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

Image feature extraction algorithm

An image feature extraction and feature calculation technology, applied in computing, special data processing applications, instruments, etc., can solve the problems of large differences in image semantic understanding and high labor costs, and achieve the effect of avoiding subjectivity and reducing workload

Inactive Publication Date: 2019-06-25
南京信安融慧网络技术有限公司
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This technology has the following problems: each image needs manual labeling, and the labor cost is too high for the current massive image data; manual labeling is highly subjective, and different people have different views on the same image; The information is very rich and cannot be described with a small amount of words; it is difficult for different countries and different ethnic groups to use the same language to mark, and the understanding of image semantics varies greatly

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
  • Image feature extraction algorithm
  • Image feature extraction algorithm
  • Image feature extraction algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0031] figure 1 The operating structure of the application of the present invention is shown, and the characteristic information can be obtained by executing the modules in sequence.

[0032] Specifically include the following steps:

[0033] Step 1, for the image frame in the currently input image, obtain the width and height of the effective image area through the black edge detection module;

[0034] Step 2, repositioning the image, and obtaining a normalized image through the image size normalization module;

[0035] Step 3, for the normalized image, perform histogram equalization processing on each area in the input image through the histogram equalization module;

[0036] Step 4. Finally, gray gradients are obtained for multiple local regions of the image through the feature calculation module, and these gradient values ​​are combin...

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 feature extraction algorithm, and the algorithm specifically comprises the following steps: 1, obtaining the width and height of an effective image region through a black edge detection module for a picture frame in a current input image; 2, repositioning the image, and obtaining a normalized image through an image size normalization module; Step 3, for the normalized image, carrying out histogram equalization processing on each region in the input image through a histogram equalization module; And step 4, calculating the gray scale gradient of the image localarea through a feature calculation module to obtain image features. The method can be applied to calling of multiple videos and multiple threads, and rapid feature extraction is achieved.

Description

technical field [0001] The invention relates to a video retrieval method based on content information in the technical field of information security, and provides an image feature extraction algorithm. Background technique [0002] With the rapid development of digital audio-visual technology and network technology, digital images have become a widely used media form. Compared with text information, digital images are more vivid and are a highly independent information carrier, so they are used in various fields, such as digital libraries, news media, medical image management, satellite remote sensing, etc. [0003] However, the current digital equipment cannot effectively manage a large number of image databases. Users need to manage and query through specific classification and retrieval technologies. Therefore, establishing a fast and effective image retrieval system has become an important research direction. [0004] Image retrieval technologies mainly include text-bas...

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): G06F16/583
Inventor 石飞
Owner 南京信安融慧网络技术有限公司