Software restores blurred images

Software restores blurred images

A Russian software engineer has developed a downloadable software tool that can be used to restore defocused and blurred images.

Restoration of distorted images is one of the most interesting and important problems of image processing - from the theoretical, as well as from the practical point of view.

For his part, Vladimir Yuzhikov -- who is currently working as an application developer at Deutsche Bank -- wanted to deal with the problem by developing code that corrects for blurring due to incorrect focus and movement.

Written in C++ using Qt 4.8 -- a development framework from Digia (Helsinki, Finland) with tools designed to streamline the creation of applications and user interfaces for desktop, embedded and mobile platforms – Yuzhikov’s SmartDeblur tool can correct for out of focus blur, motion blur and Gaussian blur.

Yuzhikov says that the software takes around 300msec to process an image of 2048 x 1500 pixels. But processing of larger images may take a few minutes.


To explain the principles behind the software, Yuzhikov has written an extensive technical article that can be found here. The article is also available in the Russian language here.

The latest source and binaries are available on GitHub here. All source files are under the GPL v3 license.

Recent articles on software development that you might also find of interest.

1. Researchers compare multicore programming methodologies

Researchers at the Department of Computer and Information Science at Linköping University (Linköping, Sweden) have recently evaluated the effectiveness of OpenCL for programming multicore CPUs in a comparative case study with OpenMP and Intel Threading Building Blocks.

2. New API aims to help developers of multiprocessor systems

Software engineers who develop code for embedded image processing systems are constantly looking for ways in which they can accelerate their applications using the latest breed of multicore processors.

3. MIT researchers develop new programming language for image processing

Researchers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL; Cambridge, MA, USA) aim to make writing image-processing algorithms easier with a new programming language called Halide.

http://www.vision-systems.com/articles/2012/08/mit-researchers-develop-new-programming-language-for-image-processing.html

Vision Systems Design magazine and e-newsletter subscriptions are free to qualified professionals. To subscribe, please complete the form here.


-- Dave Wilson, Senior Editor, Vision Systems Design



Get All the Vision Systems Design News Delivered to Your Inbox

Subscribe to Vision Systems Design Magazine or email newsletter today at no cost and receive the latest news and information.

 Subscribe Now

SPONSORED CONTENT

Webcasts

How the newest machine vision standards will affect you

How will the latest developments in machine vision standards affect you? This webcast will answer that question by featuring updates on relevant standards by some of the industry’s most knowledgeab...

How vision systems are changing automotive manufacturing

How do Ford and General Motors leverage machine vision for powertrain manufacturing? How does traditional vision application development serve today’s needs, and what machine vision capabilities co...
Date: June 24, 2015

High-speed imaging and the future of vision systems

What technologies are advancing high-speed imaging? What markets and applications are affected, and what can potential purchasers expect? In this live, interview-style webcast, Vision System Design...
Date: May 28, 2015

PRESS RELEASES

PROFINET® and Multi-Language Support Now Available with Microscan Link

October 9, 2013 Microscan Link connectivity provides vision engineers, programmers, and other users with an easy ...

Microscan’s AutoVISION™ 2.0 Wins 2013 Ringier Technology Innovation Award for Food and Beverage

August 8, 2013 Microscan, a global technology leader in barcode, machine vision and lighting solutions, announce...

Archives

Click here to view archived Vision Systems Design articles