K.B. Atkinson J.G. Fryer

Author:K.B. Atkinson,J.G. Fryer [K.B.Atkinson]
Language: eng
Format: epub
ISBN: 9781849953481
Publisher: Lightning Source Inc.

T(1) and T(2) are selected to satisfy those conditions.

Two more distinctive multi-threshold approaches will be presented here.

Recursive segmentation

This approach (Wang and Haralick, 1984) is based on applying an edge detector to the image first. It can be summarized as follows:

1. Produce an edge image from the grey-level image using a good edge detector.

2. Take only the points on or near the edges in the grey-level image.

3. Divide the points into two types; those which are darker (e.g. those on the lower step of a step edge) and those which are brighter. Disregard points in between these two levels.

4. Compute two histograms, one for the darker points only, Hd, and one for the brighter points, Hb. This type of histogram will usually have only one peak.

5. The peak in each histogram will correspond to threshold values Td and Tb respectively (note that this is in contrast to the case of the full image histogram where the valleys are the thresholds.) T for the image is selected to be Td if the condition:

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.