Research Of Interesting Target Detection Based On Integral Feature Congruency Model

Target detection is an important part of image processing and pattern recognition, and is widely used in the fields of military and civilian. It is always a hot research filed.A scheme of interesting target detection based on integral feature congruency model is studied in this paper. Generally, the abrupt changes of brightness or spatial frequency can be produced between interesting targets and backgrounds in a natural image. By detecting the abrupt changes, we can detect interesting target areas. In this paper, the local image information is obtained by logGabor filter banks, and is represented by a collection of separable features. The integral feature consists of some separable significant features. The integral feature congruence model (IFCM) is presented based on the integral feature. Then, we gain improved model by compensating noise. The interesting targets in natural backgrounds are detected based on this improved integral feature congruence model (IIFCM). Subsequently, by mathematical morphology and region labeling, we eliminate complex natural background disturbance and locate the interesting targets exactly. Experimental results show that the algorithm is effective in eliminating complex natural background disturbance and detecting interesting targets. This model is robust, general and accords with the human vision system (HVS) characteristics.