Sep 23–26, 2019

Solmaz Torabi
Data Scientist, EXL

Solmaz Torabi is a data scientist at EXL, where she’s responsible for building image and text analytics models using deep learning methods to extract information from images and documents. She holds a PhD in electrical and computer engineering from Drexel University.

Sessions

1:15pm–1:55pm Wednesday, September 25, 2019

Location: 1A 06/07

Improving OCR quality of documents using generative adversarial networks

Data Science, Machine Learning, & AI

Secondary topics: Deep Learning, Financial Services, Health and Medicine

Nagendra Shishodia (EXL), Chaithanya Manda (EXL), Solmaz Torabi (EXL)

Every NLP-based document-processing solution depends on converting scanned documents and images to machine readable text using an OCR solution, limited by the quality of scanned images. Nagendra Shishodia, Chaithanya Manda, and Solmaz Torabi explore how GAN can bring significant efficiencies in any document-processing solution by enhancing resolution and denoising scanned images. Read more.