Removing Camera Shake from a Single Photograph


This technology has applications in a wide range of areas in the consumer electronics industry. Any device incorporating a digital camera would benefit from sufficiently robust deblurring methods, which would improve the quality of pictures taken by their users. It has potential applications for both the manufacturer, in the form of an onboard system, and the consumer, as a supplementary software. Furthermore, the technology has potential applications in the field of profession photography as a means to easily correct blurred pictures without the need for reshoots or intensive image retouching.

This technology would appeal primarily to companies that produce digital cameras as well as those that produce devices with integrated cameras, such as smartphones or tablets. If this system could be deployed on such devices, it would allow the manufacturer to boast higher image quality as a key selling point. Furthermore it would allow them to advertise their device as being the premier choice for capturing candid images.  In addition, companies that produce image retouching and editing software may find the deblurring system and techniques to be a useful addition to their platform. It has the potential to be integrated in some capacity into an existing photo-retouching software for consumer grade purposes, as well as be developed into a standalone professional-grade image editing software.

Problem Addressed

The wide adoption of portable consumer electronics has corresponded with an equally substantial adoption and usage of digital cameras, many of which are integrated into the devices themselves. But the increased portability and continual development of digital cameras comes with the unfortunate trade-off of vulnerability to image blur. The lightweight nature of the cameras makes them very prone to camera shake, which in turn may cause image blurring, resulting in ruined image quality or other negative impacts. Prior methods of deblurring were forced to make very general, broad assumptions about the pictures they were correcting, restricting their viability to instances of small, uncomplicated image blur. In addition, prior techniques also ran the routine risk of removing or obscuring spatial information in the image such as object edges. In order to improve the applicability of deblurring methods while preserving essential image aspects, a substantial methodological revision is required.


The technology herein describes a methodology and algorithm for removing blur effects from photographs affected by camera shake. This is achieved by creating a “blur kernel” for the affected picture, which is a model of the motion of the camera that caused the resultant blur. Due to the complexity and irregularity of the associated camera motion, the construction of the blur kernel requires a number of assumptions and estimations in order to be used as a suitable guide for deblurring. The methodology that guides the judgement of the necessary assumptions and estimations is what sets this technology apart from existing techniques.

In this case, the system makes use of two central methodological improvements to guide the construction of the blur kernel. First, the system takes advantage of recent research in image statistics that suggests pictures taken of natural scenes typically follow very specific distributions of image gradients. This serves as a very useful tool for estimation. Second, by analysis of distributions of probable images, the technique takes into account the uncertainties associated with the unknown camera movement. Once the blur kernel is constructed, it can be used with a standard deblurring algorithm to produce a corrected version of the desired picture. 


  • Can handle image blurs over a larger area than previous techniques
  • Preserves image spatial information such as edges
  • Makes use of more robust information for the purposes of estimation