Experimental Verification of a Posteriori Quality Enhancement of Security Images

Abstract

The image quality is a crucial issue in the applied imaging system incl. security. The security imaging systems have special qualitative requirements - the general perceptive image quality is not so important compared to the preservation of selected security image characteristics such as an identification or classification. In the first part we have tested the impact of image enhancing algorithms on the display readability in presence of noise. We have chosen the registration plate as an example and two noise types have been added in order to find the readability threshold. The second part has been devoted to de-noising techniques for image noise removal and deals with advanced WT (wavelet transform) based method of noise suppression for security purposes. Specific requirements on the proposed noise suppression technique can be stated. It should be efficient, both in the sense of low computational complexity but also by means of high noise suppression performance. Moreover, the system must preserve all the important features of the scene being watched. Several tests have been done to verify high noise suppression performance, computational efficiency and low distortion of important features.