Deep CNN-based Features for Hand-Drawn Sketch Recognition via Transfer Learning Approach
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2019, Vol 10, Issue 9
Abstract
Image-based object recognition is a well-studied topic in the field of computer vision. Features extraction for hand-drawn sketch recognition and retrieval become increasingly popular among the computer vision researchers. Increasing use of touchscreens and portable devices raised the challenge for computer vision community to access the sketches more efficiently and effectively. In this article, a novel deep convolutional neural network-based (DCNN) framework for hand-drawn sketch recognition, which is composed of three well-known pre-trained DCNN architectures in the context of transfer learning with global average pooling (GAP) strategy is proposed. First, an augmented-variants of natural images was generated and sum-up with TU-Berlin sketch images to all its corresponding 250 sketch object categories. Second, the features maps were extracted by three asymmetry DCNN architectures namely, Visual Geometric Group Network (VGGNet), Residual Networks (ResNet) and Inception-v3 from input images. Finally, the distinct features maps were concatenated and the features reductions were carried out under GAP layer. The resulting feature vector was fed into the softmax classifier for sketch classification results. The performance of proposed framework is comprehensively evaluated on augmented-variants TU-Berlin sketch dataset for sketch classification and retrieval task. Experimental outcomes reveal that the proposed framework brings substantial improvements over the state-of-the-art methods for sketch classification and retrieval.
Authors and Affiliations
Shaukat Hayat, Kun She, Muhammad Mateen, Yao Yu
Keywords
Related Articles
- EP ID EP645867
- DOI 10.14569/IJACSA.2019.0100958
- Views 103
- Downloads 0
A Survey on Techniques to Detect Malicious Activites on Web
The world wide web is more vulnerable for malicious activities. Spam–advertisements, Sybil attacks, Rumour propagation, financial frauds, malware dissemination, and Sql injection are some of the malicious activities on w...
A Defeasible Logic-based Framework for Contextualizing Deployed Applications
In human to human communication, context increases the ability to convey ideas. However, in human to application and application to application communication, this property is difficult to attain. Context-awareness becom...
A Framework to Improve Communication and Reliability Between Cloud Consumer and Provider in the Cloud
Cloud services consumers demand reliable methods for choosing appropriate cloud service provider for their requirements. Number of cloud consumer is increasing day by day and so cloud providers, hence requirement for a c...
Implicit and Explicit Knowledge Mining of Crowdsourced Communities: Architectural and Technology Verdicts
The use of social media especially community Q&A Sites by software development community has been increased significantly in past few years. The ever mounting data on these Q&A Sites has open up new horizons for research...
Investigating the Idiotop Paratop Interaction in the Artificial Immune Networks
The artificial immune system is a new computational intelligence technique that has been investigated for the past decade. By reviewing the literature, two observations were found that could affect the network learning p...