Detection of Landmines from Acoustic Images Based on Cepstral Coefficients

Abstract

This paper introduces a cepstral approach for the automatic detection of landmines from acoustic images. This approach is based on treating the problem of landmine detection as a pattern recognition problem. Cepstral features are extracted from a group of landmine images which are transformed first to 1-D signals by lexicographic ordering. Mel frequency cepstral coefficients (MFCCs) and polynomial shaping coefficients are extracted from these 1-D signals to form a database of features, which can be used to train a neural network with the landmine features. The landmine detection can be performed by extracting features from any new image with the same method used in the training phase. These features are tested with the neural network to decide whether a landmine exists or not. The different domains are tested and compared for efficient feature extraction from the lexicographically ordered 1-D signals. Experimental results show the success of the proposed cepstral approach for landmine detection at low as well as high signal to noise ratios. Results also show that the discrete cosine transform is the most appropriate domain for feature extraction.