Station caption detection method based on color and gradient histograms

Abstract

The invention provides a station caption detection method based on color and gradient histograms. The station caption detection method includes steps: building a station caption sample library, training a support vector machine (SVM) classifier by extracting histograms of oriented gradients (HOG) characteristics in the library, extracting color characteristics of a to-be-measured station caption, confirming the parameter range and area proportion of at most front three main colors, through color matching algorithm, searching a to-be-measured area in a video frame, the to-be-measured area forming the same area with to-be-measured station caption colors, and obtaining the to-be-measured area where station captions possibly appear, image correcting for the to-be-measured area based on affine transformation and a minimum enclosing rectangle, extracting HOG characteristics in the to-be-measured area, and judging whether the to-be-measured station captions exist through a trained classifier. Strict test proves that the station caption identification method can identify the station captions of a video (including a microphone, a background and the like) in an accurate and approaching real-time mode.

Description

technical field [0001] The invention relates to the field of image-based recognition, in particular to a color and gradient histogram-based station logo detection method in a video image. Background technique [0002] At present, my country's entire TV system is becoming more and more large and complex, and some illegal TV signals are always trying to enter normal TV channels. Real-time monitoring has become an important task for TV signal transmitting stations. In order to save manpower and improve efficiency, it is necessary to develop a near real-time station logo identification method to realize the automatic detection function of illegal signals. [0003] The accuracy of the identification of the station logo depends on three aspects, one is the accurate positioning of the station logo; the second is the effective extraction of the station logo features; the third is the correct matching of the features. [0004] Chinese Patent Publication No. CN 102426647A, the patent...

AI Technical Summary

Problems solved by technology

However, after verification, it is found that there is a logical problem in this patent: in the HSV (Hue, Saturation, Value) space, the saturation of white and translucent colors are close to 0, the first step of this patent is to remove the low In the saturation pixel point, all the station logos composed of white pixels in the picture have been removed by mistake, so the subsequent station logos cannot be accurately positioned.

Therefore, this method cannot solve the problem of accurate positioning and real-time detection of the logo, and at the same time, it cannot detect the logo that appears in the scene.

Images