Channel logo segmentation method for pixel-level channel logo recognition network based on cross-layer feature extraction

Abstract

A channel logo segmentation method for a pixel-level channel logo recognition network based on cross-layer feature extraction includes the steps of modifying a fully connected layer of an existing classification network to a convolutional layer, combining features of input images output by low and high layers, extracting cross-layer features that integrate local and global features of the images,and constructing three pixel-level channel log recognition networks of different cross-layer architectures; using existing channel logo data sets as training and test data, including a channel logo image set and a binary label image set corresponding to the channel logo image set, and extracting three cross-layer features of the channel logo image set respectively by using the three pixel-level channel logo recognition networks; training the pixel-level channel logo recognition networks; and testing the channel logo image set by using the three pixel-level channel logo recognition networks trained on the channel logo data set of different types respectively, and finally producing pixel-level segmentation results of the same size as the input images. The channel logo segmentation method ofthe invention has a stronger description capability and discrimination capability.

Description

technical field [0001] The invention relates to a station logo segmentation method. In particular, it relates to a station logo segmentation method of a pixel-level station logo recognition network based on cross-layer feature extraction. Background technique [0002] The feature extraction of the logo image is the key factor to determine the accuracy of the logo recognition. Finding a more distinguishing feature has always been the goal pursued by researchers. At present, logo recognition mainly adopts the method of extracting features first and then calculating feature similarity. The features used include traditional features and deep features. [0003] The features used in traditional station logo recognition methods can be divided into global features and local features. Among them, global features usually include features such as color, shape, mesh, principal component analysis, edge, and texture. Although the color information has the characteristics of size and vi...

AI Technical Summary

Problems solved by technology

[0005] In summary, due to the limited description ability of manual features, the recognition effect is not good

Existing logo recognition methods based on machine learning such as support vector machines or artificial neural networks are limited by the performance of feature extraction algorithms. The network pays more attention to semantic features and cannot extract fine local features of logos.

At the same time, the performance improvement of these algorithms is also limited by the number of training samples

Images