Side scan sonar image segmentation and synthesis based on extreme learning machine

Abstract This paper presents side scan sonar (SSS) image segmentation and synthesis methods based on extreme learning machine (ELM). As an algorithm derived from single-hidden layer feedforward neural networks (SLFNs), ELM has superior performance and fast learning speed with randomly generated hidden layer parameters. The SSS image segmentation uses ELM as a classifier with features generated by convolutional neural network (CNN) of multiple pathways. The CNN of multiple pathways can learn local and global features from SSS images adaptively. Taking these features as input, ELM assigns the central pixel of each input image patch of CNN to one class. Moreover, the presented SSS image synthesis method utilizes ELM as a regression algorithm, in which the non-parametric sampling algorithm is used first to synthesize coarse SSS images according to segmentation maps and sample images for each class. Then ELM trained with the coarse synthesis images and their ground truth maps (the Gaussian-filtered SSS images) synthesizes fine SSS images. Furthermore, peak signal to noise ratio (PSNR) of the synthetic SSS images with the Gaussian-filtered SSS images as ref is used as one evaluation metric for segmentation performance. Experimental results demonstrate that the SSS image segmentation method combining convolutional features with ELM outperforms typical CNN and support vector machine (SVM), and the presented SSS image synthesis method and the evaluation metric are applicable.