Semantic feature-based face false detection screening method

Abstract

The invention relates to the technical field of face detection and recognition and aims to improve classification precision effectively and reduce generalization errors to realize effective classification screening on human face false detection result. The invention particularly relates to a semantic feature-based face false detection screening method, which comprises the following steps of performing face detection and alignment on an original image through a face detection and alignment algorithm by taking original image data as input of the stage, and zooming a detection alignment result to112 * 112 dimensions; performing pixel-level face semantic segmentation on the input face detection alignment result by adopting a BiSeNet-based real-time face semantic segmentation method to obtaina semantic segmentation result; processing the semantic segmentation result by adopting a feature engineering technology, and constructing and selecting a semantic feature with the highest representation capability; calculating the input semantic features by adopting a Stacking model integration framework to obtain a final human face false detection classification result and complete false detection screening; and realizing effective classification and screening of human face false detection results, thus the performance and robustness of the overall detection algorithm are improved.

Description

technical field [0001] The invention relates to the technical field of face detection and recognition, and aims to effectively improve classification accuracy, reduce generalization errors, realize effective classification and screening of face misdetection results, and improve the performance and robustness of the overall detection algorithm. Specifically, it relates to a Face false detection and screening method based on semantic features. Background technique [0002] As the pre-step of all face analysis tasks, face detection has always been a research hotspot in the field of computer vision. It has important application value in security monitoring, witness verification, human-computer interaction, social interaction and other fields. Face detection The goal is to get as high a face detection rate as possible, while ensuring as accurate a face detection result as possible and as low a false detection rate as possible. [0003] In recent years, many researchers have done...

AI Technical Summary

Problems solved by technology

[0004] Practice has shown that some of the current excellent face detection methods can also guarantee a high face detection rate in complex scenes, but this does not mean that they can be directly applied to the actual production environment. At the cost of a large number of false detection results, and unexpected false positives and false positives will inevitably affect the results of subsequent tasks and the performance of the entire system. Therefore, the oncoming challenge is how to effectively reduce the number of false detections. Most of the actual generation uses human Face false detection and screening method

[0005] In order to solve the problem of face misdetection, it is suggested to use the five-point coordinate feature based on the face together with the support vector machine to reduce false positives, because the corresponding part of the face can be located through the face coordinates, and any non-human In theory, no face will have reliable face coordinates. This method has shown its effectiveness in reducing false positives to a certain extent. It shows obvious deficiencies in occluded scenes; some people also propose to use convolutional neural network to judge true and false faces, but this is undoubtedly the same as the final classification stage of face detection based on deep learning, which is equivalent to using cascaded convolution Face classification by neural network cannot solve the fundamental problem, and it is difficult to effectively screen out false detection targets while increasing the amount of computation; However, when encountering face pose transformation and occlusion, the contour feature cannot play a good role at all, so it is difficult to apply in complex environments

[0006] In summary, the existing methods to solve the problem of face misdetection are basically based on simple feature selection, but they cannot be well applied in complex environments, largely because representative and discriminative features cannot be extracted. Sexual facial features for classification

Images