For access to this article, please select a purchase option:
Buy conference paper PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
This investigation describes a novel probability distribution for image representation that is function of the structural and spatial image information. It reviews the actual methods used for the assessment of the image information and shows their limits in the assessment of the image spatial information, and describes how the novel probability distribution is defined, assessed and analysed. In order to demonstrate the feasibility of the developed technique, a series of tests were carried out on rectangular, circular, and triangular images. The experimental results of the assessment of the overall probability distribution are presented. The developed probability distribution is then used with Shannon's (1948) entropy to assess the information content of artificial binary images. These binary images may be obtained from thresholding or performing boundary detection on grey-level images. The obtained results show that the image information changes with image spatial attributes; it increases with the image size and the image shape complexity. The use of this information measure in shape description is also introduced.