A Novel Trademark Image Retrieval System Based on Multi-Feature Extraction and Deep Networks

Abstract

Graphical Search Engines are conceptually used in many development areas surrounding information retrieval systems that aim to provide a visual representation of results, typically associated with retrieving images relevant to one or more input images. Since the 1990s, efforts have been made to improve the result quality, be it through improved processing speeds or more efficient graphical processing techniques that generate accurate representations of images for comparison. While many systems achieve timely results by combining high-level features, they still struggle when dealing with large datasets and abstract images. Image datasets regarding industrial property are an example of an hurdle for typical image retrieval systems where the dimensions and characteristics of images make adequate comparison a difficult task. In this paper, we introduce an image retrieval system based on a multi-phase implementation of different deep learning and image processing techniques, designed to deliver highly accurate results regardless of dataset complexity and size. The proposed approach uses image signatures to provide a near exact representation of an image, with abstraction levels that allow the comparison with other signatures as a means to achieve a fully capable image comparison process. To overcome performance disadvantages related to multiple image searches due to the high complexity of image signatures, the proposed system incorporates a parallel processing block responsible for dealing with multi-image search scenarios. The system achieves the image retrieval through the use of a new similarity compound formula that accounts for all components of an image signature. The results shows that the developed approach performs image retrieval with high accuracy, showing that combining multiple image assets allows for more accurate comparisons across a broad spectrum of image typologies. The use of deep convolutional networks for feature extraction as a means of semantically describing more commonly encountered objects allows for the system to perform research with a degree of abstraction.