Human face recognition image static correction method and system based on double cameras

Abstract

The invention discloses a human face recognition image static correction method and system based on double cameras, and the method comprises the steps: respectively capturing an infrared image and a visible image of an LED lamp in a test box through two cameras; respectively searching the brightest parts from the two captured images, and enabling the brightest parts to serve as the positions of the LED lamp in the two images, so as to calculate the position deviation of the visible camera and the infrared camera; writing the calculated position deviation into an EPROM; installing two camera plates on human face recognition equipment, and then carrying out the static correction of the human face recognition images according to the position deviation of the EPROM. According to the searched position of the LED lamp, the method calculates the position deviation of the visible camera and the infrared camera, so the method is more objective and accurate. The static correction method is employed for replacing a dynamic correction method. The deviation correction of the two images can be achieved through one correction, thereby improving the correction speed and efficiency. The method can be widely used in the field of human face recognition.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a method and system for static correction of face recognition images based on dual cameras. Background technique [0002] Existing face recognition equipment generally adopts dual cameras: one is a visible light camera and the other is an infrared camera. Infrared cameras are hardly affected by lighting, so infrared images are used for actual recognition. What is displayed on the screen of the face recognition device is not an infrared image, but a visible light image, because the infrared image is a black and white image that cannot be displayed on the screen. However, the two cameras are not installed in the same position (usually arranged left and right), so the two images captured by the actual face recognition device must have deviations. If the face recognition device does not consider this deviation during face recognition, although the user feels that he has correctly lo...

AI Technical Summary

Problems solved by technology

[0004] 1. By searching for the position of the eyes and then comparing the relative positions of the two eyes in the visible light image and the infrared image to obtain the deviation of the two images, when obtaining the position deviation between the visible light image and the infrared image, relying on the human eye to locate the relative position, subject to artificial Subjective factors have great influence, not objective and accurate enough

[0005] 2. The dynamic correction method is adopted. The position deviation of the visible light image and the infrared image is a variable. In actual use, it is necessary to perform multiple corrections according to the real-time position deviation of the two images to complete the deviation correction of the two images of the visible light image and the infrared image. , reducing the correction speed and correction efficiency

Images