System for extracting a fingerprint data from video/audio signals

• US 8,488,835 B2
• Filed: 05/21/2008
• Issued: 07/16/2013
• Est. Priority Date: 05/21/2008
• Status: Active Grant

• Current Assignee: ZTE Corporation
• Original Assignee: Yuvad Technologies Co. Ltd
• Inventors: Zhang, Ji
• Primary Examiner(s): Carter, Aaron W
• Application Number:
  US12/085,834
• Publication Number:
  US 20100066759A1
• Time in Patent Office: 1,882 Days
• Field of Search: 382/100, 382/305, 375240-241, 725/19
• 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 20/48 Matching video sequences
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence
• CPC Class Codes: H04N 1/32144 embedded in the image data, i.e. enclosed or integrated in the image, e.g. watermark, super-imposed logo or stamp
• CPC Class Codes: H04N 21/44008 involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59

Abstract

A system for extracting a fingerprint data from video/audio signals, comprising a frame buffer for storing the video frame images, which accepts a new video frame image and discards the oldest video frame image in a first in first out (FIFO) fashion; a sub-sampler for sampling the video images, 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; a divider through which the data samples go, in order to divide the data samples into groups of video frames so as to be organized as one fingerprint segment after another one; a formatter which incorporates optional information to the fingerprint segment so as to form the fingerprint data, and at the output of the formatter, the video image content is discarded, only the fingerprint data and the associated optional information remain; and a transfer buffer which transfers the fingerprint data and the associated optional information by to the fingerprint database. According to the present invention, the system 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 system for extracting fingerprint data from digitized video images, comprising

a frame buffer for holding a plurality of digitized video images, which receives video images one image at a time by means of data transfers, and discards the oldest video image each time a new video image is added to the buffer, and

a sub-sampler which selectively copies pixel values of the video images without any modification to the values, and

a plurality of sub-sampler buffers which holds pixel values copied by sub-sampler, and each sub-sampler buffer holds the copied values from a single video image, and the number of sub-sampler buffers is the same as the number of video images in the frame buffer, and

a formatter which combines auxiliary information with the data from a plurality of sub-sampler buffers to form a single data package which is called fingerprint data, and

a transfer buffer which copies fingerprint data from the formatter to a database.

2. A system of claim 1, wherein said sub-sampler copies the luminance or brightness pixel values from the video images.

3. A system of claim 1, wherein said sub-sampler copies the pixel values from different locations of the frame image and the locations are spaced in proportion to the horizontal and vertical sizes of the frame image and form straight lines vertically and horizontally on the video images.

4. A system of claim 3, wherein the sub-sampler copies the pixel values from the same plurality of locations from each of the video images.

5. A system of claim 4, wherein the said sub-sampler copies nine pixel values from each video frame image as the following locations

the 1^st pixel is at the center of the image, which is half-way vertically and half-way horizontally in the image;

the 2^nd pixel is horizontally half-way between the first pixel and the left vertical edge of the image and at the same horizontal location as the first pixel;

the 3^rd pixel is horizontally half-way between the first pixel and the right vertical edge of the image and at the same horizontal location as the first pixel;

the 4^th pixel is vertically half-way between the first pixel and the top horizontal edge of the image and half-way horizontally in the image;

the 5^th pixel is vertically half-way between the first pixel and the top horizontal edge of the image and half-way horizontally between the fourth pixel and the left vertical edge of the image;

the 6^th pixel is vertically half-way between the first pixel and the top horizontal edge of the image and half-way horizontally between the fourth pixel and the right vertical edge of the image;

the 7^th pixel is vertically half-way between the first pixel and the bottom horizontal edge of the image and half-way horizontally in the image;

the 8^th pixel is vertically half-way between the first pixel and the bottom horizontal edge of the image and half-way horizontally between the seventh pixel and the left vertical edge of the image;

the 9^th pixel is vertically half-way between the first pixel and the bottom horizontal edge of the image and half-way horizontally between the seventh pixel and the right vertical edge of the image.