Image sub-card processing method, device and image retrieval method, device and system

A card processing and image technology, which is used in electrical digital data processing, special data processing applications, character and pattern recognition, etc., can solve the problem of missed detection of similar images, and achieve the effect of overcoming the problem of missed detection and improving the recall rate.

Active Publication Date: 2018-12-11
FOSHAN GUOFANG TRADEMARK SERVICE CO LTD +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary for traditional image processing techniques to distinguish and store and record the relationship between relatively independent partial image regions that have different shapes and may have significant features in the image to be processed and the things or content they describe. The relatively independent part of the image area of ​​the salient features is converted into an image sub-card that can be directly used for image retrieval, which may easily lead to the problem of missed detection of similar images in image retrieval. An image sub-card processing method and device, and an image retrieval method and device are provided and system

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 sub-card processing method, device and image retrieval method, device and system
  • Image sub-card processing method, device and image retrieval method, device and system
  • Image sub-card processing method, device and image retrieval method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] In order to solve the problem that the traditional image processing technology is difficult to distinguish and store and record the relationship between relatively independent partial image areas that have different shapes and may have distinctive features in the image to be processed and the things or content described, it is impossible to distinguish the different shapes that may have distinctive features. The relatively independent part of the image area is converted into an image sub-card that can be directly used for image retrieval, which may easily lead to the problem of approximate image missing detection in image retrieval. The present invention provides an image sub-card processing method embodiment 1; figure 1 It is a schematic flow chart of Embodiment 1 of the image sub-card processing method of the present invention; as figure 1 As shown, the following steps may be included:

[0069] Step S110: Perform preprocessing on each sample image to obtain the correl...

Embodiment 2

[0136] In order to solve the problem that the traditional image processing technology cannot distinguish the independent part of the image area in the image to be processed, and based on the technical solution of the above-mentioned image card processing method embodiment 1, the present invention also provides an image card processing method embodiment 2 Compared with Embodiment 1 of the image splitting processing method embodiment 2 of the image splitting processing method, the color block segmentation processing of the image to be processed is further increased or refined into two steps, including: pixel classification of the image to be processed Preliminary processing of color blocks; according to the preset scatter point confirmation rules, correct the color blocks into which the pixel points of the image to be processed are classified, and perform color block segmentation processing on the image to be processed after correction, Figure 13 It is a schematic flow diagram o...

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 present invention relates to a processing method and device for image classification, and an image retrieval method, device and system, wherein the method for processing image classification includes the following steps: performing preprocessing on each sample image to obtain the relationship between each sample image and known information The association relationship of the image to be processed is performed on the color block segmentation process to obtain the segmented color block image of the image to be processed; the pixel point groups with interconnected relationships in the segmented color block image are marked and re-segmented to obtain the segmented color block image Each connected domain diagram of the color block image; based on the association relationship between each sample image and known information, the connected domain diagrams are combined according to the preset connected domain combination rules to obtain each connected domain combination diagram; the connected domain combination diagram and other connected domain graphs that cannot be combined are confirmed as sub-card images of the image to be processed. The invention can overcome the problem of missed detection of approximate images with partial features in multi-feature image retrieval.

Description

technical field [0001] The invention relates to the technical field of image processing and retrieval, in particular to an image sub-card processing method, device, and image retrieval method, device and system. Background technique [0002] At present, in the image retrieval, the processing methods of the image to be processed mainly include: one is to use the thing described in the image as the constituent element to mark its graphic element code, this method is widely used in the field of trademark image retrieval, such as 1985 The "International Classification of the Figurative Elements of Trademarks" established by the Vienna Agreement signed by various countries at the Diplomatic Conference in Vienna on August 9 uses the "coding of graphic elements of trademarks" to encode the input trademark images or sample trademark images in the database. The matching of element codes realizes the retrieval of trademark images; the other is to extract the image feature information ...

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): G06K9/34G06K9/46G06F17/30
CPCG06F16/583G06V10/267G06V10/44G06V10/56
Inventor 徐庆
Owner FOSHAN GUOFANG TRADEMARK SERVICE CO LTD
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap