Table mark detection method, device and storage medium
A detection method and detection device technology, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of insufficient accuracy of detection results, large amount of calculation, and inability to deal with various deformations of station logos.
Inactive Publication Date: 2018-12-25
BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF7 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Traditionally, through manual real-time monitoring of TV signals or selection of specific TV program recordings for station logo detection, the work intensity is high, the work efficiency is low, and there will inevitably be mistakes
[0003] Generally, the method of automatic station logo detection is usually based on CNN deep learning method. This method has a relatively large amount of calculation and needs to be run on the GPU. The model training is also more troublesome, and it cannot cope with various deformations of the station logo. The test results are not accurate enough
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
[0033] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with aspects of the invention as recited in the appended claims.
[0034] figure 1 It is a flow chart of a logo detection method according to an exemplary embodiment. The station logo detection method can be used in a terminal system or a server system. A system capable of using the station logo detection method for station logo detection falls within the protection scope of the present disclosure.
[0035] Such as figure 1 As shown, this a kind of station ...
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 present disclosure relates to a platform mark detection method, device and storage medium. The method comprises the following steps of: acquiring a currently detected target image; matching the target image with the station mark in the station mark library to obtain the station mark to be determined; extracting a global feature of a station mark area in the target image and a global feature ofthe station mark to be determined; detecting whether the target image contains the station mark to be determined or not according to the global characteristics of the station mark area in the targetimage and the global characteristics of the station mark to be determined. The method detects whether the target image contains a station mark and what station mark is included by a matching calculation method and a global feature calculation method, thereby improving the accuracy of the station mark detection.
Description
technical field [0001] The present disclosure relates to the technical field of station logo detection, in particular to a station logo detection method, device and storage medium. Background technique [0002] Station logo, used to indicate the special logo of a TV station or TV channel. Its manifestations include patterns, characters, or a combination of patterns and characters. The publisher of the video, that is, the TV station that released the video, can be determined through the station logo of the video. Traditionally, the station logo detection is carried out by manually monitoring the TV signal in real time or selecting a specific TV program to be recorded, which is labor-intensive, low-efficiency, and inevitably makes mistakes. [0003] Generally, the method of automatic station logo detection is usually based on CNN deep learning method. This method has a relatively large amount of calculation and needs to be run on the GPU. The model training is also more trou...
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 Applications(China)
IPC IPC(8): G06K9/32G06K9/46G06K9/62
CPCG06V20/62G06V10/443G06V10/462G06V10/757
Inventor 宋丛礼
Owner BEIJING DAJIA INTERNET INFORMATION TECH CO LTD