Attention-Net: An Ensemble Sketch Recognition Approach Using Vector Images

For the past few decades, machines have replaced humans in several disciplines. However, machine cognition still lags behind the human capabilities. We address the machines' ability to recognize human drawn sketches in this work. Visual representations, such as sketches have long been a medium...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on cognitive and developmental systems 2022-03, Vol.14 (1), p.136-145
Main Authors: Jain, Gaurav, Chopra, Shivang, Chopra, Suransh, Parihar, Anil Singh
Format: Article
Language:English
Subjects:
Attention mechanism and development
Cognition
Convolution
Feature extraction
Human performance
Image classification
Image recognition
Object recognition
Recurrent neural networks
sketch recognition
Sketches
Styling
Support vector machines
System effectiveness
Task analysis
temporal convolution network (TCN)
transformers
visual cognition
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:For the past few decades, machines have replaced humans in several disciplines. However, machine cognition still lags behind the human capabilities. We address the machines' ability to recognize human drawn sketches in this work. Visual representations, such as sketches have long been a medium of communication for humans. For artificially intelligent systems to effectively immerse in interactive environments, it is required that machines understand such notations. The abstract nature and varied artistic styling of these sketches make automatic recognition of drawings more challenging than other areas of image classification. In this article, we use sketches represented as a sequence of strokes, i.e., as vector images, to effectively capture the long-term temporal dependencies in hand-drawn sketches. The proposed approach combines the self-attention capabilities of Transformers while effectively utilizing the long-term temporal dependencies through temporal convolution networks (TCNs) for sketch recognition. The confidence scores obtained from the two techniques are combined using triangular-norm (T-norm). Attention heat maps are plotted to isolate the discriminating parts of a sketch that contribute to sketch classification. The extensive quantitative and qualitative evaluation confirms that the proposed network performs favorably against state-of-the-art techniques.
ISSN:2379-8920
2379-8939
DOI:10.1109/TCDS.2020.3023055