Piyush Prasad
Research
Below is my published research work:
Natural Scene Text Localization Removal: Deep Learning and Navier Stokes Inpainting Approach
2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), 2021, pp. 1-5, doi: 10.1109/CONECCT52877.2021.9622609. A new algorithm is proposed that provides effective text removal from scenes, real world images containing text. It directly predicts and localizes scene text in any given image. Algorithm utilizes adaptive gaussian binary thresholding, text localization, dynamic masking and TELEA/NavierStokes Inpainting Algorithm. A number of examples on real world images containing scene text demonstrate the effectiveness of the algorithm in removing large as well as smaller detectable texts.
Pose Estimation and 3D Model Overlay in Real Time for Applications in Augmented Reality
Intelligent Systems. Springer, Singapore, 2021. 201-208. Pose estimation in real-time is a challenging research area with numerous applications. Obtaining detected key points in a given pose presents us with useful applications, one such application being in the Augmented Reality domain. This paper presents an approach to 3D model overlay on an image with pose keypoint information.
Back to Home