Advertisement image detection method and device

Abstract

The invention provides an advertisement image detection method and device. The advertisement image detection method comprises the steps of extracting images at reference positions in advertisement video stream and at least one image before and after the reference positions; taking pixels with high identification rates in the selected images as identification points for matching images; segmenting the extracted images in a mode of dividing the images at the reference positions and the at least one image before and after the reference positions of the extracted images into segments, thereby forming image segments; dividing the image segments into multiple parts, thereby forming image groups; carrying out parallel similarity matching on the identification points of the reference position images in each image segment of the image groups and the identification points of the at least one image before and after the reference positions, thereby obtaining an advertisement segmentation time vector of each image group; and obtaining start time and end time of each piece of advertisement in the advertisement video stream according to the advertisement segmentation time vector of each image group.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method and device for detecting an advertisement image. Background technique [0002] With the development and widespread application of digital TV, people have higher and higher requirements for the content of TV, and advertisement, as the main carrier of commercial information, plays an increasingly important role in today's digitization. Faced with such a vast amount of advertising information, how to quickly detect the advertisements that meet people's needs will become a problem that people need to solve. [0003] The existing advertising detection method is to convert the color image into a grayscale image first, and then perform the binary processing on the grayscale image with the maximum between-class variance (OTSU), that is, the grayscale image of 0 to 255 levels is selected through an appropriate threshold. Obtain a black-and-white image that can reflect the overall...

AI Technical Summary

Problems solved by technology

[0005] Based on the above-mentioned deficiencies in the prior art, the present invention proposes a detection method and device for an advertisement image to solve the problem of converting a color image into a grayscale image and losing a large amount of information when detecting an advertisement in the prior art, and identifying all pixels of the image. It leads to a large amount of calculation and the problem that the correspondence with the original image is not unique during OTSU binarization processing and feature extraction, which reduces the accuracy of recognition

Images