Methods and apparatus relating to text items in images
View Patent ↗A method and an electronic device are provided for obtaining an image or a video frame, including applying to the image or the video frame, at least one image processing technique, scanning the image or the video frame, to identify a text item, determining an item type for the identified text item, and determining an action, corresponding to the item type.
1. A method performed by an electronic device, comprising:
obtaining an image;
applying to the image at least one image processing technique;
scanning the image to identify a text item;
determining an item type for the identified text item; and
determining an action, corresponding to the item type.
2. The method of claim 1 , further comprising:
displaying a user interface element, corresponding to the action;
receiving a selection of the user interface element; and
performing the action.
3. The method of claim 1 , wherein the at least one image processing technique comprises:
boosting contrast in the image, to bring out potential text items; and
drawing rectangles around the potential text items.
4. The method of claim 1 , wherein the at least one image processing technique comprises:
performing thresholding on the image, to bring out potential text items; and
drawing rectangles around the potential text items.
5. The method of claim 3 , further comprising:
determining boundaries for each of the rectangles; and
combining overlapping rectangles, to form larger rectangles.
6. The method of claim 3 , wherein the scanning of the image, comprises scanning the rectangles for any text items.
7. The method of claim 6 , further comprising:
assigning a confidence score to each scan; and
discarding any scans with a low confidence score.
8. The method of claim 7 , further comprising correcting any misspellings in the text items.
9. The method of claim 7 , further comprising discarding any text items that do not meet at least one predetermined criterion.
10. The method of claim 1 , wherein the image is obtained from a frame of a video.
11. An electronic device to perform an action based on scanned text, comprising:
a display; and
a processor configured to:
obtain an image;
apply to the image at least one image processing technique;
scan the image to identify a text item;
determine an item type for the identified text item; and
determine an action, corresponding to the item type.
12. The electronic device of claim 11 , wherein the processor is further configured to:
display a user interface element, corresponding to the action;
receive a selection of the user interface element; and
perform the action.
13. The electronic device of claim 11 , wherein the at least one image processing technique comprises:
boosting contrast in the image, to bring out potential text items; and
drawing rectangles around the potential text items.
14. The electronic device of claim 11 , wherein the at least one image processing technique comprises:
performing thresholding on the image, to bring out potential text items; and
drawing rectangles around the potential text items.
15. The electronic device of claim 13 , wherein the processor is further configured to:
determine boundaries for each of the rectangles; and
combine overlapping rectangles, to form larger rectangles.
16. The electronic device of claim 13 , wherein the scanning of the image, comprises scanning the rectangles for any text items.
17. The electronic device of claim 16 , wherein the processor is further configured to:
assign a confidence score to each scan; and
discard any scans with a low confidence score.
18. The electronic device of claim 16 , wherein the processor is further configured to correct any misspellings in the text items.
19. The electronic device of claim 16 , wherein the processor is further configured to discard any text items that do not meet at least one predetermined criterion.
20. The electronic device of claim 11 , wherein the image is obtained from a frame of a video.
21. A computer readable storage medium comprising computer executable instructions to perform an action based on scanned text, comprising:
obtaining an image;
applying to the image at least one image processing technique;
scanning the image to identify a text item;
determining an item type for the identified text item; and
determining an action, corresponding to the item type.