System and method for extracting information from a non-planar surface

1. A method of extracting data from an image, comprising:

receiving images that capture a non-planar surface from different respective angles, wherein each of the images captures a section of an area on the non-planar surface, the area including textual or graphical information;

identifying low image quality sections corresponding to curved edges of the non-planar surface in the images;

cropping the images to remove the low image quality sections;

stitching together the images to obtain a stitched image that captures an entirety of the area on the non-planar surface;

processing the stitched image to extract the textual or graphical information from the area on the non-planar surface;

associating the textual or graphical information with one or more information fields in a report template; and

generating a report by populating the one or more information fields of the report template with corresponding associated information within the textual or graphical information.

2. The method of claim 1 , further comprising:

wherein receiving of the images includes receiving a sequence of images; and

down-sampling the sequence of images to obtain the images.

3. The method of claim 1 , wherein the stitching comprises:

detecting one or more features in the images;

matching the one or more features across at least two adjacent ones of the images; and

combining the images by aligning the one or more features to obtain the stitched image.

4. The method of claim 1 , wherein the stitching comprises one or more of:

correcting rotation mismatches across the images;

performing color normalization on the images; or

removing artifacts from the stitched image.

5. The method of claim 1 , wherein the processing of the stitched image to extract the textual or graphical information comprises:

binarizing the stitched image to obtain a black and white stitched image; and

performing optical character recognition “OCR” on the black and white stitched image to extract textual information from the area on the non-planar surface.

6. The method of claim 1 , wherein the processing of the stitched image to extract the textual or graphical information comprises:

performing object recognition or pattern recognition on the stitched image to extract graphical information from the area on the non-planar surface.

7. The method of claim 1 , wherein the non-planar surface comprises a curved surface of a cylindrical vessel, wherein the area corresponds to a rectangular label attached on the curved surface of the cylindrical vessel, wherein the report comprises an inspection report of the cylindrical vessel.

8. The method of claim 1 , wherein the receiving of the images further comprises obtaining by a camera of a portable computing device via an application executed on the portable computing device.

9. The method of claim 8 , further comprising:

determining to start the application based on a user input received through a user interface of the portable computing device; and

wherein the obtaining of the images further comprises obtaining by the application via accessing the camera in the portable computing device.

10. The method of claim 9 , further comprising:

determining to stop the application based on detecting an edge of the area on the non-planar surface.

11. The method of claim 1 , wherein the receiving of the images further comprises obtaining by security cameras installed in a corresponding area where an object comprising the non-planar surface is located.

12. The method of claim 11 , further comprising:

adjusting a position of at least one of the security cameras to achieve a field of view that includes the non-planar surface.

13. The method of claim 11 , further comprising:

obtaining a first image by one of the security cameras;

changing a setting of the one of the security cameras; and

obtaining a second image by the one of the security cameras, wherein the first image and the second image comprise different sections of the area on the non-planar surface.

14. The method of claim 11 , further comprising:

determining a trigger to obtain the images; and

initiating the security cameras to obtain the images in response to the trigger.

15. The method of claim 14 , wherein the trigger comprises a periodic inspection schedule or a user input received via a user interface of a central computing device in communication with the security cameras.

16. An apparatus comprising:

a processor; and

a memory storing instructions that when executed by the processor cause the processor to:

receive images capturing a non-planar surface from different respective angles, wherein each of the images captures a section of an area on the non-planar surface, the area including textual or graphical information;

identify low image quality sections corresponding to curved edges of the non-planar surface in each of the images;

crop each of the images to remove the low image quality sections;

stitch together the images to obtain a stitched image that captures an entirety of the area on the non-planar surface;

process the stitched image to extract the textual or graphical information from the area on the non-planar surface;

associate the textual or graphical information with one or more information fields in a report template; and

generate a report by populating the one or more information fields of the report template with corresponding associated information within the textual or graphical information.

17. A method of extracting data from an image, comprising:

receiving images that capture a non-planar surface from different respective angles, wherein each of the images captures a section of an area on the non-planar surface, the area including textual or graphical information;

identifying low image quality sections corresponding to curved edges of the non-planar surface in each of the images;

cropping each of the images to remove the low image quality sections;

stitching together the images to obtain a stitched image that captures an entirety of the area on the non-planar surface;

processing the stitched image to extract the textual or graphical information from the area on the non-planar surface; and

sending the textual or graphical information to a second device.

18. The method of claim 17 , wherein the second device comprises a cloud processing device or a central computing device.

19. A first device comprising:

a processor; and

a memory storing instructions that when executed by the processor cause the processor to:

receive images that capture a non-planar surface from different respective angles, wherein each of the images captures a section of an area on the non-planar surface, the area including textual or graphical information;

identify low image quality sections corresponding to curved edges of the non-planar surface in each of the images;

crop each of the images to remove the low image quality sections;

stitch together the images to obtain a stitched image that captures an entirety of the area on the non-planar surface;

process the stitched image to extract the textual or graphical information from the area on the non-planar surface; and

send the textual or graphical information to a second device.

20. A method of extracting data from an image, comprising:

receiving, by a first device, a stitched image from a second device, the stitched image capturing an entirety of an area on a non-planar surface, the stitched image being based on cropped images obtained by cropping images that capture the non-planar surface from different respective angles, wherein each of the images captures a section of the area on the non-planar surface, the area including textual or graphical information, wherein cropping the images crops low image quality sections corresponding to curved edges of the non-planar surface in each of the images;

processing the stitched image to extract the textual or graphical information from the area on the non-planar surface;

associating the textual or graphical information with one or more information fields in a report template; and

generating a report by populating the one or more information fields of the report template with corresponding associated information within the textual or graphical information.

21. The method of claim 20 , wherein the first device comprises a cloud processing device or a central computing device, wherein the second device comprises a portable computing device.

22. A first device comprising:

a processor; and

a memory storing instructions that when executed by the processor cause the processor to:

receive a stitched image from a second device, the stitched image capturing an entirety of an area on a non-planar surface, the stitched image being based on cropped images obtained by cropping images that capture the non-planar surface from different respective angles, wherein each of the images captures a section of the area on the non-planar surface, the area including textual or graphical information, wherein cropping the images crops low image quality sections corresponding to curved edges of the non-planar surface in each of the images;

process the stitched image to extract the textual or graphical information from the area on the non-planar surface;

associate the textual or graphical information with one or more information fields in a report template; and

generate a report by populating the one or more information fields of the report template with corresponding associated information within the textual or graphical information.