Video processing system with text recognition and methods for use therewith

• US 9,600,725 B2
• Filed: 05/09/2012
• Issued: 03/21/2017
• Est. Priority Date: 04/18/2012
• Status: Active Grant

• Current Assignee: VIXS Systems Incorporated (Pixelworks Incorporated)
• Original Assignee: VIXS Systems Incorporated (Pixelworks Incorporated)
• Inventors: Li, Ying, Zhao, Xu Gang (Wilf)
• Primary Examiner(s): SOSANYA, OBAFEMI OLUDAYO
• Application Number:
  US13/467,630
• Publication Number:
  US 20130279572A1
• Time in Patent Office: 1,777 Days
• Field of Search: 375/240.08, 375/240.26
• US Class Current: 1/1
• CPC Class Codes: G06V 20/42 of sport video content
• CPC Class Codes: H04N 19/103 Selection of coding mode or of prediction mode
• CPC Class Codes: H04N 19/152 by measuring the fullness of the transmission buffer
• CPC Class Codes: H04N 19/167 Position within a video image, e.g. region of interest [ROI]
• CPC Class Codes: H04N 19/17 the unit being an image region, e.g. an object

Abstract

A system for processing a video signal into a processed video signal includes a pattern recognition module for detecting a region of text in the image sequence based on coding feedback data and generating pattern recognition data in response thereto. A video codec generates the processed video signal and generates the coding feedback data in conjunction with the processing of the image sequence.

Claims

1. A system for processing a video signal into a processed video signal, the video signal including an image sequence, the system comprising:

a pattern recognition module for detecting a region of text in the image sequence based on coding feedback data including edge detection data generated as an intermediate byproduct of;

a decoding of the video signal, an encoding of the video signal, or a transcoding of the video signal, and generating pattern recognition data in response thereto, wherein the coding feedback data further includes shot transition data that identifies temporal segments in the image sequence corresponding to a plurality of video shots and wherein the pattern recognition module generates a text string by recognizing the text in the region of text and further generates index data that includes the text string correlated to at least one of the plurality of video shots; and

a video codec, coupled to the pattern recognition module, that generates the processed video signal by processing the image sequence and by generating the coding feedback data including the edge detection data as the intermediate byproduct of;

the decoding of the video signal, the encoding of the video signal, or the transcoding of the video signal.

2. The system of claim 1 wherein the video codec includes an encoding section that generates the processed video signal by encoding the image sequence, wherein the pattern recognition data includes a location of the region of text and wherein the encoder section guides the encoding of the image sequence based on pattern recognition feedback that indicates presence of text in at least one image of the image sequence and indicates the location of the region of text.

3. The system of claim 1 wherein the pattern recognition module further generates index data that correlates the region of text to at least one of the plurality of video shots.

4. The system of claim 1 wherein the coding feedback data includes at least one image statistic.

5. The system of claim 1 wherein the coding feedback data includes motion vector data.

6. A method for encoding a video signal into a processed video signal, the video signal including an image sequence, the method comprising:

generating encoder feedback data including edge detection data generated as an intermediate byproduct of the encoding of the image sequence via an encoder section, wherein the encoder feedback data further includes shot transition data that identifies temporal segments in the image sequence corresponding to a plurality of video shots;

detecting a text region in the image sequence, based on the encoder feedback data;

generating pattern recognition data when the text region is detected, wherein the pattern recognition data indicates presence of the text region;

generating a text string by recognizing text in the region of text; and

generating index data that includes the text string and correlates the text string to at least one of the plurality of video shots.

7. The method of claim 6 wherein the pattern recognition data includes a location of the region of text and wherein the encoding of the image sequence is modified based on pattern recognition feedback that indicates presence of text in at least one image and indicates the location of the region of text.

8. The method of claim 6 further comprising:

generating index data that correlates the region of text to at least one of the plurality of video shots.

9. The method of claim 6 wherein the encoder feedback data includes at least one image statistic.

10. The method of claim 6 wherein the encoder feedback data includes motion vector data.