Unlock instant, AI-driven research and patent intelligence for your innovation.

A kind of image discriminating device and discriminating method thereof

The technology of a discrimination method and a discrimination device is applied in the field of image processing, and can solve problems such as the inability to discriminate JPEG decompressed images and the inability to discriminate images I

Active Publication Date: 2017-01-11
深圳国信安信息技术有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, under normal circumstances, tampering cannot produce obvious differences visually, and existing technologies cannot distinguish JPEG decompressed images well, for example, image 3 As shown, when the image is uncompressed image I by P 1 ,P 2 Composition, P 1 is an uncompressed image, P 2 decompresses the image for JPEG, if P 2 When the compression quality QF=100 or 99, the prior art cannot distinguish the image I

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 kind of image discriminating device and discriminating method thereof
  • A kind of image discriminating device and discriminating method thereof
  • A kind of image discriminating device and discriminating method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0091] Randomly select a color image in uncompressed TIFF format from the UCID image database.

[0092] The first coefficient block set generating module of the image discrimination device cuts the selected image into 32×32 image blocks from the center. Carry out 8×8 blocks, divided into 16 sub-blocks, such as Figure 15 shown. It is found that the 8th and 12th sub-blocks contain a pixel value of 255. After the 8th and 12th sub-blocks are removed, the remaining 14 sub-blocks are sorted in the original order, and then DCT is performed to obtain the DCT coefficient value, such as Figure 16 shown.

[0093] The second coefficient block set generation module is for example Figure 16 The sub-blocks shown are rounded, and all sub-blocks with AC coefficients of zero in the obtained result are removed, and reordered, the following is obtained: Figure 17 The results shown.

[0094] The DCT quantization noise set generation module pairs Figure 17 Take the difference between the...

Embodiment 2

[0096] Randomly download a color image in JPEG format through the Internet, and perform the steps described in Example 1 again.

[0097] First, the image type discrimination and conversion module saves the JPEG image as a TIFF image and converts the TIFF image to a grayscale value. After the image is divided into blocks, the first coefficient block set generation module does not find any Sub-blocks of pixel values, then perform DCT transformation on all sub-blocks,

[0098] The second coefficient block set generating module processes the transformed sub-blocks, and reserves and reorders the sub-blocks 1, 6, 7, 12, 13, and 14 whose AC coefficients are not all zero.

[0099] The DCT quantization noise set generation module takes the difference between the DCT coefficient values ​​between the sorted sub-blocks, calculates the variance through the discrimination module, and obtains a variance value of and compared with the threshold, since less than the threshold T A , so it is...

Embodiment 3

[0101] The image discrimination device and method of the present invention are verified by converting from uncompressed to JPEG and back to uncompressed format.

[0102] Randomly select two TIFF format images TIF1 and TIF2 in the UCID image library, and compress them into JPEG images JPG1 and JPG2 with compression factors Q=99 and Q=100 respectively;

[0103] Decompress JPG1 and JPG2 back to TIFF format images respectively, save and check according to the steps described in Example 1. The final result is:

[0104] Variance value of TIF1 less than the threshold T A , so the image is a JPEG decompressed image. The judgment result is correct.

[0105] Variance value of TIF2 less than the threshold T A , so the image is a JPEG decompressed image. The judgment result is correct.

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 discloses an image discriminating device and method. The device comprises a first coefficient block set generating module, a second coefficient block set generating module, a DCT quantized noise set generating module and a discriminating module, wherein the first coefficient block set generating module is used for segmenting an image and removing subblocks with pixel values being 0 or 255, and DCT conversion is conducted to obtain a first coefficient block set; the second coefficient block set generating module is used for rounding DCT coefficient values in the first coefficient block set and removing all the subblocks with pixel values being 0, and then a second coefficient block set is formed; the DCT quantized noise set generating module is used for obtaining difference values between coefficient values at different positions in the first coefficient block set and the second coefficient block set, and then a DCT quantized noise set is formed; the discriminating module is used for calculating variance of coefficient values in the DCT quantized noise set, and the image is discriminated as a JEPG uncompressed image if the variance is lower than a threshold value. Whether a high-compression-quality image which can not be discriminated in the prior art is a JEPG uncompressed image can be effectively discriminated through the image discriminating device and method.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image discrimination device and a discrimination method for discriminating whether an image is a JPEG decompressed image. Background technique [0002] JPEG (Joint Photographic Experts Group) is an image format widely used in many occasions. It is widely used because of its easy storage and transmission. The JPEG image compression standard was first proposed in 1988 by the International Telecommunication Union (International Telecommunication Union, ITU), the International Organization for Standardization (ISO), and the International Electrotechnical Commission (International Electrotechnical Commission, IEC), and quickly gained popularity and application. The encoding and decoding process is as follows figure 1 and figure 2 As shown, the quantizer means to use a custom quantization step to remove 64 DCT (Discrete CosineTransform) transform coefficients, and then r...

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 Patents(China)
IPC IPC(8): H04N19/154H04N19/625H04N19/88H04N19/132
Inventor 李斌
Owner 深圳国信安信息技术有限公司