Techniques for providing user image capture feedback for improved machine language translation

1. A computer-implemented method, comprising:

capturing, by a camera in electronic communication with a computing system having one or more processors, a first image of an object comprising a text in a source language;

receiving, at the computing system and from the camera, the first image;

performing, by the computing system, optical character recognition (OCR) on the first image to obtain an OCR text that is a machine-encoded text representation of the text;

in response to obtaining the OCR text, automatically obtaining, by the computing system and from a machine translation system, a first translated OCR text and a translation score indicative of a degree of likelihood that the first translated OCR text is an appropriate translation of the OCR text to a target language; and

when the translation score is less than a translation score threshold indicative of an acceptable degree of likelihood:

outputting, by the computing system, a user instruction to capture a set of second images of at least a portion of the object using the camera;

in response to outputting the user instruction, capturing, by the camera, the second set of images;

receiving, at the computing system and from the camera, the set of second images;

performing, by the computing system, OCR on at least one of the set of second images to obtain a modified OCR text corresponding to the text;

in response to obtaining the modified OCR text, obtaining, by the computing system and from the machine translation system, a second translated OCR text representing a translation of the modified OCR text from the source language to the target language; and

outputting, by the computing system, the second translated OCR text.

2. The computer-implemented method of claim 1 , further comprising: when the translation score is less than the translation score threshold, adjusting, by the computing system, an intensity of a light source while capturing the second set of images, the light source being in electronic communication with at least one of the camera and the computing system.

3. The computer-implemented method of claim 1 , further comprising: when the translation score is less than the translation score threshold, adjusting, by the computing system, a number of flashes of a light source camera while capturing the second set of images, the light source being in electronic communication with at least one of the camera and the computing system.

4. The computer-implemented method of claim 1 , further comprising:

when the translation score is less than the translation score threshold, identifying, by the computing system, a portion of the first image causing the OCR text and the corresponding first translated OCR text to have the translation score less than the translation score threshold, wherein the user instruction is to capture the set of second images with respect to the identified portion of the first image.

5. The computer-implemented method of claim 4 , wherein performing OCR on at least one of the set of second images to obtain a modified OCR text corresponding to the text comprises:

combining portions of at least two of the first image and the set of second images to obtain a combined image; and

performing OCR on the combined image to obtain the modified OCR text.

6. The computer-implemented method of claim 1 , wherein performing OCR on the first image to obtain the OCR text includes:

performing, by the computing system, OCR on the first image to obtain a set of possible OCR texts, wherein each possible OCR text has a corresponding OCR score indicative of a degree of likelihood that the possible OCR text is the text; and

selecting, by the computing system, the possible OCR text having a highest corresponding OCR score relative to the OCR scores of the other possible OCR texts to obtain the OCR text.

7. The computer-implemented method of claim 6 , further comprising when the translation score is less than the translation score threshold, selecting, by the computing system, another one of the possible OCR texts to obtain the modified OCR text.

8. The computer-implemented method of claim 7 , wherein the other one of the possible OCR texts has a second highest corresponding OCR score relative to the OCR scores of the other possible OCR texts.

9. The computer-implemented method of claim 1 , wherein the camera is a device that is distinct from the one or more processors and a display of the computing system.

10. The computer-implemented method of claim 1 , wherein the user instruction further instructs the user to position the camera at a particular position with respect to the object at least one of prior to and while capturing the second set of images.

11. The computer-implemented method of claim 10 , wherein the only interaction by the user after the user instruction is output and until the second translated OCR text is output includes the positioning of the camera at the particular position.

