Method for extracting a fingerprint data from video/audio signals

• US 8,548,192 B2
• Filed: 05/22/2008
• Issued: 10/01/2013
• Est. Priority Date: 05/22/2008
• Status: Active Grant

• Current Assignee: ZTE Corporation
• Original Assignee: Yuvad Technologies Co. Ltd
• Inventors: Zhang, Ji
• Primary Examiner(s): Carter, Aaron W
• Application Number:
  US12/085,764
• Publication Number:
  US 20100135521A1
• Time in Patent Office: 1,958 Days
• Field of Search: 382/100, 382/195, 382/305, 713/176, 725/19, 375240-241
• US Class Current: 382/100
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G06V 20/47 Detecting features for summarising video content

Abstract

A method for extracting a fingerprint data from video/audio signals, comprising the steps of sending a series of video frame images into a fingerprint extractor; extracting a fingerprint data through the fingerprint extractor; and storing the fingerprint data into a fingerprint database, characterized in that, in the fingerprint extractor, said method further comprises the sub-steps of storing the video frame images in a frame buffer which accepts a new video frame image and discards the oldest video frame image in a first in first out (FIFO) fashion; sampling the video images by a sub-sampler which operates on one video frame image at a time, so that the output of the sub-sampler contains data samples obtained from multiple video frame images while the video image content itself is discarded, and after each video frame image is sampled at the head of the frame buffer, it is discarded after the sampling; making the data samples to go through a divider which divides the data samples into groups of video frames so as to be organized as one fingerprint segment after another one; incorporating optional information by a formatter to the fingerprint segment so as to form the fingerprint data, at the output of the formatter, the video image content is discarded, only the fingerprint data and the associated optional information remain; and transferring the fingerprint data and the associated optional information by a transfer buffer to the fingerprint database. According to the present invention, the method for extracting a fingerprint data from video/audio signals facilitates the automatic identification, archiving and search of video content without the need for human visual inspections.

Claims

1. A method for extracting fingerprint data from video signals, comprising the steps of:

sending a plurality of video images into a fingerprint extractor;

extracting fingerprint data through the fingerprint extractor by performing further the steps of;

storing video images in a buffer;

sampling the video frame images by a sub-sampler which copies a plurality of pixel values from the video images in the buffer without any modification to the sampled pixel values, wherein the sampling comprises taking

a first sample at the center of the video frame image;

a second sample between the first sample and the left edge of the frame;

a third sample between the first sample and right edge of the frame;

a fourth sample between the first sample and the top edge of the frame;

a fifth sample between the first sample and the bottom edge of the frame;

organizing the plurality of data samples into a plurality of data units with one data unit corresponding to one video frame;

dividing the plurality of data units at data unit boundaries into groups of data units;

sequentially organizing the groups of data units as fingerprint segments with one fingerprint segment corresponding to each group of data units; and

incorporating auxiliary information by a formatter to the fingerprint segments to form the fingerprint data; and

transferring the fingerprint data by a transfer buffer to a fingerprint database.

2. The method according to claim 1, wherein the steps of storing video images in a buffer further comprise the steps of storing the video frames in a first-in-first-out (FIFO) fashion in that each time the latest video frame is added to the buffer, the oldest video frame is discarded from the buffer, and the number of frames in the buffer remain fixed.

3. The method according to claim 1, wherein multiple samples taken from a video frame are obtained on different locations within the frame.

4. The method according to claim 1, wherein a single pixel value is taken as a sample for each of the sample locations.

5. The method according to claim 4, wherein the same number of samples are taken for each of the video frames, and the samples are identically located on all of the video frames sampled.

6. The method according to claim 5, wherein the steps of sampling the video frame images further includes taking a plurality of samples of a frame substantially evenly distributed in the video frame.

7. The method according to claim 6, wherein the steps of sampling further includes taking a plurality of samples that remain invariant and proportional to each other even when the horizontal or vertical resolutions of the video image are changed.

8. The method according to claim 7, wherein the steps of sampling the video frame images by a sub-sampler further includes the steps of discarding a video frame data after the video has been sampled.

9. The method according to claim 8, wherein the image brightness pixel values are used as the samples.

10. The method according to claim 1, wherein:

the first sample is at an intersection of a first line at a distance of about ½

H from a top edge of the frame and a second line substantially perpendicular to the first line and at a distance of about ½

W from a left edge of the frame;

the second sample is at an intersection of the first line and a third line substantially perpendicular to the first line and at a distance of about ¼

W from the left edge;

the third sample is at an intersection of the first line and fourth line substantially perpendicular to the first line and at a distance of about ¾

W from the left edge;

the fourth sample is at an intersection of a fifth line substantially parallel to the first line and at a distance of about ¼

H from the top edge and the second line;

the fifth sample is at an intersection of a sixth line substantially parallel to the first line and at a distance of about ¾

H from the top edge and the second line; and

wherein H represents a height of the frame and W represents a width of the frame.

11. The method according to claim 10, wherein the step of taking a plurality of samples further includes taking:

a sixth sample at an intersection of the third line and the fifth line;

a seventh sample at an intersection of the third line and the sixth line;

an eighth sample at an intersection of the fourth line and the fifth line; and

a ninth sample at an intersection of the fourth line and the sixth line.