System For Text Restoration Using Mutual Information Based Radon Domain Regularization

Tufts University
posted on 09/02/2011

• request more info 
•   
•  LICENSE ONLINE

Tufts University Categories:
imaging:camera
optics

Additional Keywords:
(none specified)

Invention Summary

Background: There is an ever-increasing need to recognize text in an image in applications such as video surveillance. These applications require a device that can sense and capture an image. For example, a charge-coupled device (CCD) is included in many imaging devices, such as cell phones and security cameras. However, several problems may occur due to low resolution CCD devices, since text can become degraded by blurring due to the distance of the document from the imaging device, poor resolution due to insufficient sensor outputs from the imaging device, and uncorrelated noise from a variety of sources, including, but not limited to, noise due to sensor behavior in low light environments. These degradations may be so great as to render the text contained within the photograph illegible. Invention: This invention discloses a system that extracts from text from an image. The system includes a capture device that captures the image having a low resolution. An image segmentation subsystem partitions the image into image segments. An image restoration subsystem generates a resolution-expanded image from the image segments and negates degradation effects of the low-resolution image by transforming the image segments from a first domain to a second domain and deconvolving the transformed image segments in the second domain to determine parameters of the low-resolution image. A text recognition subsystem transforms the restored image data into computer readable text data based on the determined parameters.