Single Shot MultiBox Detector on WIDER FACE
Download as PDF
We try SSD, which is a method for detecting objects in images using a single deep neural network, on the data set called WIDER FACE The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location. At prediction time, the network generates scores for the presence of each object category in each default box and produces adjustments to the box to better match the object shape. Additionally, the network combines predictions from multiple feature maps with different resolutions to naturally handle objects of various sizes. SSD is simple relative to methods that require object proposals be-cause it completely eliminates proposal generation and subsequent pixel or feature resampling stages and encapsulates all computation in a single network. This makes SSD easy to train and straightfor-ward to integrate into systems that require a detection component. Former writers has tried experi-ments on the PASCAL VOC, COCO, and ILSVRC datasets confifirm that SSD has competitive accuracy to methods that utilize an additional object proposal step and is much faster, while provid-ing a unifified framework for both training and inference. This article has established on WIDER FICE data set, which has 61 collections, each of them is split into train,validation, and test sets.
Convolutional Neural Network, Face Detection, Single Shot Detection, Real-time Object Detection