An Efficient Detection and Classification Method for Landmine Types Based on IR Images Using Neural Network

---Infrared Image characteristics have some interesting capabilities that may assist in the detection of shallowly buried objects, in particular to help in the identification of landmine contaminated areas. This paper presents some preliminary results for the detection of buried Anti-Personnel Landmines (APLs) using an infrared imaging system. We describe an algorithm for the detection of landmine candidates by exploiting features in the images after extracting the object from background. Different threshold levels are applied to select groups of pixels that correspond to the object, and are the ones that could indicate a target position to the produced binary images. Unsupervised Self Organizing Map neural network was employed to differentiate among the land mines for better choice of the suitable removal method. Our test results approved more than 98% detection accuracy.