Image processing method and image processing device

Abstract

The embodiment of the invention discloses an image processing method. The method comprises the steps of obtaining a first to-be-processed image according to a first weight parameter, wherein the first to-be-processed image is divided into multiple sub-pixel blocks; determining the proportion of the first target image in the sub-pixel blocks when the first to-be-processed image comprises a first target image; determining a second weight parameter according to the proportion of the first target image in the sub-pixel blocks, wherein the second weight parameter is used for obtaining a second to-be-processed image. The embodiment of the invention also provides an image processing device. According to the method and the device, the weight parameter for obtaining the image can be dynamically controlled; the image is collected in real time according to the changed weight parameter; the influence that a sampling image is unclear due to the fact that an imaging background is changed can be reduced; and the clear and uniform image without partial image overexposure or insufficient exposure can be collected, thereby facilitating post processing of the device.

Description

technical field [0001] The present invention relates to the field of human biological feature recognition, in particular to an image processing method and an image processing device. Background technique [0002] With the continuous development of Complementary Metal Oxide Semiconductor (English full name: Complementary Metal Oxide Semiconductor, English abbreviation: CMOS) image sensor, video technology based on CMOS image sensor has been widely used in video surveillance and aerospace fields. [0003] At present, there are many ways to obtain images by adjusting CMOS exposure time or gain. One of the implementation methods is to divide the acquired image into multiple blocks, and then select a fixed number of pixels from each block for brightness analysis. The analysis result is compared with the preset brightness threshold, and then the brightness threshold level of the entire image is counted, and the exposure time of the next image acquisition is determined by the stati...

AI Technical Summary

Problems solved by technology

[0004] The images collected by the existing technology are feasible for ordinary shooting, but for the security field, especially for the human biometric identification industry, there are relatively large defects. Due to the interference of background light, the exposure and gain control of the entire image cannot be achieved. Accurate shooting of the target object is difficult to extract clear and uniform features, and it is impossible to deal with the overexposure or underexposure of partial images

Images