Open Access

ARTICLE

A Hybrid Deep Learning Architecture for the Classification of Superhero Fashion Products: An Application for Medical-Tech Classification

by Inzamam Mashood Nasir, Muhammad Attique Khan, Majed Alhaisoni, Tanzila Saba, Amjad Rehman, Tassawar Iqbal

1 Department of Computer Science, HITEC University, Taxila, Pakistan
2 College of Computer Science and Engineering, University of Ha’il, Ha’il, Saudi Arabia
3 College of Computer and Information Sciences, Prince Sultan University, Riyadh, Saudi Arabia
4 Department of Computer Science, COMSATS University Islamabad, Wah Campus, Islamabad, Pakistan

* Corresponding Author: Muhammad Attique Khan. Email:

(This article belongs to the Special Issue: Recent Advances on Deep Learning for Medical Signal Analysis (RADLMSA))

Computer Modeling in Engineering & Sciences 2020, 124(3), 1017-1033. https://doi.org/10.32604/cmes.2020.010943

Received 08 April 2020; Accepted 08 May 2020; Issue published 21 August 2020

Abstract

Comic character detection is becoming an exciting and growing research area in the domain of machine learning. In this regard, recently, many methods are proposed to provide adequate performance. However, most of these methods utilized the custom datasets, containing a few hundred images and fewer classes, to evaluate the performances of their models without comparing it, with some standard datasets. This article takes advantage of utilizing a standard publicly dataset taken from a competition, and proposes a generic data balancing technique for imbalanced dataset to enhance and enable the in-depth training of the CNN. In addition, to classify the superheroes efficiently, a custom 17-layer deep convolutional neural network is also proposed. The computed results achieved overall classification accuracy of 97.9% which is significantly superior to the accuracy of competition’s winner.

---

Keywords

---

Citations