Systems and methods for deep learning based approach for content extraction
Disclosed are systems and methods for extracting content based on image analysis. A method may include receiving content including at least an image depicting a coupon; converting the received content into a larger image including the image depicting the coupon; determining, utilizing one or more neural networks, the image depicting the coupon within the larger image, wherein determining the image depicting the coupon comprises: segmenting a foreground bounding box including the image depicting the coupon from background image portions of the image; cropping the larger image based on the bounding box, wherein the cropped image consists of the image depicting the coupon; determining text included in the cropped image; and extracting information included in the coupon based on the determined text.
1. A computer-implemented method comprising:
receiving content including at least one image of an object;
determining, utilizing one or more neural networks, a cropping of the image, wherein the cropped image includes a depiction of the object;
determining text included in the cropped image;
extracting information based on the determined text; and
displaying the extracted information.
2. The computer-implemented method of claim 1 , wherein the at least one image comprises text and/or one or more images regarding a product and/or service.
3. The computer-implemented method of claim 1 , wherein determining text included in the cropped image comprises:
utilizing a detection engine to determine text included in the cropped image; and
utilizing a classification engine to classify the determined text.
4. The computer-implemented method of claim 1 , wherein extracting information based on the determined text comprises:
detecting one or more predetermined words among the determined text; and
assigning a tag for each detected predetermined word, wherein the tag indicates a classification for a word.
5. The computer-implemented method of claim 4 , wherein extracting information based on the determined text further comprises:
concatenating one or more detected predetermined words based on the assigned tags for each of the one or more detected predetermined words.
6. The computer-implemented method of claim 1 , further comprising
displaying the extracted information included in the image.
7. The computer-implemented method of claim 1 , wherein the content is received in a HyperText Markup Language (HTML) format.
8. A computer system comprising:
at least one memory having processor-readable instructions stored therein; and
at least one processor configured to access the memory and execute the processor-readable instructions to perform a method including:
receiving content including at least one image of an object;
determining, utilizing one or more neural networks, a cropping of the image, wherein the cropped image includes a depiction of the object;
determining text included in the cropped image;
extracting information based on the determined text; and
displaying the extracted information.
9. The computer system of claim 8 , wherein the image comprises text and/or one or more images regarding a product and/or service.
10. The computer system of claim 8 , wherein determining text included in the cropped image comprises:
utilizing a detection engine to determine text included in the cropped image; and
utilizing a classification engine to classify the determined text.
11. The computer system of claim 8 , wherein extracting information included based on the determined text comprises:
detecting one or more predetermined words among the determined text; and
assigning a tag for each detected predetermined word, wherein the tag indicates a classification for a word.
12. The computer system of claim 11 , wherein extracting information based on the determined text further comprises:
concatenating one or more detected predetermined words based on the assigned tags for each of the one or more detected predetermined words.
13. The computer system of claim 8 , further comprising
displaying the extracted information with the image.
14. The computer system of claim 8 , wherein the content is received in a HyperText Markup Language (HTML) format.
15. A non-transitory computer-readable medium containing instructions that, when executed by a processor, cause the processor to perform a method comprising:
receiving content including at least one image of an object;
determining, utilizing one or more neural networks, a cropping of the image, wherein the cropped image includes a depiction of the object;
determining text included in the cropped image;
extracting information based on the determined text; and
displaying the extracted information.
16. The non-transitory computer-readable medium of claim 15 , wherein the image comprises text and/or one or more images regarding a product and/or service.
17. The non-transitory computer-readable medium of claim 15 , wherein determining text included in the cropped image comprises:
utilizing a detection engine to determine text included in the cropped image; and
utilizing a classification engine to classify the determined text.
18. The non-transitory computer-readable medium of claim 15 , wherein extracting information based on the determined text comprises:
detecting one or more predetermined words among the determined text;
assigning a tag for each detected predetermined word, wherein the tag indicates a classification for a word; and
concatenating one or more detected predetermined words based on the assigned tags for each of the one or more detected predetermined words.
19. The non-transitory computer-readable medium of claim 15 , further comprising displaying the extracted information with the image.
20. The non-transitory computer-readable medium of claim 15 , wherein the content is received in a HyperText Markup Language (HTML) format.