Television station logo detection and recognition method

Abstract

The invention relates to a television station logo detection and recognition method, and belongs to the technical field of image detection and recognition. The method comprises the following steps: (1) collecting station logo picture samples, carrying out labeling on corresponding station logo positions of pictures, and carrying out size normalization processing on all the images of object detection; (2) setting parameters of a learning rate, an iteration number and the like of TB-Net network training; (3) sending the normalized images into a TB-Net network for training, extracting primary features and abstract features of the images, sending the same into a position regression layer and a classification layer, and obtaining a best station logo detection model after training; and (4) loading the station logo detection model and network by a test program, sending a to-be-detected picture into the network, and outputting a result of whether the image contains a station logo and a position where the station logo is located. According to the method, station logos in video pictures can be more accurately detected, and accuracy of station logo recognition can be improved.

Description

technical field [0001] The invention relates to a television station logo detection and recognition method, which belongs to the technical field of image detection and recognition. Background technique [0002] With the vigorous development of the Internet and TV broadcasting technology, more and more radio stations and network video files are disseminated on the Internet. Using computer vision systems to identify the logos in videos or images can bring more benefits to the supervision of radio and television. Convenience, so various Taiwan logo detection and recognition technologies came into being. The existing mainstream station logo detection algorithms mainly include: based on color histogram, spatial distribution histogram, ordinary Hu invariant distance, weighted Hu invariant distance and other technologies. [0003] At present, the traditional detection algorithms based on spatial histogram or constant distance have certain shortcomings. First of all, it is difficu...

AI Technical Summary

Problems solved by technology

First of all, it is difficult to identify similar station logos, the accuracy rate is not high, the complex and changeable image background and the existence of noise will have a relatively large impact on station logo recognition

Secondly, the efficiency of station logo detection and recognition is not high. In the large-scale multimedia data existing in the Internet, the existing station logo detection and recognition algorithms are difficult to meet the real-time detection requirements.

Images