Yang C.-YHOMER H. CHEN2022-04-252022-04-25202110577149https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108742075&doi=10.1109%2fTIP.2021.3087400&partnerID=40&md5=9e79c04556459b0e71848c3206ee864dhttps://scholars.lib.ntu.edu.tw/handle/123456789/607103Significant progress has been made for face detection from normal images in recent years; however, accurate and fast face detection from fisheye images remains a challenging issue because of serious fisheye distortion in the peripheral region of the image. To improve face detection accuracy, we propose a light-weight location-aware network to distinguish the peripheral region from the central region in the feature learning stage. To match the face detector, the shape and scale of the anchor (bounding box) is made location dependent. The overall face detection system performs directly in the fisheye image domain without rectification and calibration and hence is agnostic of the fisheye projection parameters. Experiments on Wider-360 and real-world fisheye images using a single CPU core indeed show that our method is superior to the state-of-the-art real-time face detector RFB Net. ? 1992-2012 IEEE.face detectionFisheye camerafisheye distortionimage rectificationImage processingMathematical modelsDetection accuracyEfficient facesFace detection systemFeature learningFisheye imagesLocation dependentsPeripheral regionsState of the artFace recognitionAgnosticarticlecalibrationhumanlearning[SDGs]SDG3journal article10.1109/TIP.2021.3087400341256772-s2.0-85108742075