System and method for automated electronic catalogue management and electronic image quality assessment

1. A method comprising:

receiving a plurality of electronic images of an item;

identifying, via a processor configured to perform image analysis, and within each image in the plurality of images, the item;

performing, via the processor, a structural similarity analysis of the item, to yield a structural similarity score;

for each image in the plurality of images applying, via the processor, a plurality of distortions, such that for each image in the plurality of images a plurality of distorted images are generated;

identifying, via the processor, within the plurality of distorted images associated with each image in the plurality of images, at least one feature; and

applying, via the processor, a regression model to the plurality of images using the at least one feature and the structural similarity score.

2. The method of claim 1 , further comprising:

ordering, via the processor, the plurality of images based on applying the regression model to the plurality of images.

3. The method of claim 1 , wherein the plurality of distortions comprises a mean blur, a Gaussian blur, and a bilateral blur.

4. The method of claim 1 , wherein the regression model is a ridge regression.

5. The method of claim 1 , wherein the structural similarity identifies at least luminance, contrast, and structure of the item.

6. The method of claim 1 , wherein the plurality of images comprises a front image, a side image, and a back view of the item.

7. The method of claim 1 , further comprising: training a convolution neural network using the at least one feature, to yield a trained convolution neural network; and using the trained convolution neural network during the applying of the regression model to the plurality of images.

8. A system, comprising:

a processor configured to perform image analysis; and

a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:

receiving a plurality of electronic images of an item;

identifying, within each image in the plurality of images, the item;

performing a structural similarity analysis of the item, to yield a structural similarity score;

for each image in the plurality of images applying a plurality of distortions, such that for each image in the plurality of images a plurality of distorted images are generated;

identifying within the plurality of distorted images associated with each image in the plurality of images, at least one feature; and

applying a regression model to the plurality of images using the at least one feature and the structural similarity score.

9. The system of claim 8 , the computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:

ordering the plurality of images based on applying the regression model to the plurality of images.

10. The system of claim 8 , wherein the plurality of distortions comprises a mean blur, a Gaussian blur, and a bilateral blur.

11. The system of claim 8 , wherein the regression model is a ridge regression.

12. The system of claim 8 , wherein the structural similarity identifies at least luminance, contrast, and structure of the item.

13. The system of claim 8 , wherein the plurality of images comprises a front image, a side image, and a back view of the item.

14. The system of claim 8 , the computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:

training a convolution neural network using the at least one feature, to yield a trained convolution neural network; and

using the trained convolution neural network during the applying of the regression model to the plurality of images.

15. A non-transitory computer-readable storage medium having instructions stored which, when executed by a computing device configured to perform image processing, cause the computing device to perform operations comprising:

receiving a plurality of electronic images of an item; identifying, within each image in the plurality of images, the item;

performing a structural similarity analysis of the item, to yield a structural similarity score;

for each image in the plurality of images applying a plurality of distortions, such that for each image in the plurality of images a plurality of distorted images are generated;

identifying within the plurality of distorted images associated with each image in the plurality of images, at least one feature; and

applying a regression model to the plurality of images using the at least one feature and the structural similarity score.

16. The non-transitory computer-readable storage medium of claim 15 , having instructions stored which, when executed by the computing device, cause the computing device to perform operations comprising:

ordering the plurality of images based on applying the regression model to the plurality of images.

17. The non-transitory computer-readable storage medium of claim 15 , wherein the plurality of distortions comprises a mean blur, a Gaussian blur, and a bilateral blur.

18. The non-transitory computer-readable storage medium of claim 15 , wherein the regression model is a ridge regression.

19. The non-transitory computer-readable storage medium of claim 15 , wherein the structural similarity identifies at least luminance, contrast, and structure of the item.

20. The non-transitory computer-readable storage medium of claim 15 , wherein the plurality of images comprises a front image, a side image, and a back view of the item.