Learning-based framework for personalized image quality evaluation and optimization
A computer-implemented method for providing image quality optimization individualized for a user includes a computer receiving raw image data acquired from an image scanner and identifying one or more raw image quality features based on the raw image data. The computer automatically determines one or more target image quality features by applying one or more user preferences to the one or more raw image quality features. The computer also automatically determines one or more processing parameters based on the one or more target image quality features. The computer may then process the raw image data using the one or more processing parameters to yield an image.
1. A computer-implemented method for providing image quality optimization individualized for a user, the method comprising:
receiving, by a computer, raw image data acquired from an image scanner;
identifying, by the computer, one or more raw image quality features based on the raw image data;
using a first deep learning network to automatically determine one or more target image quality features based on the one or more raw image quality features, wherein the first deep learning network is trained based on past behavior of a user when operating the image scanner;
using a second deep learning network to automatically determine one or more processing parameters for processing the raw image data based on the one or more target image quality features;
processing the raw image data using the one or more processing parameters to yield an image.
2. The method of claim 1 , further comprising:
providing the image to the user in a feedback interface configured to allow the user to associate a preference indicator with the image.
3. The method of claim 2 , wherein the preference indicator is a binary tag set to one of an accept value or a reject value.
4. The method of claim 2 , wherein the preference indicator is a numerical value selected from a range of numerical values.
5. The method of claim 2 , wherein the feedback interface is further configured to identify one or more new image quality features based on the preference indicator and the method further comprises:
modifying the one or more target image quality features based on the one or more new image quality features.
6. The method of claim 1 , wherein the raw image data is an additional input to the first deep learning network.
7. The method of claim 1 , wherein the one or more raw image quality features are an additional input to the first deep learning network.
8. The method of claim 1 , wherein the first deep learning network is an artificial neural network.
9. An article of manufacture for providing image quality optimization individualized for a user, the article of manufacture comprising a non-transitory, tangible computer-readable medium holding computer-executable instructions for performing a method comprising:
receiving raw image data acquired from an image scanner;
identifying one or more raw image quality features based on the raw image data;
using a first deep learning network to automatically determine one or more target image quality features based on the one or more raw image quality features, wherein the first deep learning network is trained based on past behavior of a user when operating the image scanner;
using a second deep learning network to automatically determine one or more processing parameters for processing the raw image data based on the one or more target image quality features; and
processing the raw image data using the one or more processing parameters to yield an image.
10. The article of manufacture of claim 9 , wherein the method further comprises:
providing the image to the user in a feedback interface configured to allow the user to associate a preference indicator with the image.
11. The article of manufacture of claim 10 , wherein the preference indicator is a binary tag set to one of an accept value or a reject value.
12. The article of manufacture of claim 10 , wherein the preference indicator is a numerical value selected from a range of numerical values.
13. The article of manufacture of claim 10 , wherein the feedback interface is further configured to identify one or more new image quality features based on the preference indicator and the method further comprises:
modifying the one or more target image quality features based on the one or more new image quality features.
14. The article of manufacture of claim 9 , wherein the raw image data is an additional input to the first deep learning network.
15. The article of manufacture of claim 9 , wherein the one or more raw image quality features are an additional input to the first deep learning network.
16. A system for providing image quality optimization individualized for a user, the system comprising:
an image scanner configured to acquire raw image data;
a computer comprising one or more processors configured to:
identify one or more raw image quality features based on the raw image data;
use a first deep learning network to automatically determine one or more target image quality features based on the one or more raw image quality features, wherein the first deep learning network is trained based on past behavior of a user when operating the image scanner;
use a second deep learning network to automatically determine one or more processing parameters for processing the raw image data based on the one or more target image quality features;
process the raw image data using the one or more processing parameters to yield an image.
17. The system of claim 16 , further comprising:
a feedback interface configured to present the image to the user and receive a preference indicator associated with the image from the user.
18. The system of claim 17 , wherein the one or more processors are further configured to modify the one or more user preferences based on the preference indicator.