Smart Safe Prototype Based Internet of Things (IoT) with Face and Fingerprint Recognition

Abstract

The safe box is currently considered safe but is not truly safe. That is because safe storage has a security method using PINs that can be seen by others. Therefore, a more secure safe box security system is needed. This paper purpose a safe box prototype with an added security system using a two-way verification system and an integrated Internet of Things (IoT) system. The face recognition system and fingerprint system used in this system. The face recognition system developed an LBP (Local Binary Pattern) clarification and embedded Haar cascade program in raspberry Pi. For real-time monitoring, the safe box has been designed to provide violation alerts via notifications on android apps. Two-way verification smart safe box has a good face recognition system especially when the conditions are bright and also the best way to identify fingerprints on a flat position. In LOS conditions, the best distance is at 4 meters with a delay value of 0.373 s and throughput of 3680.533 bps. In non-LOS condition, the best distance is 2 meters with a delay value of 0.380 seconds and throughput of 4055.73 bytes/s.