With the increasing popularity of intelligent hardware, the variety of its products tends to be more diversified to adapt to more demand scenarios. Take the camera, an important part of face recognition, as an example, various products not only have different prices and styles, but also distinguish between monocular and binocular. So how to choose?

Recently, at the 2020 high tech fair, the author introduced he Shikun, general manager of the camera module manufacturer kingsicom, which focuses on image acquisition industry and has strong professional ability, and conducted a deep communication on how to select the face recognition camera.






Key point one: single or binocular? It also depends on the needs of in vivo testing






Monocular camera is mainly RGB camera. With monocular algorithm, it can quickly complete the acquisition and deliver high-quality images to the back-end for recognition and comparison. It is suitable for face deployment, accurate promotion, passenger flow statistics, access control management and other application scenarios. This kind of camera can achieve monocular live detection with appropriate living detection algorithm. For example, by introducing arcface face face recognition algorithm, which is free and open on the hongruan visual open platform, Kingview realizes silent live recognition without user action cooperation. In addition, with the help of arcface algorithm, the whole set of functions such as face recognition, age detection, gender detection, face recognition under large area occlusion can be realized quickly.








The binocular camera is based on the RGB camera, adding an IR lens, which has the video capture function of near-infrared light and visible light. Based on the principle of infrared imaging, the screen class can not image, so it has the inherent ability to resist the false screen imaging


Face attack ability.










Therefore, compared with the monocular camera, the binocular camera is superior to the monocular camera in the defense ability against the fake face attack. For example, the hot-selling 5 million binocular wide dynamic face recognition camera adopts the IR binocular living technology of hongruan free arcface algorithm. Based on the principle of infrared imaging and the high robustness of deep learning algorithm, it has excellent defense against paper photos and screen photos.






However, due to the differences in hardware, the cost of binocular is higher than that of monocular RGB. In general, monocular face recognition solutions are easy to deploy and low-cost, while binocular face recognition solutions have higher accuracy in living detection, and are more adaptable to light changes, complex background environment and other factors, and can support real unattended. Therefore, in the selection process, specific consideration should be made according to the actual application scenario, the desired living effect, and the final cost, so as to balance the needs of all parties.