Complex Wavelets and SPIHTL for Edge Feature Enhancement and Optimum Feature Selection with Deep Learning Algorithm for Video Salient Object Detection

Abstract

Cognitive property of the human visual system to detect salient objects in image and video sequences to correlate with neighbouring objects for information retrieval and understanding is developed for computer vision application. Detecting salient objects with accurate boundaries and features is addressed in this work by using the directional selectivity property of complex wavelets. Computation complexity of processing complex wavelet sub band is addressed by companding the features into eight sub bands and optimum number of features are selected using SPIHTL (Set Partition In Hierarchical Trees List) algorithm. Five layered deep learning algorithm is designed with 2D FFNN ( Feed Forward Neural Network) structure and reordering units to detect salient object features. The 3D DTCWT (Dual Tree Complex Wavelet Transform) model combined with 2D SPIHTL encoder and deep learning algorithm is modelled in MATLAB and is trained to identify 120 objects with PSNR (Peak Signal To Noise Ration) of 40dB. The designed model is demonstrated to detect generic objects. Keywords: Video saliency, DTCWT, Directional Features, SPIHTL, Deep Learning, 2D Neural Network