Face deployment and control alarm method and device

Abstract

The invention provides a face deployment and control alarm method and a face deployment and control alarm device. The method and the device are applied to a server, a plurality of different feature models and face features of a target deploying and controlling character under the feature models are pre-stored in the server, and the method comprises the steps that a to-be-identified character imageis acquired, feature extraction is conducted on the to-be-identified character image through the feature models, and corresponding face features are obtained; comparing each face feature of the to-be-identified person image with the corresponding face feature of the target monitoring person to obtain feature similarity between the to-be-identified person image and the target monitoring person under different feature models; and comparing the feature similarity under each feature model with a preset similarity threshold to obtain each target feature similarity which is not less than the presetsimilarity threshold, and performing monitoring alarm based on the distribution condition among the target feature similarities. The method is low in manpower consumption, wide in application range and capable of providing face deployment and control alarm service low in false alarm rate, high in precision and high in efficiency.

Description

technical field [0001] The present invention relates to the technical field of face recognition, in particular, to a method and device for face control and alarm. Background technique [0002] With the continuous development of science and technology, the application of face recognition technology is becoming more and more extensive. Among them, face recognition deployment and control technology is an important branch of face recognition technology. However, the existing face recognition deployment and control technology directly compares the imported face photos with the face photos of the target person, and sends an alarm when the similarity of the compared photos exceeds the threshold, so as to realize the detection of the target. The characters are deployed and controlled. [0003] However, this face control technology will issue incorrect alarms or false alarms due to the low quality of the imported photos. For this reason, the existing face control technology usually ...

AI Technical Summary

Problems solved by technology

[0003] However, this face control technology will issue incorrect alarms or false alarms due to the low quality of the imported photos. For this reason, the existing face control technology usually checks the imported faces before comparing the photos. Photo quality detection is performed on photos, and after removing face photos whose photo quality scores are less than the score threshold, photo comparisons are performed with the remaining face photos after the removal operation, thereby reducing the false positive rate of face control

Among them, it is necessary for the staff to manually analyze the false positives of the false positives of the face control for many times in order to determine a more accurate score threshold. In this process, human resources are consumed and the analysis takes a long time. The threshold accuracy is not high, which leads to low efficiency of deployment and control alarm, and low precision of deployment and control alarm

Images