An image retrieval method and system
An image retrieval and image technology, applied in the field of image processing, can solve the problems of increased bandwidth overhead or space capacity overhead, lack of encryption protection, easy loss or damage, etc., to achieve the effect of reducing space complexity, small impact, and improving effectiveness
Active Publication Date: 2020-12-29
开易(北京)科技有限公司
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In terms of transmission and storage, these two marking methods increase bandwidth overhead or space capacity overhead on the one hand, and are easily lost or damaged on the other hand.
In addition, most of the marked information lacks encryption protection, and the marked information is not safe and easy to leak
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 Construction
[0042] like figure 1 As shown, the present invention provides an image retrieval method, comprising the following steps:
[0043] S101, encrypting the annotation information into ciphertext data and then embedding the original image, and using a reversible watermarking algorithm to use the replaced original pixels as a watermark to generate an annotation image;
[0044] Digital watermarking technology is a method to embed some identification information (ie watermark) into a digital carrier without affecting the use value of the original carrier. According to the robustness of digital watermarking against attacks, it can be divided into two categories: robust digital watermarking and vulnerable digital watermarking. According to the reversibility of digital watermarking, watermarking can be divided into two categories: reversible digital watermarking and irreversible digital watermarking. Among them, the reversible digital watermark requires that the watermark can not only b...
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 discloses an image retrieval method and system. The method comprises the steps that an original image is embedded after annotation information is encrypted into ciphertext data, and substituted original pixels are used as a watermark generation annotation image through a reversible watermarking algorithm; and the ciphertext data in the annotation image is extracted and decrypted, the decryption result is matched with retrieval conditions to acquire a target annotation image, a pixel value of the original image corresponding to the target annotation image is calculated, and a watermark is output after being extracted. The algorithm has a small influence on the original image, and the original image can be restored in one hundred percent at a receiving end; meanwhile, the algorithm is high in speed and adaptive to a large quantity of sample annotation scenes, so that space complexity is lowered; the encrypted annotation information is prevented from being tampered, and therefore the validity, relevancy and manageability of the annotation information are improved.
Description
technical field [0001] The invention belongs to the technical field of image processing, and in particular, relates to an image retrieval method and system. Background technique [0002] With the rapid development of information and communication technology, all kinds of image data have exploded exponentially. How to effectively manage the massive image data has become an urgent problem to be solved. With the development of pattern recognition and machine learning theories and algorithms, the automatic management of images has been realized to a certain extent. Currently, there are mainly two image management methods: image machine learning and traditional image annotation. Among them, the image machine learning technology mainly uses a large number of labeled samples to train a stable classification model to realize the detection, classification and recognition of a series of unknown images; while the traditional image annotation method creates an auxiliary file correspon...
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 Patents(China)
IPC IPC(8): G06T1/00
CPCG06T1/0021
Inventor 刘鹏张世亮
Owner 开易(北京)科技有限公司