Identifying screenshots within document images
View Patent ↗Systems and methods for identifying screenshots within document images. An example method comprises: receiving an image of at least a part of a document; identifying, within the image, a polygonal object having a visually distinct border comprising a plurality of edges of one or more intersecting rectangles; asserting a screenshot image hypothesis with respect to the identified polygonal object; and responsive to evaluating at least one condition associated with one or more attributes of the identified polygonal object, classifying the identified polygonal object as a screenshot image.
1. A method comprising:
receiving an image of at least a part of a document;
performing optical character recognition of at least the part of the image based on a physical structure;
identifying, within the image, a polygonal object having a visually distinct border comprising a plurality of edges of one or more intersecting rectangles; and
responsive to evaluating at least one condition associated with one or more attributes of the identified polygonal object, classifying the identified polygonal object as a screenshot image.
2. The method of claim 1 , further comprising: asserting a classification hypothesis with respect to the identified polygonal object.
3. The method of claim 1 , wherein the polygonal object is provided by a rectangular object.
4. The method of claim 1 , wherein the border of the polygonal object comprises at least one visual separator provided by one of: a black separator, a gradient separator, or an inverse zone separator.
5. The method of claim 1 , wherein identifying the polygonal object comprises identifying at least three mutually perpendicular visual separators comprised by the visually distinct border.
6. The method of claim 1 , wherein evaluating the condition comprises identifying a window header element comprised by the polygonal object.
7. The method of claim 1 , wherein evaluating the condition comprises identifying, within the polygonal object, a background having at least one of: a color or a fill pattern that is different from a background of the image.
8. The method of claim 1 , wherein evaluating the condition comprises ascertaining that a ratio of a height of the polygonal object to a width of the polygonal object falls within a pre-defined range.
9. The method of claim 1 , wherein evaluating the condition comprises identifying a callout graphical element associated with the polygonal object.
10. The method of claim 1 , wherein evaluating the condition comprises identifying a plurality of grayscale items within the polygonal object.
11. The method of claim 1 , wherein evaluating the condition comprises identifying, within the polygonal object, a first text object having a first font size, wherein the first font size is less than a second font size of a second text object that is located outside of the polygonal object.
12. The method of claim 1 , wherein evaluating the condition comprises identifying, within the polygonal object, images of one or more graphical user interface (GUI) controls.
13. The method of claim 1 , further comprising: producing a physical structure of at least the part of the image, the physical structure comprising a definition of a screenshot associated with the polygonal object.
14. The method of claim 13 , further comprising:
performing optical character recognition of at least the part of the image based on the physical structure;
saving, using an image format, a portion of the image corresponding to the identified screenshot.
15. A computing device, comprising:
a memory;
a processor, coupled to the memory, the processor configured to:
receive an image of at least a part of a document;
performing optical character recognition of at least the part of the image based on a physical structure;
identify, within the image, a polygonal object having a visually distinct border comprising a plurality of edges of one or more intersecting rectangles; and
responsive to evaluating at least one condition associated with one or more attributes of the identified polygonal object, classify the identified polygonal object as a screenshot image.
16. The computing device of claim 15 , wherein the border of the polygonal object comprises at least one visual separator provided by one of: a black separator, a gradient separator, or an inverse zone separator.
17. The computing device of claim 15 , wherein evaluating the condition comprises identifying a window header element comprised by the polygonal object.
18. The computing device of claim 15 , wherein evaluating the condition comprises identifying, within the polygonal object, a background having at least one of: a color or a fill pattern that is different from a background of the image.
19. The computing device of claim 15 , wherein evaluating the condition comprises ascertaining that a ratio of a height of the polygonal object to a width of the polygonal object falls within a pre-defined range.
20. The computing device of claim 15 , wherein evaluating the condition comprises identifying a callout graphical element associated with the polygonal object.
21. The computing device of claim 15 , wherein evaluating the condition comprises identifying a plurality of grayscale items within the polygonal object.
22. The computing device of claim 15 , wherein evaluating the condition comprises identifying, within the polygonal object, a first text object having a first font size, wherein the first font size is less than a second font size of a second text object that is located outside of the polygonal object.
23. The computing device of claim 15 , wherein evaluating the condition comprises identifying, within the polygonal object, images of one or more graphical user interface (GUI) controls.
24. A computer-readable non-transitory storage medium comprising executable instructions that, when executed by a computing device, cause the computing device to perform operations comprising:
receiving an image of at least a part of a document;
performing optical character recognition of at least the part of the image based on a physical structure;
identifying, within the image, a polygonal object having a visually distinct border comprising a plurality of edges of one or more intersecting rectangles; and
responsive to evaluating at least one condition associated with one or more attributes of the identified polygonal object, classifying the identified polygonal object as a screenshot image.
25. The computer-readable non-transitory storage medium of claim 23 , further comprising executable instructions causing the computing device to: produce a physical structure of at least the part of the image, the physical structure comprising a definition of a screenshot associated with the polygonal object.