Scene recognition method based on single-hidden-layer neural network

Abstract

The invention provides a scene recognition method based on a single-hidden-layer neural network, and the method is characterized in that the method comprises a training stage and a recognition stage; the training stage comprises the steps: carrying out the preprocessing of a pre-collected sampling image set for training, extracting the local gradient statistical characteristics of the pre-collected sampling image set after preprocessing, enabling the local gradient statistical characteristics and a corresponding scene type label to be added to a single-hidden-layer neural network classifier for layered supervised learning, obtaining a plurality of different optimal parameters of various types of single-hidden-layer neural networks, and constructing a multilayer scene classifier according to the optimal parameters; the recognition stage comprises the steps: carrying out the preprocessing of a to-be-recognized image set, carrying out the local gradient statistical characteristics of the to-be-recognized image set after preprocessing, enabling a local gradient statistical characteristic vector to be inputted into the multilayer scene classifier for recognition, and obtaining a class mark of the scene. The method achieves the high-precision scene recognition.

Description

technical field [0001] The invention relates to a scene recognition method based on a single hidden layer neural network. Background technique [0002] Scene recognition refers to identifying the scene in the scene picture according to the similar content of the scene image, such as the same color feature. The purpose is to mine the scene features in the image by imitating human perception, so as to automatically identify the scene to which the image belongs. In the scene recognition process, the whole image is discriminated as a whole, and no specific object is involved. Because the specific target can only be used as a basis for determining the category in the scene classification, but it is not necessarily completely related to the category of the scene. Scene recognition is a basic preprocessing process in the fields of computer vision and robotics, and it plays an important role in computer intelligence fields such as image content retrieval, pattern recognition, and m...

AI Technical Summary

Problems solved by technology

[0012] Difficulties in existing scene recognition, such as the dynamic change of the same scene, the variability of pictures in the same scene, the images of different classes may have many similar points, and the images of different scenes may overlap The accuracy of the scene classification is not high due to the situation of the situation, etc., the present invention provides a scene recognition method based on a single hidden layer neural network, the scene recognition based on the global feature, the whole scene image is judged as a whole, High scene image recognition rate can be achieved without involving specific targets

Images