Shuvendu Roy

Work place: Department of Computer Science and Engineering, Khulna University of Engineering & Technology, Bangladesh



Research Interests: Data Structures and Algorithms, Computer Vision, Computational Learning Theory, Artificial Intelligence, Computer systems and computational processes


Shuvendu Roy has completed his B.Sc in Computer Science and Engineering from Khulna University of Engineering & Technology, Khulna, Bangladesh. His current research interest includes using deep learning and artificial intelligence in Computer vision application and build a robust system that understand the view of the world for taking a complex decision.

Author Articles
Island Loss for Improving the Classification of Facial Attributes with Transfer Learning on Deep Convolutional Neural Network

By Shuvendu Roy

DOI:, Pub. Date: 8 Feb. 2020

Classification task on the human facial attribute is hard because of the similarities in between classes. For example, emotion classification and age estimation are two important applications. There are very little changes between the different emotions of a person and a different person has a different way of expressing the same emotion. Same for age classification. There is little difference between consecutive ages. Another problem is the image resolution. Small images contain less information and large image requires a large model and lots of data to train properly. To solve both of these problems this work proposes using transfer learning on a pre-trained model combining a custom loss function called Island Loss to reduce the intra-class variation and increase the inter-class variation. The experiments have shown impressive results on both of the application with this method and achieved higher accuracies compared to previous methods on several benchmark datasets.

[...] Read more.
Applying Aging Effect on Facial Image with Multi-domain Generative Adversarial Network

By Shuvendu Roy

DOI:, Pub. Date: 8 Dec. 2019

Face Aging is an important and challenging application in computer vision. This is an application of conditional image generation. Until recently generative model was not good enough to generate considerable good resolution images. A generative model called generative adversarial network has introduced impressive capabilities in generating realistic images in both unconditional and conditional settings. Still, the task of generating images of different age conditioning on a given image is a very challenging task. Because there are two constraints to satisfy here in the generated images. The generated image must preserve the identity of the person in the source image and the image must have the features of the target age. In this work, we have applied the generative adversarial network in conditional settings along with custom loss function to satisfy the two mentioned constraints. The experiment has shown improved performance both in preserving the person’s identity and classification accuracy of generated images in the target class compared to previous known approach to this problem. 

[...] Read more.
Other Articles