IP Library Granted Patent US 9,277,148
Granted Patent B2
US 9,277,148 · App. 14/404,969 · Granted Mar 1, 2016

Maximizing perceptual quality and naturalness of captured images

Inventors: Alan Bovik (Austin, TX); Anush Moorthy (San Diego, CA)
Assignee: Board of Regents, The University of Texas System
H04N5/3572G06K9/00697G06K9/036G06T7/0002H04N5/23222G06T2207/20076G06T2207/30168
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,277,148
App. No.
14/404,969
Granted
Mar 1, 2016
Kind
B2
Abstract

A method, system and computer program product for improving the perceptual quality and naturalness of an image captured by an image acquisition device (e.g., digital camera). Statistical features of a scene being imaged by the image acquisition device are derived from models of natural images. These statistical features are measured and mapped onto the control parameters (e.g., exposure, ISO) of the digital acquisition device. By mapping these statistical features onto the control parameters, the perceptual quality and naturalness of the scene being imaged may be based on the values of these control parameters. As a result, these control parameters are modified to maximize the perceptual quality and naturalness of the scene being imaged. After modification of these control parameters, the image is captured by the image acquisition device. In this manner, the perceptual quality and naturalness of the image captured by the image acquisition device is improved.

Claims (50)

1. A method for improving a perceptual quality and naturalness of an image captured by an image acquisition device, the method comprising:

detecting a scene being imaged;

deriving statistical features of locally normalized luminance coefficients from said scene being imaged from a model of natural images with little or minimal distortion;

measuring said statistical features from said scene being imaged;

mapping said statistical features onto one or more control parameters of said image acquisition device; and

modifying, by a processor, said one or more control parameters of said image acquisition device to maximize said perceptual quality and naturalness of said scene being imaged.

2. The method as recited in claim 1 further comprising:

capturing said scene being imaged after said modification of said one or more control parameters of said image acquisition device.

3. The method as recited in claim 1 further comprising:

assessing said perceptual quality and naturalness of said scene being imaged.

4. The method as recited in claim 3 further comprising:

identifying a most significant distortion present in said scene being imaged in response to said assessed perceptual quality and naturalness of said scene being imaged being below a threshold; and

modifying one or more control parameters that caused said identified most significant distortion present in said scene being imaged in response to said assessed perceptual quality and naturalness of said scene being imaged being below said threshold.

5. The method as recited in claim 1 , wherein variations in said perceptual quality and naturalness of said scene being imaged change with one of said one or more control parameters, wherein said variations are measured against a statistical natural scene model, wherein a value of said one of said one or more control parameters is modified to correspond to a best fit of said statistical features of said scene being imaged to said statistical natural scene model which corresponds to a maximum perceptual quality and naturalness of said scene being imaged.

6. The method as recited in claim 1 , wherein said image acquisition device comprises one of the following: a digital camera and an imaging system coupled with a digital camera.

7. The method as recited in claim 1 , wherein said image acquisition device comprises one of the following: an x-ray system, a radiographic system, medical imaging modalities using ultrasound, magnetic resonance imaging and positron emission tomography.

8. A computer program product embodied in a non-transitory computer readable storage medium for improving a perceptual quality and naturalness of an image captured by an image acquisition device, the computer program product comprising the programming instructions for:

detecting a scene being imaged;

deriving statistical features of locally normalized luminance coefficients from said scene being imaged from a model of natural images with little or minimal distortion;

measuring said statistical features from said scene being imaged;

mapping said statistical features onto one or more control parameters of said image acquisition device; and

modifying said one or more control parameters of said image acquisition device to maximize said perceptual quality and naturalness of said scene being imaged.

9. The computer program product as recited in claim 8 further comprising the programming instructions for:

capturing said scene being imaged after said modification of said one or more control parameters of said image acquisition device.

10. The computer program product as recited in claim 8 further comprising the programming instructions for:

assessing said perceptual quality and naturalness of said scene being imaged.

