FACE RECOGNITION AND POSTURE RECOGNITION USING DRONE IMAGES

Abstract

Face recognition is a biometric technology that identifies or verifies individuals by analyzing and comparing facial features from images or video. The technology works by capturing an image of a face, extracting unique features such as the distance between the eyes, the shape of the cheekbones, and the contour of the lips, and then comparing these features to a database of known faces to find a match. There are many places and situation where human cannot access the field and hence cannot perform face recognition of criminals. In these situations, drone comes in handy for recognising criminals. It can fly at many places where humans cannot reach, it can fly at a certain height which can achieve better result compared to a soldier. There are many factors that can affect the operation from its main objective such as, height of the drone, camera quality carried by drone, lighting, pose. Posture recognition involves analyzing and interpreting the positions and movements of the human body.By recognizing different postures, systems can provide real-time feedback, improve user interfaces, and even prevent injuries. Using a posture detection one can unlock potential of Face recognition using drone images to many extents as we can derive what posture a particular person is in and effective response can be prepared further. This thesis work tries to find a better accurate working model for Face recognition as well as posture recognition. While extensive research has been conducted on datasets the performance and accuracy range can be explored. To address this gap, this thesis work tries out certain parameters whose values can adjusted to achieve higher accuracy.