Face Recognition Using Cnn
Sohail Sheikh · International Journal for Research in Applied Science and Engineering Technology · 2018
Face (facial) recognition is the identification of humans by the unique characteristics of their Faces. Face recognition technology is the least intrusive and fastest bio-metric technology. Face detection and tracking have been an important and active research field because it offered many applications especially in video surveillance, biometrics or video coding the goal of this project was to implement face recognition Technology to help human trafficking victim on a static photograph and real-time surveillance system to trace trafficked victims by their faces. The face recognition was determined by calculating different aspects of faces. The face detection algorithm involved color-based skin segmentation and image filtering. An open source software program library called TensorFlow is used to implement face recognition Technology. The previous experimental results have proven the accuracy and effectiveness of API over real-time systems and even under the varying condition of light facial poses and skin color. All calculation of hardware implementation was done in real time with the minimal computational effort, thus suitable for power-limited applications. Trafficking in persons is a serious crime and a grave violation of human rights. Every year, thousands of men, women and children fall into the hands of traffickers, in their own countries and abroad. Almost every country in the world is affected by trafficking, whether as a country of origin, transit or destination for victims. The basic purpose begins to identify the face uploaded (sighted person) on the server and drive information stored (lost person) in the database. It involves two main steps. First to classify the image of (lost person) and store them in the database or cloud and the second step to compare it with the uploaded images (sighted person) and returning the data related to that image. Various API libraries that can be used for face detection such as Google's inception, facenet, and Open CV.