Open AccessLogo Recognition with the Use of Deep Convolutional Neural Networks
Author(s) -
Ahmed A. Alsheikhy,
Yahia Said,
Mohammad Barr
Publication year - 2020
Publication title -
engineering, technology and applied science research/engineering, technology and applied science research
Language(s) - English
Resource type - Journals
eISSN - 2241-4487
pISSN - 1792-8036
DOI - 10.48084/etasr.3734
Subject(s) - computer science , logo (programming language) , convolutional neural network , artificial intelligence , cognitive neuroscience of visual object recognition , pattern recognition (psychology) , deep learning , object (grammar) , transfer of learning , overhead (engineering) , artificial neural network , programming language , operating system
Automatic logo recognition is gaining importance due to the increasing number of its applications. Unlike other object recognition tasks, logo recognition is more challenging because of the limited amount of the available original data. In this paper, the transfer leaning technique was applied to a Deep Convolutional Neural Network model to guarantee logo recognition using a small computational overhead. The proposed method was based on the Densely Connected Convolutional Networks (DenseNet). The experimental results show that for the FlickrLogos-32 logo recognition dataset, our proposed method performs comparably with state-of-the-art methods while using fewer parameters.