Automatic thresholding of gray-level pictures using two-dimensional entropy
Computer Vision, Graphics, and Image Processing
Pattern Spectrum and Multiscale Shape Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiresolution-information analysis for images
Signal Processing
Using spatial information as an aid to maximum entropy image threshold selection
Pattern Recognition Letters
ICPR '96 Proceedings of the 1996 International Conference on Pattern Recognition (ICPR '96) Volume I - Volume 7270
Hi-index | 0.10 |
Many image information assessment techniques have been proposed in the past. Most of them are based on the image histogram. When the histogram of an image is derived, the structural component of the image is generally ignored. The information assessed using the histogram is thus independent of the image spatial attributes. In this investigation an original computational technique for the assessment of the structural information content of an image is described. The developed technique produces as output an information measure which is proportional to the image geometrical attributes such as the size, the shape complexity, etc. The technique is normalised and tested on a series of artificial images. The results obtained are analysed to show how the normalised information is related to the image geometrical attributes. The results obtained are also confirmed when English character images are considered. Finally, conclusions will be drawn in terms of the suitability of the technique for applications in computer imaging problems.