12. A computer-implemented method, comprising:

capturing, by a camera in electronic communication with a computing system having one or more processors, a first image of an object comprising a text in a source language;

receiving, at the computing system and from the camera, the first image;

performing, by the computing system, optical character recognition (OCR) on the first image to obtain a set of possible OCR texts, wherein each possible OCR text has a corresponding OCR score indicative of a degree of likelihood that the possible OCR text is the text;

selecting, by the computing system, the possible OCR text having a highest corresponding OCR score relative to the OCR scores of the other possible OCR texts to obtain an OCR text; and

when the OCR score of the OCR text is less than an OCR score threshold indicative of an acceptable degree of likelihood:

outputting, by the computing system, a user instruction to capture a set of second images of at least a portion of the object using the camera;

adjusting, by the computing system, an intensity of a light source while capturing, by the camera, the second set of images to increase a likelihood that an OCR score of a modified OCR text corresponding to the text and obtained from at least one of the second set of images will achieve the OCR score threshold, the light source being in electronic communication with at least one of the camera and the computing system;

receiving, at the computing system and from the camera, the set of second images;

performing, by the computing system, OCR on the at least one of the set of second images to obtain the modified OCR text; and

outputting, by the computing system, the modified OCR text.

13. The computer-implemented method of claim 12 , further comprising: when the OCR score is less than the OCR score threshold, adjusting, by the computing system, a number of flashes of the light source while capturing, by the camera, the second set of images to further increase the likelihood that the OCR score of the modified OCR text will achieve the OCR score threshold.

14. The computer-implemented method of claim 12 , further comprising:

when the OCR score is less than the OCR score threshold, identifying, by the computing system, a portion of the first image causing the OCR score to be less than the OCR score threshold, wherein the user instruction is to capture the set of second images with respect to the identified portion of the first image.

15. The computer-implemented method of claim 14 , wherein performing OCR on at least one of the set of second images to obtain a modified OCR text corresponding to the text comprises:

combining portions of at least two of the first image and the set of second images to obtain a combined image; and

performing OCR on the combined image to obtain the modified OCR text.

16. The computer-implemented method of claim 12 , further comprising when the OCR score is less than the OCR score threshold, selecting, by the computing system, another one of the possible OCR texts to obtain the modified OCR text.

17. The computer-implemented method of claim 16 , wherein the other one of the possible OCR texts has a second highest corresponding OCR score relative to the OCR scores of the other possible OCR texts.

18. The computer-implemented method of claim 12 , further comprising:

obtaining, by the computing system and from a machine translation system, a first translated OCR text and a translation score indicative of a degree of likelihood that the first translated OCR text is an appropriate translation of the OCR text to a target language; and

when the translation score is less than a translation score threshold indicative of an acceptable degree of likelihood, outputting, by the computing system, the user instruction to capture the set of second images of at least a portion of the object using the camera.

19. A computing system having one or more processors configured to perform operations comprising:

receiving, from a camera in electronic communication with the computing system, a first image of an object comprising a text in a source language, the first image having been captured by the camera;

performing optical character recognition (OCR) on the first image to obtain an OCR text that is a machine-encoded text representation of the text;

in response to obtaining the OCR text, automatically obtaining, from a machine translation system, a first translated OCR text and a translation score indicative of a degree of likelihood that the first translated OCR text is an appropriate translation of the OCR text to a target language; and

when the translation score is less than a translation score threshold indicative of an acceptable degree of likelihood:

outputting a user instruction to capture a set of second images of at least a portion of the object using the camera;

receiving, from the camera, the set of second images;

performing OCR on at least one of the set of second images to obtain a modified OCR text corresponding to the text;

in response to obtaining the modified OCR text, obtaining, from the machine translation system, a second translated OCR text representing a translation of the modified OCR text from the source language to the target language; and

outputting the second translated OCR text.

20. The computing system of claim 19 , wherein the operations further comprise: when the translation score is less than the translation score threshold, adjusting an intensity of a light source while capturing the second set of images, the light source being in electronic communication with at least one of the camera and the computing system.

21. The computing system of claim 19 , wherein the operations further comprise: when the translation score is less than the translation score threshold, adjusting a number of flashes of a light source while capturing the second set of images, the light source being in electronic communication with at least one of the camera and the computing system.

