Generating preference indices for image content
Briefly, embodiments of methods and/or systems of generating preference indices for contiguous portions of digital images are disclosed. For one embodiment, as an example, parameters of a neural network may be developed to generate object labels for digital images. The developed parameters may be transferred to a neural network utilized to generate signal sample value levels corresponding to preference indices for contiguous portions of digital images.
1. A method, comprising:
transferring, to a second neural network associated with measuring a sentiment evocable towards a captured image upon display of the captured image to one or more users, parameters from a first neural network associated with identifying one or more object labels for the captured image via at least one transfer learning classifier; and
generating a term-independent preference index for a contiguous portion of an image using the second neural network to which the parameters from the first neural network associated with identifying the one or more object labels were transferred, wherein the term-independent preference index is indicative of both (i) a measurement of the sentiment evocable towards the captured image upon display of the captured image to one or more users and (ii) at least one of one or more qualities or one or more attributes likely to be perceived by one or more users as applying to the captured image; and
personalizing, by a processor, content to be displayed via a social network page or a blog using the term-independent preference index.
2. The method of claim 1 , wherein the term-independent preference index comprises a sentiment index.
3. The method of claim 1 , comprising using the term-independent preference index to assist in viral marketing.
4. The method of claim 1 , wherein the term-independent preference index is indicative of the one or more qualities perceivable by one or more users as applying to the captured image.
5. The method of claim 1 , wherein the term-independent preference index is indicative of the one or more attributes perceivable by one or more users as applying to the captured image.
6. The method of claim 1 , wherein the first neural network comprises a plurality of convolutional layers and a plurality of fully-connected layers.
7. The method of claim 1 , wherein the generating the term-independent preference index comprises generating the term-independent preference index via classification of signal samples generated by one or more convolutional layers of the second neural network.
8. The method of claim 7 , wherein the classification comprises classification via a machine learning process.
9. The method of claim 8 , wherein the first neural network comprises a plurality of convolutional layers and a plurality of fully-connected layers, wherein the machine learning process comprises a support vector machine process.
10. The method of claim 7 , wherein the first neural network comprises a plurality of convolutional layers and a plurality of fully-connected layers, wherein the classification comprises classification via a regression process.
11. An apparatus, comprising:
a processor; and
memory comprising processor-executable instructions that when executed by the processor cause performance of operations, the operations comprising:
transferring, to a second neural network associated with measuring a sentiment towards a captured image upon display of the captured image to one or more users, parameters from a first neural network associated with identifying one or more object labels for the captured image;
generating a term-independent preference index for a contiguous portion of an image using the second neural network to which the parameters from the first neural network associated with identifying the one or more object labels were transferred, wherein the term-independent preference index is indicative of both (i) a measurement of the sentiment towards the captured image upon display of the captured image to one or more users and (ii) at least one of one or more qualities or one or more attributes likely to be perceived by one or more users as applying to the captured image; and
personalizing content to be displayed via a social network page or a blog using the term-independent preference index.
12. The apparatus of claim 11 , the term-independent preference index comprises a sentiment index.
13. The apparatus of claim 11 , wherein the first neural network comprises a plurality of convolutional layers and a plurality of fully-connected layers, wherein the term-independent preference index comprises an odd number of allowed value levels.
14. The apparatus of claim 11 , wherein the second neural network comprises a deep convolutional neural network.
15. The apparatus of claim 11 , wherein the term-independent preference index is generated via classification of signal samples generated by one or more convolutional layers of the second neural network.
16. The apparatus of claim 11 , wherein the term-independent preference index is generated via classification of signal samples generated by one or more convolutional layers of the second neural network via a machine learning process.
17. A non-transitory computer-readable medium having stored thereon processor-executable instructions that when executed cause performance of operations, the operations comprising:
transferring, to a second neural network associated with measuring a sentiment evocable towards a captured image, parameters from a first neural network associated with identifying one or more object labels for the captured image;
generating a term-independent preference index for a contiguous portion of an image using the second neural network to which the parameters from the first neural network associated with identifying the one or more object labels were transferred, wherein the term-independent preference index is indicative of both (i) a measurement of the sentiment evocable towards the captured image and (ii) at least one of one or more qualities or one or more attributes likely to be perceived by one or more users as applying to the captured image; and
personalizing, by a processor, content to be displayed via a social network page or a blog using the term-independent preference index.
18. The non-transitory computer-readable medium of claim 17 , the operations comprising classifying signal samples generated by one or more convolutional layers.
19. The non-transitory computer-readable medium of claim 18 , wherein the classifying the signal samples comprises classifying via a machine learning process.
20. The non-transitory computer-readable medium of claim 17 , wherein the first neural network comprises a plurality of convolutional layers and a plurality of fully-connected layers, the operations comprising generating an odd number of allowed levels of the term-independent preference index.