Small Scale Targeted Face Detection Using Deep Convolutional Neural Network

Under the field of object detection,face detection is the fundamental element of computer vision technology,for a few decades it become the popular research area.However due to the limitation of some scenes image data have low resolution,occlusion,illumination,makeup and others issue that make face detection hard.Today many recent algorithms can recognize face detection well under the condition of positive and high resolution.However most of the faces were located in challenged condition and low resolution are the problem of face detection.Small Scale Face Detection is one of the challenged faces that hard to detect easily.Because of the low resolution,scale invariance and contextual reasoning,due to the lack of detail information about located face.To achieve the required goal of small scale face detection we proposed novel Small Scale Targeted Face Detection(SSTFD)and the combination of MS-faster-RCNN to increase the accuracy of multiscale face.In our proposed approach we used Residual Network(ResNet)50,101 and 152 as the backbone network and from Intersection over Union(IoU)regression we used Complete Intersection over Union(CIoU)and Control Distance Intersection over Union(CDIoU).We applied various techniques like small scale targeted face detection to produce high accuracy results and good speed.We implemented our work based on small scale targeted face detection on the hard test most popular and challenging face detection benchmark WIDER FACE.With a single model and a single scale within ResNet 50 size dataset we got 93.2 Average Precision(AP),within ResNet 101 we got93.5% Average Precision(AP)and we got 94.1% Average Precision(AP)within the ResNet152.Genarally when we compare our proposed method with recent face detector our proposed model has achieved motivating result.