Saliency detection based on hybrid artificial bee colony and firefly optimization

Abstract

Saliency detection is one of the challenging problems still tackled by image processing and computer vision research communities. Although not very numerous, recent studies reveal that optimization-based methods provide relatively accurate and fast solutions for such problems. This paper presents a novel unsupervised hybrid optimization method that aims to propose reasonable solution to saliency detection problem by combining the familiar artificial bee colony and firefly algorithms. The proposed method, HABCFA, is based on creating hybrid-personality individuals behaving like both bees and fireflies. A superpixel-based method is used to obtain better background intensity values in the saliency detection process, providing a better precision in extracting the salient regions. HABCFA algorithm is capable of achieving an optimum saliency map without requiring any extra mask or training step. HABCFA has produced superior performance against its basis algorithms, artificial bee colony, and firefly on four known benchmark problems regarding convergence rate and iteration count. On the other hand, the experimental results on four commonly used datasets, including MSRA-1000, ECSSD, ICOSEG, and DUTOMRON, demonstrate that HABCFA is adequately robust and effective in terms of accuracy, precision, and speed in comparison with the eleven state-of-the-art methods.