11. The computer program product as recited in claim 10 further comprising the programming instructions for:

identifying a most significant distortion present in said scene being imaged in response to said assessed perceptual quality and naturalness of said scene being imaged being below a threshold; and

modifying one or more control parameters that caused said identified most significant distortion present in said scene being imaged in response to said assessed perceptual quality and naturalness of said scene being imaged being below said threshold.

12. The computer program product as recited in claim 8 , wherein variations in said perceptual quality and naturalness of said scene being imaged change with one of said one or more control parameters, wherein said variations are measured against a statistical natural scene model, wherein a value of said one of said one or more control parameters is modified to correspond to a best fit of said statistical features of said scene being imaged to said statistical natural scene model which corresponds to a maximum perceptual quality and naturalness of said scene being imaged.

13. The computer program product as recited in claim 8 , wherein said image acquisition device comprises one of the following: a digital camera and an imaging system coupled with a digital camera.

14. The computer program product as recited in claim 8 , wherein said image acquisition device comprises one of the following: an x-ray system, a radiographic system, medical imaging modalities using ultrasound, magnetic resonance imaging and positron emission tomography.

15. An image acquisition device, comprising:

a memory unit for storing a computer program for improving a perceptual quality and naturalness of an image captured by said image acquisition device; and

a processor coupled to said memory unit, wherein the processor is configured to execute the program instructions of the non-transitory computer program comprising:

detecting a scene being imaged;

deriving statistical features of locally normalized luminance coefficients from said scene being imaged from a model of natural images with little or minimal distortion;

measuring said statistical features from said scene being imaged;

mapping said statistical features onto one or more control parameters of said image acquisition device; and

modifying said one or more control parameters of said image acquisition device to maximize said perceptual quality and naturalness of said scene being imaged.

16. The image acquisition device as recited in claim 15 , wherein the program instructions of the computer program further comprise:

capturing said scene being imaged after said modification of said one or more control parameters of said image acquisition device.

17. The image acquisition device as recited in claim 15 , wherein the program instructions of the computer program further comprise:

assessing said perceptual quality and naturalness of said scene being imaged.

18. The image acquisition device as recited in claim 17 , wherein the program instructions of the computer program further comprise:

identifying a most significant distortion present in said scene being imaged in response to said assessed perceptual quality and naturalness of said scene being imaged being below a threshold; and

modifying one or more control parameters that caused said identified most significant distortion present in said scene being imaged in response to said assessed perceptual quality and naturalness of said scene being imaged being below said threshold.

19. The image acquisition device as recited in claim 15 , wherein variations in said perceptual quality and naturalness of said scene being imaged change with one of said one or more control parameters, wherein said variations are measured against a statistical natural scene model, wherein a value of said one of said one or more control parameters is modified to correspond to a best fit of said statistical features of said scene being imaged to said statistical natural scene model which corresponds to a maximum perceptual quality and naturalness of said scene being imaged.

20. The image acquisition device as recited in claim 15 , wherein said image acquisition device comprises one of the following: a digital camera and an imaging system coupled with a digital camera.

21. The image acquisition device as recited in claim 15 , wherein said image acquisition device comprises one of the following: an x-ray system, a radiographic system, medical imaging modalities using ultrasound, magnetic resonance imaging and positron emission tomography.

Assignments (3)
INSIDE THE ASSIGNMENT DOCUMENT. PREVIOUSLY RECORDED AT REEL: 034299 FRAME: 0877. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Feb 11, 2016
From: BOVIK, ALAN; MOORTHY, ANUSH
To: BOARD OF REGENTS, THE UNIVERSITY OF TEXAS SYSTEM
Reel/Frame 037782/0698 →
CONFIRMATORY LICENSE Recorded Feb 18, 2015
From: THE UNIVERSITY OF TEXAS AT AUSTIN
To: NATIONAL SCIENCE FOUNDATION
Reel/Frame 035021/0823 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 2, 2014
From: BOVIK, ALAN; MOORTHY, ANUSH
To: BOARD OF REGENTS, THE UNIVERSITY OF TEXAS SYSTEM
Reel/Frame 034299/0877 →
Continuity (2)
Provisional Application 61656075 · Jun 6, 2012
Related Publication 20150116548A1 · Apr 30, 2015