Libraries
JS libraries
Face recognition
Face api
The Tiny Face Detector is a very performant, realtime face detector, which is much faster, smaller and less resource consuming compared to the SSD Mobilenet V1 face detector, in return it performs slightly less well on detecting small faces. This model is extremely mobile and web friendly, thus it should be your GO-TO face detector on mobile devices and resource limited clients. The size of the quantized model is only 190 KB (tiny_face_detector_model).
The face detector has been trained on a custom dataset of ~14K images labeled with bounding boxes. Furthermore the model has been trained to predict bounding boxes, which entirely cover facial feature points, thus it in general produces better results in combination with subsequent face landmark detection than SSD Mobilenet V1.
This model is basically an even tinier version of Tiny Yolo V2, replacing the regular convolutions of Yolo with depthwise separable convolutions. Yolo is fully convolutional, thus can easily adapt to different input image sizes to trade off accuracy for performance (inference time).
Kairos
Kairos is a simple concept—you submit images into the API, and the deep learning algorithms analyze the faces found, then the API returns a bunch of useful data about the faces we find. You can use this to search, match and compare faces, or measure characteristics such as age, gender and ethnicity.
This i tried different types of api and tried to make algorithm trough tensorflow but it was very difficult to implement in my application because i needed to classify different types of data points. To build a deep learning algorithm would be out of my scope.
Camerajs
To create different snapshots in my application i created a function to recognize the face of the user i needed access to the camera. This library helps me with the connection between the webapp and the webcam of the user.
Rest db
To store the data of the user i created a database with the entities of the analyzed data. When the user grant access to store the data, the data will be send to the restdb where it wil be collected and distributed to the mugshot page.
Last updated
Was this helpful?