Audio copy-move tampering detection and positioning method and system based on multi-feature decision fusion
A technology of tampering detection and positioning method, applied in speech analysis, character and pattern recognition, instruments, etc., can solve the problem of inability to accurately locate the specific location of copy-move tampering, and achieve the effect of improving accuracy
Pending Publication Date: 2022-04-15
HEFEI UNIV OF TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] Aiming at the deficiencies of the prior art, the present invention provides an audio copy-move tampering detection and location method, system, storage medium and electronic equipment based on multi-feature decision-making fusion, which solves the problem that the prior art cannot accurately locate copy-move tampering location-specific technical questions
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0049] First Fangming, such as figure 1 As shown, the embodiment of the present invention provides an audio copy-move tampering detection and location method based on multi-feature decision fusion, including:
[0050] S1. Preprocessing the audio file to be tested, and obtaining all the voiced segments of the audio file to be tested;
[0051] S2. Using an energy entropy ratio method to segment each of the voiced segments into bytes;
[0052] S3. Calculate multiple typical features of each of the bytes, and compare the similarity of any two of the same typical features of the bytes until the pairwise comparison is completed, and obtain a complete similarity comparison result; the multiple A typical feature includes at least pitch frequency feature, color autocorrelation map feature and short-term energy feature;
[0053] S4. Fusing the complete similarity comparison results to complete copy-move tampering detection and positioning of the audio file to be tested.
[0054] First,...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides an audio copy-move tampering detection and positioning method and system based on multi-feature decision fusion, a storage medium and electronic equipment, and relates to the technical field of digital audio. The method comprises the following steps: calculating a plurality of typical features of each byte in a video to be detected, and comparing the similarity of the same typical features of any two bytes until every two bytes are compared, thereby obtaining a complete similarity comparison result; the typical features at least comprise a fundamental tone frequency feature, a color autocorrelation graph feature and a short-time energy feature, that is, the most typical features are extracted from three different domains, namely, a frequency domain, a space domain and a time domain, so that the detection accuracy of a single feature can be ensured to a certain extent; the complete similarity comparison result is fused, copy-move tampering detection and positioning of the audio file to be detected are completed, the positioning accuracy can be further improved based on multi-feature decision fusion, and the specific tampering position can be accurately positioned.
Description
technical field [0001] The invention relates to the technical field of digital audio, in particular to an audio copy-move tampering detection and location method, system, storage medium and electronic equipment based on multi-feature decision fusion. Background technique [0002] With the popularity of a variety of powerful audio editing software, even ordinary users without professional knowledge can easily edit or even maliciously tamper with digital audio files, which brings great challenges to the authenticity of digital audio. challenge. Among them, copy-move tampering is to copy and paste some regions in the same audio to other parts, so as to realize the semantic tampering of audio. [0003] For copy-move tampering detection, the current mainstream methods are mostly based on voice activity detection (VAD) technology, which aims to distinguish voiced segments and silent segments from complex voice signals, and determine the starting position of each voiced segment ,...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G10L25/51G06K9/62
Inventor 张国富苏兆品肖锐岳峰李孟珂陈佳乐
Owner HEFEI UNIV OF TECH