Authors:
E. Ghodhbani
1
;
M. Kaaniche
2
and
A. Benazza-Benyahia
1
Affiliations:
1
University of Carthage SUP’COM, LR11TIC01, COSIM Lab., 2083, El Ghazala, Tunisia
;
2
Institut Galilée, L2TI, Université Sorbonne Paris Nord, France
Keyword(s):
Image Retrieval, Color Stereo Images, Disparity Maps, Deep Learning, Residual Neural Networks.
Abstract:
While recent stereo images retrieval techniques have been developed based mainly on statistical approaches, this work aims to investigate deep learning ones. More precisely, our contribution consists in designing a two-branch neural networks to extract deep features from the stereo pair. In this respect, a 3D residual network architecture is first employed to exploit the high correlation existing in the stereo pair. This 3D model is then combined with a 2D one applied to the disparity maps, resulting in deep feature representations of the texture information as well as the depth one. Our experiments, carried out on a large scale stereo image dataset, have shown the good performance of the proposed approach compared to the state-of-the-art methods.