Face shielding detection algorithm

Abstract

The invention relates to a face shielding detection algorithm, which comprises the following steps of: face image preprocessing: cutting a plurality of collected face images according to face positioninformation and face key point coordinates to obtain a plurality of face five-sense-organ images as a basic data set; data augmentation: performing data augmentation on the basic data set; data annotation and division: carrying out classification annotation on different types of augmented images, and taking the annotated data as a training sample which comprises a training set, a verification setand a test set; building a convolutional neural network model; setting hyper-parameters, training the convolutional neural network model, determining the hyper-parameters, configuring the training set to simulate training, testing the model by the verification set, observing whether the accuracy of the model obviously floats or not, if the accuracy obviously floats, returning to setting the hyper-parameters, and otherwise, outputting the hyper-parameters as a face shielding detection model; and testing the model, verifying the accuracy, determining the accuracy of the model by using the testset, and evaluating the generalization ability of the optimal hyper-parameter training model.

Description

technical field [0001] The invention relates to a human face occlusion detection algorithm, which belongs to the field of human face recognition. Background technique [0002] At present, most face occlusion detection uses feature extraction algorithms to extract image features, and then uses classifiers to classify features. The traditional method is to use feature extraction algorithms such as SIFT (Scale-invariant Feature Transform, scale-invariant feature transformation) and HOG (Histogram of Oriented Gradient, histogram of directional gradient), extract features and then undergo different feature processing, and then use support vectors Machine and other classifiers are trained to obtain a classifier model. [0003] In recent years, the rise of deep neural networks has provided another solution. Among them, the convolutional neural network is suitable for image recognition and classification. By building a convolutional neural network, train a large amount of complet...

AI Technical Summary

Problems solved by technology

[0004] The traditional face occlusion detection uses the whole face image as input data, which requires a large amount of data to learn the position of facial features and facial occlusion information to achieve the accuracy rate for the training of convolutional neural network. The accuracy rate is low and the training data is large. Therefore, the present invention Provide a face occlusion detection algorithm to solve the above problems

Images