Target extraction of banded blurred infrared images by immune dynamical algorithm with two-dimensional minimum distance immune field

Banded blurred Infrared image segmentation is a challenging topic since banded blurred infrared images are characterized by high noise, low contrast, and weak edges. Based on the interconnected and networked collaborative mechanism between innate immune factors and adaptive immune factors, this paper presents an immune dynamical algorithm with two-dimensional minimum distance immune field to solve this puzzle. Firstly, using the original characteristics as antigen surface molecular patterns, innate immune factors in the first layer of immune dynamical network extract banded blurred regions from the whole banded blurred infrared image region. Secondly, innate immune factors in the second layer of immune dynamical network extract new characteristics to design the complex of major histocompatibility complex (MHC) and antigen peptide. Lastly, adaptive immune factors in the last layer will extract object and background antigens from all the banded blurred image antigens, and design the optimal immune field of every adaptive immune factors. Experimental results on hand trace infrared images verified that the proposed algorithm could efficiently extract targets from images, and produce better extraction accuracy.