Image indexing systems

• US 7,245,824 B2
• Filed: 03/07/2001
• Issued: 07/17/2007
• Est. Priority Date: 03/07/2000
• Status: Expired due to Fees

• Current Assignee: Ian Fletcher
• Original Assignee: Ian Fletcher
• Inventors: Fletcher, Ian
• Primary Examiner(s): Stucker; Jeffrey
• Assistant Examiner(s): Chio; Tat Chi
• Application Number:
  US10/220,954
• Publication Number:
  US 20030147623A1
• Time in Patent Office: 2,323 Days
• Field of Search: 386/1, 386/45, 386 69- 70, 386/95, 386125-126, 348700-702, 3483971-3981, 3484201-4211
• US Class Current: 386/241
• CPC Class Codes: G06F 16/7847 using low-level visual features of the video content

Abstract

An image indexing system comprising a video frame store, an averager which provides a first signal indicative of the average brightness level of each frame stored, an image splitter and averager which divides each frame into contiguous blocks of pixels, and provides for each block, a second signal indicative of its average brightness level, a comparator which compares each of the second signals with the first signal so as to produce in respect of each block a binary signal indicative of whether or not its brightness level, as indicated by the first signal, is greater or less than the average brightness level for the frame as indicated by the first signal, thereby to produce for each frame, an index signal comprising one binary bit for each block which serves to identify each frame for indexing purposes.

Claims

1. An image indexing system comprising a video frame store, an averager which provides a first signal indicative of the average brightness level of each frame stored, an image splitter and averager which divides each frame into contiguous blocks of pixels, and provides for each block, a second signal indicative of its average brightness level, a comparator which compares each of the second signals with the first signal so as to produce in respect of each block a binary signal indicative of whether or not its brightness level, as indicated by the second signal, is greater or less than the average brightness level for the frame as indicated by the first signal, thereby to produce for each frame, an index signal comprising one binary bit for each block which serves to identify each frame for indexing purposes.

2. An image indexing system as claimed in claim 1, wherein data representative of an image is converted to monochrome using RGB averaging in order to provide monochrome data for the frame store.

3. An image indexing system as claimed in claim 2, wherein the overall average brightness level is computed for each frame by averaging the brightness level of all pixels which comprise the frame.

4. An image indexing system as claimed in claim 2, wherein the imager splitter operates to divide each frame into rows and columns of contiguous rectangular pixel blocks.

5. An image indexing system as claimed in claim 2 which forms a part of image identification apparatus and which additionally comprises a database in which the binary index for each of a plurality of images is stored and a further comparator wherein an index of an image to be identified as established by the image indexing system, is compared with indices stored in the database, thereby to provide an output signal when the index of the image to be identified corresponds to the index of a stored image, the output signal including data which identifies the stored image in respect of which correspondence obtains.

6. An image indexing system as claimed in claim 1, wherein the overall average brightness level is computed for each frame by averaging the brightness level of all pixels which comprise the frame.

7. An image indexing system as claimed in claim 6, wherein the imager splitter operates to divide each frame into rows and columns of contiguous rectangular pixel blocks.

8. An image indexing system as claimed in claim 6 which forms a part of image identification apparatus and which additionally comprises a database in which the binary index for each of a plurality of images is stored and a further comparator wherein an index of an image to be identified as established by the image indexing system, is compared with indices stored in the database, thereby to provide an output signal when the index of the image to be identified corresponds to the index of a stored image, the output signal including data which identifies the stored image in respect of which correspondence obtains.

9. An image indexing system as claimed in claim 1, wherein the imager splitter operates to divide each frame into rows and columns of contiguous rectangular pixel blocks.

10. An image indexing system as claimed in claim 9 which forms a part of image identification apparatus and which additionally comprises a database in which the binary index for each of a plurality of images is stored and a further comparator wherein an index of an image to be identified as established by the image indexing system, is compared with indices stored in the database, thereby to provide an output signal when the index of the image to be identified corresponds to the index of a stored image, the output signal including data which identifies the stored image in respect of which correspondence obtains.

11. An image indexing system as claimed in claim 1 which forms a part of image identification apparatus and which additionally comprises a database in which the binary index for each of a plurality of images is stored and a further comparator wherein an index of an image to be identified as established by the image indexing system, is compared with indices stored in the database, thereby to provide an output signal when the index of the image to be identified corresponds to the index of a stored image, the output signal including data which identifies the stored image in respect of which correspondence obtains.

12. An image indexing system as claimed in claim 11, wherein the output signal includes confidence level data derived in dependence upon the degree of correspondence which obtains between the index of an image to be identified and the indices of corresponding to stored images.

13. An image indexing system as claimed in claim 12, wherein the system includes a confidence level threshold detector whereby stored images are identified if a predetermined percentage match obtains between the index of a stored image and the index of an image to be identified.

14. An image indexing system as claimed in claim 11, wherein the system includes a confidence level threshold detector whereby stored images are identified if a predetermined percentage match obtains between the index of a stored image and the index of an image to be identified.