Station caption identifying method and device

A technology for station logo recognition and station logo, which is applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of recognition method failure and slow recognition speed, achieve high recognition rate, reduce false detection rate, and high-efficiency recognition speed Effect

Active Publication Date: 2013-04-03
TCL CORPORATION
View PDF2 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the embodiments of the present invention is to provide a method for identifying a station logo and a set-top box, aiming at solving the problem

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 identifying method and device
  • Station caption identifying method and device
  • Station caption identifying method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0018] Such as figure 1 Shown is a flow chart of the logo recognition method provided by the first embodiment of the present invention. For ease of description, only the parts related to the embodiment of the present invention are shown.

[0019] In step S101, the template images of the logos of each TV station are acquired in advance, and the template images of the logos of each TV station are classified.

[0020] In the embodiment of the present invention, the template images of the station logos of each TV station are collected and made in advance, so that the template images of the station logos of each station only contain the content of the station logo, and the size of the template image is the same as that of the station logos of each station, and finally record the contents of each station logo. The azimuth position of the standard template image in the entire frame of the TV screen image (such as whether it is located at the upper left of the TV screen or at the uppe...

Embodiment 2

[0057] figure 2 The schematic diagram of the structure of the station logo recognition device provided by the embodiment of the present invention only shows the parts related to the embodiment of the present invention for the convenience of description. in:

[0058] The station logo template database building unit 21 is used to pre-acquire the template images of the station logos of each TV station, and classify the station logo template images of each station.

[0059] The station logo classifier training unit 22 is used to train the station logo classifier according to the extracted features of the station logo template images of each TV station.

[0060] In an embodiment of the present invention, the station logo classifier training unit 22 includes a subunit: a classifier training subunit 221, which is used to use the support vector machine SVM method to use the features of the extracted station logo template images of each TV station as the input of the SVM The feature...

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 is applicable to the field of multimedia application, and provides a station caption identifying method and device. The station caption identifying method comprises steps of: intercepting an image in a predetermined area of the current screen, isolating the image of a station caption after multi-frame images in the predetermined area of the current channel are accumulated; obtaining the category of the station caption by a pre-trained station caption categorizer; and matching the station caption with each pre-stored station caption template image belonging to the category, so as to determine the current channel. According to the station caption identifying method and device, after being isolated, the station caption is matched with station captions which are pre-stored and are effectively categorized by using the effective template matching method, the identifying method based on the category and the identifying method based on the template matching are effectively combined, so that not only can the false positive rate be effectively reduced, but also the high-efficient identifying speed and the high rate of identification are provided.

Description

technical field [0001] The invention belongs to the field of multimedia applications, and in particular relates to a method and device for identifying a station logo. Background technique [0002] With the continuous development of radio and television, more and more TV programs, more and more rich. In TV programs, a TV station logo is a symbol of a TV station, which contains important semantic information such as the name of the TV station and program orientation. Although there are many existing identification methods for station logos, usually when the television station logo recognition algorithm needs to recognize a large number of station logos (such as two or three hundred station logos), the recognition speed becomes very slow, and even the recognition method fails. Contents of the invention [0003] The purpose of the embodiments of the present invention is to provide a method for identifying a station logo and a set-top box, aiming at solving the problem that th...

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): G06K9/64
Inventor 李相涛邵诗强付东
Owner TCL CORPORATION
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