Assessing camouflage methods using textural features

Developments in the area of signature suppression make it progressively mor e difficult to recognize targets. The emphasis has been on the reduction of distinct features, like hot spots in the infrared band. Thus, to obtain a low false alarm rate, threat sensors have to utilize more information, i.e. , spatial and spectral properties. The purpose of our work is to develop a general tool for camouflage assessment. The approach proposed applies textu re descriptors to quantify the similarity between different parts of an ima ge. In addition, other descriptors are used to distinguish man-made object characteristics. The selection of an appropriate set of features is discuss ed. The assumption is that an area containing observable targets has differ ent statistics than other areas. Statistical properties along with detected target specific features have to be combined with methods used in data fus ion. An experiment with a dataset of 44 reference images has been carried o ut, using a recently developed computer program called Terrtex. High correl ation with perception experiments is achieved using only one or two texture features. The importance of a careful selection of background area size is finally discussed. (C) 2001 Society of Photo-optical instrumentation Engin eers.