Electronic apparatus for recognizing multimedia signal and operating method of the same

Patent metadata

Field	Value
Publication number	US-11468257-B2
Application number	US-202016898837-A
Country	US
Kind code	B2
Filing date	Jun 11, 2020
Priority date	Jun 13, 2019
Publication date	Oct 11, 2022
Grant date	Oct 11, 2022

Abstract

Disclosed are an electronic apparatus for recognizing a multimedia signal and an operating method of the electronic apparatus, including segmenting a detection signal into a plurality of frames; segmenting each of the frames into a plurality of blocks; and representing each of the blocks as a hash word based on a time feature and a frequency feature for each of the blocks.

First claim

What is claimed is:

1. An operating method of an electronic apparatus, the method comprising:
segmenting a multimedia signal detected through an input into a plurality of frames;
segmenting each of the frames into a plurality of blocks defined by a time axis and a frequency axis that intersects;
representing each of the blocks as a hash word based on a time feature and a frequency feature for each of the blocks; and
generating a fingerprint of the signal based on the hash words representing the blocks,
wherein the representing each of the blocks as the hash word comprises detecting the hash word based on a combination of a first time direction on the time axis and a first frequency direction on the frequency axis and a combination of a second time direction on the time axis and a second frequency direction on the frequency axis.

2. The method of claim 1 , wherein the time feature represents an energy distribution over time with respect to each of the blocks, and
the frequency feature represents an energy distribution over frequency with respect to each of the blocks.

3. The method of claim 1 , wherein the representing each of the blocks as the hash word further comprises:
detecting the hash word for each of the blocks based on a differential value calculated through the combination; and
representing each of the blocks as the detected hash word.

4. The method of claim 3 , wherein the detecting of the hash word comprises:
calculating a first differential value according to a first time direction of the time axis and a first frequency direction of the frequency axis;
calculating a second differential value according to a second time direction of the time axis and a second frequency direction of the frequency axis;
calculating a differential value by adding up the first differential value and the second differential value; and
detecting the hash word based on the differential value.

5. The method of claim 4 , wherein the detecting of the hash word further comprises calculating at least one of a third differential value and a fourth differential value, the calculating of the third differential value according to the first time direction and the second frequency direction, and the calculating the fourth differential value according to the second time direction and the first frequency direction.

6. The method of claim 5 , wherein the calculating of the differential value further comprises calculating the differential value by adding up at least one of the third differential value and the fourth differential value with the first differential value and the second differential value.

7. The method of claim 4 , wherein the detecting of the hash word based on the differential value comprises comparing the differential value and a threshold.

8. The method of claim 7 , wherein the threshold is determined as a differential value in a previous frame among the plurality of frames.

9. The method of claim 7 , wherein the detecting of the hash word comprises detecting the hash word as 1 if the differential value exceeds the threshold, and detecting the hash word as 0 if the differential value is less than or equal to the threshold.

10. An electronic apparatus comprising:
an input; and
processing circuitry configured to
segment a multimedia signal detected through the input into a plurality of frames,
segment each of the frames into a plurality of blocks defined by a time axis and a frequency axis that intersects, and
represent each of the blocks as a hash word based on a time feature and a frequency feature for each of the blocks, and
generate a fingerprint of the signal based on the hash words representing the blocks,
wherein the representing each of the blocks as the hash word comprises detecting the hash word based on a combination of a first time direction on the time axis and a first frequency direction on the frequency axis and a combination of a second time direction on the time axis and a second frequency direction on the frequency axis.

11. The electronic apparatus of claim 10 , wherein the time feature represents an energy distribution over time with respect to each of the blocks, and
the frequency feature represents an energy distribution over frequency with respect to each of the blocks.

12. The electronic apparatus of claim 10 , wherein the processing circuitry is further configured to detect the hash word for each of the blocks based on a differential value according to the combination.

13. The electronic apparatus of claim 12 , wherein the processing circuitry is further configured to
calculate a first differential value according to a first time direction of the time axis and a first frequency direction of the frequency axis,
calculate a second differential value according to a second time direction of the time axis and a second frequency direction of the frequency axis,
calculate a differential value by adding up the first differential value and the second differential value, and
detect the hash word based on the differential value.

14. The electronic apparatus of claim 13 , wherein the processing circuitry is further configured to
calculate at least one of a third differential value and a fourth differential value, the third differential value according to the first time direction and the second frequency direction and the fourth differential value according to the second time direction and the first frequency direction and
calculate the differential value by adding up at least one of the third differential value and the fourth differential value with the first differential value and the second differential value.

15. The electronic apparatus of claim 13 , wherein the processing circuitry is further configured to detect the hash word based on the differential value by comparing the differential value and a threshold.

16. The electronic apparatus of claim 15 , wherein the threshold is determined as a differential value in a previous frame among the plurality of frames.

17. The electronic apparatus of claim 15 , wherein the processing circuitry is further configured to detect the hash word as 1 if the differential value exceeds the threshold, and detect the hash word as 0 if the differential value is less than or equal to the threshold.

18. A non-transitory computer-readable storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform an operating method of an electronic apparatus, the method comprising:
segmenting a multimedia signal detected from an input into a plurality of frames;
segmenting each of the frames into a plurality of blocks defined by a time axis and a frequency axis that intersects; and
representing each of the blocks as a hash word based on a time feature and a frequency feature for each of the blocks; and
generating a fingerprint of the signal based on the hash words representing the blocks,
wherein the representing each of the blocks as the hash word comprises detecting the hash word based on a combination of a first time direction on the time axis and a first frequency direction on the frequency axis and a combination of a second time direction on the time axis and a second frequency direction on the frequency axis.

Assignees

• Naver Corp

Inventors

• Jeon Jisu
• Kim Dong Hwan
• Suh Dong Woo
• Kim Dae Hwang
• Park Jongeun

Classifications

• G06F16/41 Primary

  Indexing; Data structures therefor; Storage structures · CPC title

• G06F2218/16

  by matching signal segments · CPC title

• G06F2218/04

  Denoising · CPC title

• G06F2218/08

  Feature extraction · CPC title

• G06F16/783

  using metadata automatically derived from the content · CPC title