Small-scale face detection method based on generative adversarial network

The invention discloses a small-scale face detection method based on a generative adversarial network, relates to the technical field of face detection, and solves the technical problem of poor precision of an existing small-scale face detection mode. The method comprises the following steps: S1, inputting a noise image and a small face image in real acquisition data into a first generative adversarial network to generate enough small face context region samples; S2, training a face detection network by using the small face context region sample and the small face image; S3, acquiring a workplace image, and acquiring possible small-scale face candidate regions by using the potential face region network; and S4, performing super-resolution reconstruction on the small-scale face candidate region, and inputting the reconstructed small-scale face candidate region into the face detection network to obtain a small face position regression result. According to the method, sufficient small face context region samples