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

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.