SOTAVerified

Real-time Document Localization in Natural Images by Recursive Application of a CNN.

2017-11-13ICDAR2017 2017Code Available0· sign in to hype

Khurram Javed, Faisal Shafait

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We propose a document segmentation algorithm that recursively uses convolutional neural networks to precisely localize a document in a natural image. The system can run in real-time on a mobile CPU, has minimal storage requirements, and achieves results comparable to the state of the art on the simple backgrounds and considerably better (Improving previous 86% to 94%) than the state of the art on the complex background of the "ICDAR 2015 SmartDoc Competition 1" dataset.

Tasks

Reproductions