Face sketch recognition: an application of Z-numbers

To simulate the capability of human decision making with rationality on a machine is a quite difficult task. In the seminal line the automation of sketching of face involves computation of words and propositions based on human perceptions. It is this challenge that motivated us to apply the concept of ‘Sketching With Words’ or SWW. Moreover, the computerization of sketching of face is augmented by the involvement of uncertainty, in perception of human, e.g. ‘I am not quite sure, nose of criminal was fairly small’. A perception based natural language statements may be represented by a set of tuples. Simple examples of Z-valuations are: (he has small eyes, closed to 2.8 cm, very likely), (forehead of criminal, small, not sure), (his nose, about 2 in., quite sure). Since ‘Z-numbers’ provides a foundation for a theory that can simulate a wide variety of rational decision made by humans, without any measurements and computations and might be made by machines. Hence, ‘Z-numbers’ are used as a tool of automation of such type of task, where the decision making is influenced by perception, experience, and mental status of human being. Various geometric objects based on fuzzy geometry are used for drawing different parts of face. These fuzzy objects are drawn by using SWW technique. Since computation of SWW with Z-numbers may provide ability to build model of real life. Hence these two concepts are used in proposed work to draw the sketch of facial features of miscreant on the basis of perceptions of eyewitness.