I love working in problems related to machine learning and computer vision.


  • A New U-Net based Enhancement Model for License Plate Detection in Night and Day Images
    Pinaki Nath Chowdhury, Palaiahnakote Shivakumara, Raghavendra Ramachandra, Umapada Pal, Tong Lu, and Michael Blumenstein
    Conference, Year

  • Handwritten Numeral String Recognition for Indian Scripts
    Hongjian Zhan, Pinaki Nath Chowdhury, Umapada Pal, and Yue Lu
    Conference, Year

  • ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition – RRC-MLT-2019
    Nibal Nayef, Yash Patel, Michal Busta, Pinaki Nath Chowdhury, Dimosthenis Karatzas, Wafa Khlif, Jiri Matas, Umapada Pal, Jean-Christophe Burie, Cheng-lin Liu, Jean-Marc Ogier

Research Projects

  • Doctor's Handwritten Offline Recognition
    Indian Statistical Institute, Kolkata, 2 years
    I am working with a team of senior researcher to build a system to read Doctor's Handwritten Prescription offline.

Research Implementations

  • PhocNet: A zero shot word spotting algorithm originally proposed by S Sudholt

  • MLT_OCR: This code extracts only the recogition of "E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text" by Michal Busta

  • Final Year Project (undergraduate): Includes implementation of boundary detection of nebulae or Supernova Remnants using KMeans(slightly modified for this project)