IP Library › Granted Patent US 11,861,923
Granted Patent B2
US 11,861,923 · App. 17/566,817 · Granted Jan 2, 2024

Methods, apparatuses, and computer-readable storage media for image-based sensitive-text detection

Inventors: Zhiwei Shang (Waterloo, CA); Tongyu Ge (Waterloo, CA); Zhijun Mo (Waterloo, CA)
Assignee: HUAWEI TECHNOLOGIES CO., LTD.
G06V30/19093G06V30/12G06V30/164H04N1/448
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,861,923
App. No.
17/566,817
Granted
Jan 2, 2024
Kind
B2
Abstract

The present disclosure describes a method, an apparatus, and a non-transitory computer-readable medium for detecting sensitive text information such as privacy-related text information from a signal and modifying the signal by removing the detected sensitive text information therefrom. The apparatus receives the signal such as an image, a video clip, or an audio clip, and recognizes a text string therefrom. The apparatus then detects, from the text string, a substring based on a similarity between the substring and a regular expression, and modifies the signal by removing information related to the detected substring from the signal.

Claims (39)

1. A method comprising:

recognizing a text string from a signal;

detecting, from the text string, a substring of a sensitive-text type based on a similarity between the substring and a regular expression, the regular expression defining a pattern for searching a text string and finding substrings matching the pattern; and

modifying the signal by removing information related to the detected substring from the signal;

wherein said detecting the substring comprises:

detecting, from the text string, the substring if an edit distance between the substring and the regular expression is smaller than a predefined threshold.

2. The method of claim 1 , wherein the signal comprises an image, a frame of a video clip, or an audio clip.

3. The method of claim 1 further comprising:

processing the signal for correcting distortion to remove noise in the signal.

4. The method of claim 1 , wherein the detecting the substring further comprises:

verifying correctness of the detected substring.

5. The method of claim 1 , wherein the edit distance is a Levenshtein distance between the substring and the regular expression.

6. The method of claim 1 , wherein said detecting the substring comprises:

detecting, from the text string, the substring if a smallest Levenshtein distance between the substring and a final state in a Thompson's nondeterministic finite automaton (NFA) corresponding to the regular expression is smaller than the predefined threshold.

7. The method of claim 1 , wherein the regular expression corresponds to a predefined type of text.

8. An apparatus for executing instructions to perform actions comprising:

recognizing a text string from a signal;

detecting, from the text string, a substring of a sensitive-text type based on a similarity between the substring and a regular expression, the regular expression defining a pattern for searching a text string and finding substrings matching the pattern; and

modifying the signal by removing information related to the detected substring from the signal;

wherein said detecting the substring comprises:

detecting, from the text string, the substring if an edit distance between the substring and the regular expression is smaller than a predefined threshold.

9. The apparatus of claim 8 , wherein the signal comprises an image, a frame of a video clip, or an audio clip.

10. The apparatus of claim 8 , wherein the actions further comprise:

processing the signal for correcting distortion thereof and/or removing noise therein.

11. The apparatus of claim 8 , wherein the actions further comprise:

verifying correctness of the detected substring.

12. The apparatus of claim 8 , wherein the edit distance is a Levenshtein distance between the substring and the regular expression.

13. The apparatus of claim 8 , wherein said detecting the substring comprises:

detecting, from the text string, the substring if a smallest Levenshtein distance between the substring and a final state in a Thompson's nondeterministic finite automaton (NFA) corresponding to the regular expression is smaller than the predefined threshold.

14. The apparatus of claim 13 , wherein the regular expression corresponds to a predefined type of text.

15. A non-transitory computer-readable storage medium comprising computer-executable instructions, wherein the instructions, when executed, cause a processing structure to perform actions comprising:

recognizing a text string from a signal;

detecting, from the text string, a substring of a sensitive-text type based on a similarity between the substring and a regular expression, the regular expression defining a pattern for searching a text string and finding substrings matching the pattern; and

modifying the signal by removing information related to the detected substring from the signal;

wherein said detecting the substring comprises:

detecting, from the text string, the substring if an edit distance between the substring and the regular expression is smaller than a predefined threshold.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the edit distance is a Levenshtein distance between the substring and the regular expression.

17. The non-transitory computer-readable storage medium of claim 15 , wherein said detecting the substring comprises:

detecting, from the text string, the substring if a smallest Levenshtein distance between the substring and a final state in a Thompson's nondeterministic finite automaton (NFA) corresponding to the regular expression is smaller than the predefined threshold.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 4, 2023
From: SHANG, ZHIWEI; GE, TONGYU; MO, ZHIJUN
To: HUAWEI TECHNOLOGIES CO., LTD.
Reel/Frame 063219/0063 →
Continuity (1)
Related Publication 20230215202A1 · Jul 6, 2023
Cited By (2)
US 12,566,876 US 12,639,946