Station caption recognition method and station caption recognition device

A technology of station logo recognition and station logo, applied in the field of image recognition, can solve problems such as decreased user experience, low recognition accuracy, and no corresponding interactive information.

Active Publication Date: 2014-12-10
KUYUN INTERACTIVE TECH
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, because the identification accuracy of the logo of the station logo in the prior art is not high, especially when identifying some logos similar to the logo of the station, it is easy to misidenti

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
  • Station caption recognition method and station caption recognition device
  • Station caption recognition method and station caption recognition device
  • Station caption recognition method and station caption recognition device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0128] Figure 5 The flow chart of the station logo recognition method provided by Embodiment 2 of the present invention, such as Figure 5 As shown, the logo identification method includes:

[0129] Step 201: Calculate the similarity between each station logo sample and other station logo samples.

[0130] Step 202: Generate a multi-layer structure classification tree of the station logo according to the similarity between each station logo sample and other station logo samples, wherein the root node of the station logo classification tree is all the station logo samples, and the leaves of the station logo classification tree The nodes are samples of the station logo, and the minimum value of the similarity between the station logo samples in the branch nodes of the station logo classification tree is greater than the minimum value of the similarity between the station logo samples in the parent nodes of the branch nodes.

[0131] Step 203: Train a corresponding multi-level...

Embodiment 3

[0159] Figure 7 A schematic structural diagram of a station logo recognition device provided in Embodiment 3 of the present invention, as shown in Figure 7 As shown, the station logo recognition device includes: a classifier generation module 3 and a logo recognition module 4, wherein the classifier generation module 3 is connected to the logo recognition module 4, and the classifier generation module 3 is used to generate The station logo classification tree trains out the corresponding multi-level classifier, and the multi-level classifier includes several sub-classifiers corresponding to each branch node in the station logo classification tree one by one, and the sub-classifier includes a child node of the corresponding branch node. One corresponds to several classification models. The positive samples of the classification model are all station logo samples contained in the corresponding sub-node, and the negative samples of the classification model are all station logo ...

Embodiment 4

[0164] Embodiment 4 of the present invention provides a station logo recognition device, which includes: a similarity calculation module, a classification tree generation module, a classifier generation module, and a logo recognition module. The difference between this embodiment and the third embodiment above is that the identification recognition module in this embodiment is different from the identification recognition module in the third embodiment above.

[0165] Figure 9 It is a schematic structural diagram of the identification recognition module in Embodiment 4 of the present invention, such as Figure 9As shown, the identification identification module 4 includes: a second image extraction unit 8, a second node identification unit 9 and a second node type judgment unit 10, wherein the second node identification unit 9 is connected with the second image extraction unit 8 and the second node type The judging unit 10 is connected, the second image extracting unit 8 is ...

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 a station caption recognition method and a station caption recognition device. The station caption recognition method includes: training a corresponding multilevel classifier according to a pre-generated station caption classification tree with a multilayered structure, wherein the multilevel classifier comprises a plurality of sub-classifiers in one-to-one-correspondence to branch nodes of the station caption classification tree, each sub-classifier comprises a plurality of classification models in one-to-one-correspondence to child nodes corresponding to the branch nodes, positive samples of the classification models are all station caption samples included in the corresponding child nodes, and negative samples of the classification models are all station caption samples included in the other child nodes in brotherhood relation with the corresponding child nodes; recognizing the logo of a to-be-tested station caption in a display image according to the multilevel classifier. The station caption classification tree with the multilayered structure is structured in advance, the corresponding multilevel classifier is generated on the basis of the station caption classification tree, and accurate recognition of the logo of the to-be-tested station caption in the display image can be realized by the aid of the multilevel classifier.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a station logo recognition method and a station logo recognition device. Background technique [0002] With the improvement of people's living standards, smart TVs are increasingly popular in families, and play an increasingly important role in people's daily leisure and entertainment life. [0003] When smart TVs provide users with interactive point-to-point entertainment and information services, they first need to know the content of the programs currently played by smart TVs, and then provide relevant services based on the current broadcast content, so as to realize real-time interaction with users. In the prior art, in order to obtain the content currently played by the user, it is first necessary to identify the identity of the station logo in the user's current broadcast screen, and then obtain the corresponding live signal from the server based on the identified identity ...

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
IPC IPC(8): G06K9/66
Inventor 李鹏高鹏程陆承恩张阳
Owner KUYUN INTERACTIVE TECH
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