22. The computing system of claim 19 , wherein the operations further comprise:

when the translation score is less than the translation score threshold, identifying a portion of the first image causing the OCR text and the corresponding first translated OCR text to have the translation score less than the translation score threshold, wherein the user instruction is to capture the set of second images with respect to the identified portion of the first image.

23. The computing system of claim 22 , wherein performing OCR on at least one of the set of second images to obtain a modified OCR text corresponding to the text comprises:

combining portions of at least two of the first image and the set of second images to obtain a combined image; and

performing OCR on the combined image to obtain the modified OCR text.

24. The computing system of claim 19 , wherein performing OCR on the first image to obtain the OCR text includes:

performing OCR on the first image to obtain a set of possible OCR texts, wherein each possible OCR text has a corresponding OCR score indicative of a degree of likelihood that the possible OCR text is the text; and

selecting the possible OCR text having a highest corresponding OCR score relative to the OCR scores of the other possible OCR texts to obtain the OCR text.

25. The computing system of claim 24 , wherein the operations further comprise when the translation score is less than the translation score threshold, selecting, by the computing system, another one of the possible OCR texts to obtain the modified OCR text.

26. The computing system of claim 25 , wherein the other one of the possible OCR texts has a second highest corresponding OCR score relative to the OCR scores of the other possible OCR texts.

27. A computing system having one or more processors configured to perform operations comprising:

receiving, from a camera in electronic communication with the computing system, a first image of an object comprising a text in a source language, the first image having been captured by the camera;

performing optical character recognition (OCR) on the first image to obtain a set of possible OCR texts, wherein each possible OCR text has a corresponding OCR score indicative of a degree of likelihood that the possible OCR text is the text;

selecting the possible OCR text having a highest corresponding OCR score relative to the OCR scores of the other possible OCR texts to obtain an OCR text; and

when the OCR score of the OCR text is less than an OCR score threshold indicative of an acceptable degree of likelihood:

outputting a user instruction to capture a set of second images of at least a portion of the object using the camera;

adjusting a number of flashes of a light source while capturing, by the camera, the second set of images to increase a likelihood that an OCR score of a modified OCR text corresponding to the text and obtained from at least one of the second set of images will achieve the OCR score threshold, the light source being in electronic communication with at least one of the camera and the computing system;

receiving, from the camera, the set of second images;

performing OCR on the at least one of the set of second images to obtain the modified OCR text; and

outputting the modified OCR text.

28. The computing system of claim 27 , wherein the operations further comprise: when the OCR score is less than the OCR score threshold, adjusting an intensity of the light source while capturing, by the camera, the second set of images to further increase the likelihood that the OCR score of the modified OCR text will achieve the OCR score threshold.

29. The computing system of claim 27 , wherein the operations further comprise:

when the OCR score is less than the OCR score threshold, identifying a portion of the first image causing the OCR score to be less than the OCR score threshold, wherein the user instruction is to capture the set of second images with respect to the identified portion of the first image.

30. The computing system of claim 29 , wherein performing OCR on at least one of the set of second images to obtain a modified OCR text corresponding to the text comprises:

combining portions of at least two of the first image and the set of second images to obtain a combined image; and

performing OCR on the combined image to obtain the modified OCR text.

31. The computing system of claim 27 , wherein the operations further comprise when the OCR score is less than the OCR score threshold, selecting another one of the possible OCR texts to obtain the modified OCR text.

32. The computing system of claim 31 , wherein the other one of the possible OCR texts has a second highest corresponding OCR score relative to the OCR scores of the other possible OCR texts.

33. The computing system of claim 27 , wherein the operations further comprise:

obtaining, from a machine translation system, a first translated OCR text and a translation score indicative of a degree of likelihood that the first translated OCR text is an appropriate translation of the OCR text to a target language; and

when the translation score is less than a translation score threshold indicative of an acceptable degree of likelihood, outputting the user instruction to capture the set of second images of at least a portion of the object using the camera.