A variant of learning vector quantizer based on the L2 mean for segmentation of ultrasonic images

The segmentation of ultrasonic images using self-organizing neural networks (NN) is investigated. A modification of learning vector quantizer (called L₂ LVQ) is proposed so that the weight vectors of the output neurons correspond to the L₂ mean instead of the sample arithmetic mean of the input observations. The convergence in the mean and in the mean square of the proposed variant of LVQ is studied. Experimental results show that L ₂ LVQ outperforms other segmentation techniques that employ thresholding a filtered ultrasonic image with respect to the probability of detection for the same probability of false alarm in all cases