saurabhshah0410

Google Summer of Code 2018 @ CCExtractor

Student Name: Saurabh Kumar M Shah

GSoC Project Proposal: Improve the OCR Subsystem

Email: saurabhshah.0410@gmail.com

Mentor: Abhinav Shukla

Project Synopsis:

The goal of my project was to make the hard subtitle extraction user friendly by making the subsystem independent of arbitrary user input parameters like sub_color, conf_thresh, luminance, whiteness etc. This would also extend CCExtractor's usage to extract burned in subtitles from video files containing multi color captions. The whole idea was to implement Neumann Mata's text detection algorithm which would meet the above objectives and also work with a reasonable time complexity and memory requirements.

saurabhshah0410

The Frobenius Number for small n

Formula for g(p,q):

Let p, q be non-negative relatively prime integers. Then, g(p,q) = pq-p-q.

A Formula for g(a₁,a₂,a₃)

Theorem:

Let A = {(a₁,a₂,a₃) ∈ N³ | a₁ < a₂ < a₃ , a₁ and a₂ are prime, and a₁, a₂ do not divide a₃}. Then there is no non-zero polynomial

saurabhshah0410

Improve the OCR subsytem for CCExtractor

Aim

To improve the OCR subsystem of CCExtractor.

Summary

When hard subtitles are extracted from a video, the results obtained are very poor in many cases. For example:

39
00:04:59,418 --> 00:05:00,383
‘ In America. there was lhll guy