Evaluating image-text consistency without reference
Embodiments describing an approach to evaluate text and image consistency. Receiving one or more images. Receiving one or more text documents. Identifying relevant text in the one or more text documents. Determining the consistency between the one or more images and the one or more text documents. Creating one or more image and text consistency scores based on the determined consistency between the one or more images and the one or more text documents, and outputting the one or more image and text consistency scores for evaluating text and image consistency.
1. A method for evaluating text and image consistency, the method comprising:
receiving, by one or more processors, one or more images;
receiving, by the one or more processors, one or more text documents;
identifying, by the one or more processors, text in the one or more text documents;
determining, by the one or more processors, consistency between the one or more images and the one or more text documents;
creating, by the one or more processors, one or more image and text consistency scores based on the determined consistency between the one or more images and the one or more text documents;
outputting, by the one or more processors, the one or more image and text consistency scores for evaluating text and image consistency, wherein the one or more image and text consistency scores are displayed in a mathematical, alphabetical, and alphanumeric manner; and
outputting, by the one or more processors, inconsistency in errors in resolution and content mismatch between the one or more images and the one or more text documents.
2. The method of claim 1 further comprising:
identifying, by the one or more processors, one or more image attributes.
3. The method of claim 2 further comprising:
matching, by the one or more processors, the identified image attributes to a text label.
4. The method of claim 3 further comprising:
outputting, by the one or more processors, one or more labels for the identified image attributes.
5. The method of claim 1 further comprising:
analyzing, by the one or more processors, the one or more images and the one or more text documents, wherein the analysis comprises analyzing keywords in the text document and annotations on the one or more images.
6. The method of claim 1 , wherein the image attributes comprise: color, shape, texture, contour, depth, location, shading, tint, brightness, transparency, annotation location, annotation positions, sharpness, and annotation style.
7. The method of claim 5 , wherein the annotations comprise: arrows, colors, bold font, a text box, dotted lines, throbbing text, any shape known in the art, a thought cloud, a speech cloud, a footnote, a note, a reference number, captions, map legends, and text descriptions.
8. A computer program product for evaluating text and image consistency, the computer program product comprising:
one or more computer readable storage devices and program instructions stored on the one or more computer readable storage devices, the stored program instructions comprising:
program instructions to receive one or more images;
program instructions to receive one or more text documents;
program instructions to identify text in the one or more text documents;
program instructions to determine consistency between the one or more images and the one or more text documents;
program instructions to create one or more image and text consistency scores based on the determined consistency between the one or more images and the one or more text documents;
program instructions to output the one or more image and text consistency scores for evaluating text and image consistency, wherein the one or more image and text consistency scores are displayed in a mathematical, alphabetical, and alphanumeric manner; and
program instructions to output inconsistency in errors in resolution and content mismatch between the one or more images and the one or more text documents.
9. The computer program product of claim 8 further comprising:
program instructions to identify one or more image attributes.
10. The computer program product of claim 9 further comprising:
program instructions to match the identified image attributes to a text label.
11. The computer program product of claim 10 further comprising:
program instructions to output one or more labels for the identified image attributes.
12. The computer program product of claim 8 further comprising:
program instructions to analyze the one or more images and the one or more text documents, wherein the analysis comprises analyzing keywords in the text document and annotations on the one or more images.
13. The computer program product of claim 8 , wherein the image attributes comprise: color, shape, texture, contour, depth, location, shading, tint, brightness, transparency, annotation location, annotation positions, sharpness, and annotation style.
14. The computer program product of claim 12 , wherein the annotations comprise: arrows, colors, bold font, a text box, dotted lines, throbbing text, any shape known in the art, a thought cloud, a speech cloud, a footnote, a note, a reference number, captions, map legends, and text descriptions.
15. A computer system for evaluating text and image consistency, the computer system comprising:
one or more computer processors;
one or more computer readable storage devices;
program instructions stored on the one or more computer readable storage devices for execution by at least one of the one or more computer processors, the stored program instructions comprising:
program instructions to receive one or more images;
program instructions to receive one or more text documents;
program instructions to identify text in the one or more text documents;
program instructions to determine consistency between the one or more images and the one or more text documents;
program instructions to create one or more image and text consistency scores based on the determined consistency between the one or more images and the one or more text documents;
program instructions to output the one or more image and text consistency scores for evaluating text and image consistency, wherein the one or more image and text consistency scores are displayed in a mathematical, alphabetical, and alphanumeric manner;
program instructions to output inconsistency in errors in resolution and content mismatch between the one or more images and the one or more text documents.
16. The computer system of claim 15 further comprising:
program instructions to identify one or more image attributes.
17. The computer system of claim 16 further comprising:
program instructions to match the identified image attributes to a text label.
18. The computer system of claim 17 further comprising:
program instructions to output one or more labels for the identified image attributes.
19. The computer system of claim 15 further comprising:
program instructions to analyze the one or more images and the one or more text documents, wherein the analysis comprises analyzing keywords in the text document and annotations on the one or more images.
20. The computer system of claim 15 , wherein the image attributes comprise: color, shape, texture, contour, depth, location, shading, tint, brightness, transparency, annotation location, annotation positions, sharpness, and annotation style.