Algorithm for image retravel in the space of hash functions based on the deep neural network technologies

Authors: Zelenskiy A. A., Pismenskova M. M., Voronin V. V.

Annotation: This paper addresses the problem by novel technique for simultaneous learning of global image features and binary hash codes. Our approach provide mapping of pixel–based image representation to hash–value space simultaneously trying to save as much of semantic image content as possible. We use deep learning methodology to generate image description with properties of similarity preservation and statistical independence. The main advantage of our approach in contrast to existing is ability to fine–tune retrieval procedure for very specific application which allow us to provide better results in comparison to general techniques. The framework for data–dependent image presented in the paper hashing is based on use two different kinds of neural networks: convolutional neural networks for image description and autoencoder for feature to hash space mapping. Experimental results confirmed that our approach has shown promising results comparing to other state–of–the–art methods.

Keywords: content–based image retrieval, deep convolutional neural network, semantic hashing, autoencoder