Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A non-uniform fingerprint extraction and comparison method for camera light response based on combined feature representation

A technology of non-uniformity and combined features, applied in the field of computer vision, can solve the problems of unfavorable video fingerprint real-time extraction, high algorithm complexity, high resource occupation rate, etc., to improve detection efficiency and detection accuracy, algorithm complexity is small, The effect of high space occupancy

Active Publication Date: 2019-02-22
SHANDONG UNIV
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this patent has a high algorithm complexity when extracting video fingerprints. For a single frame of video, processing the entire image has a high resource occupation rate, which is not conducive to real-time extraction of video fingerprints.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A non-uniform fingerprint extraction and comparison method for camera light response based on combined feature representation
  • A non-uniform fingerprint extraction and comparison method for camera light response based on combined feature representation
  • A non-uniform fingerprint extraction and comparison method for camera light response based on combined feature representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0091] A camera light response non-uniformity fingerprint extraction and comparison method based on combined feature representation, such as figure 1 As shown, the specific steps are as follows:

[0092] (1) Perform image preprocessing on the input image;

[0093] (2) Detect the saturation, chroma, brightness, texture area, edge area and flat area of ​​the input image, and use the detected corresponding feature area as a candidate area for camera photoresponse non-uniformity fingerprint extraction;

[0094] (3) According to the candidate area, the input image is cut into M*M size color patches (patch), the value of M is not greater than the value of the original image pixel (or resolution), and these color patches are evenly extracted , divided into 6 subsets; here the 6 subsets are six subsets of saturation, chroma, brightness, texture area, edge area and flat area;

[0095] M=32 or M=64 or M=128.

[0096] (4) Send the color blocks in each subset to the residual network (R...

Embodiment 2

[0099] According to the method for extracting and comparing fingerprints of non-uniformity of camera photoresponse based on combined feature representation described in Embodiment 1, the difference is that:

[0100] In step (1), image preprocessing is carried out to the input image, including steps as follows:

[0101] A. Normalize the input image to form a unified standard format image; for example, uniformly zoom any input image into a JPG format image with a size of 4000*3000, where the zoom size needs to be greater than the color block size M;

[0102] B. Perform color space conversion on the image processed in step A, that is, convert from the original RGB color space to the HSI color space.

[0103] In step (2), detect input image saturation, chroma, brightness, texture area, edge area and flat area, as candidate area; Include steps as follows:

[0104] C. Set the input image P. For the input image P, first calculate the mean (mean) and standard deviation (standard devi...

Embodiment 3

[0151] A camera light response non-uniformity fingerprint extraction and comparison method based on combined feature representation, the specific steps are as follows:

[0152] (1) Carry out image preprocessing to input image; Include steps as follows:

[0153] A. Uniformly scale any input image into a JPG format image with a size of 3456*2592;

[0154] B. Perform color space conversion on the image processed in step A, that is, convert from the original RGB color space to the HSI color space.

[0155] (2) Detect the saturation, chroma, brightness, texture area, edge area and flat area of ​​the input image, and use the detected corresponding feature area as the candidate area for the camera photoresponse non-uniformity fingerprint extraction; the steps are as follows:

[0156] C. Set the input image P. For the input image P, first calculate the mean (mean) and standard deviation (standard deviation) of the pixel values, and the value range of the pixel values ​​is [0,255]:

...

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

No PUM Login to View More

Abstract

The invention relates to a non-uniform fingerprint extraction and comparison method for camera light response based on combined feature representation. Firstly, the input image is preprocessed such asnormalization, color space conversion and the like. Secondly, saturation, chrominance, brightness, edge region, texture region and flat region of the input image are detected as candidate regions ofinterest. Then, the image is cut into color blocks of specified size according to the above information, and these color blocks are divided into six subsets; Finally, the color blocks in six subsets are sent to the residual network respectively, and the non-uniform fingerprint of camera light response in each color block is extracted by depth learning method, and a fingerprint extraction system isformed by pre-training, which is used for source camera identification. The method has the advantages of uniqueness and good robustness, and can detect the non-uniformity fingerprint of camera lightresponse quickly and accurately, and is suitable for forensic identification, check anti-counterfeiting, image matching, information security and other fields.

Description

technical field [0001] The invention relates to a camera photoresponse non-uniformity fingerprint extraction and comparison method based on combined feature representation, which belongs to the technical field of computer vision. Background technique [0002] With the development of computer vision technology, the source camera recognition technology is getting more and more attention. More and more occasions use the source camera recognition technology to identify the source and authenticity of the image, such as criminal investigation identification, check anti-counterfeiting, image comparison, information security, etc. If the detection is performed directly on the original image, it will cause problems such as low accuracy, large amount of calculation, and slow detection speed. Therefore, the camera photoresponse non-uniformity fingerprint extraction based on deep learning has been widely used, and the key to its success is the effective selection of photoresponse non-un...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62
CPCG06V40/1347G06V40/1365G06V10/44G06F18/24G06F18/214
Inventor 杨阳闵永浩刘云霞
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products