Face recognition based door lock system

Abstract : Nowadays, we are facing security issues in every aspect. So we have to resolve these issues by using updated technology. In this project, we are using the Face recognition module to capture human images and to compare with stored database images. The most important of feature of any home security system is to detect the people who enter or leave the house. Instead of monitoring that through passwords or pins, unique faces can be made use of as they are one’s biometric trait. We aim to create a smart door, which secures the gateway on the basis of who we are. We want to develop this system based on Raspberry-pi 3, to make the house only accessible when your face is recognized by the recognition algorithms from Open CV library and meanwhile you are allowed in by the house owner, who could monitor entrance remotely. Whenever the person comes in front of the door, it recognizes the face and if it is registered then it unlocks the door, if the face is not registered it will raise an alarm in the mobile and clicks a picture and send it on the registered number. This is how the system works.

 EXISTING SYSTEM :

 ? Once the image is fed to the system, the recognizer will generate histogram of that image which will be matched to the existing histogram. The person with the outmost matching result will be labelled in the output window. ? Thus, from this project, it is able to encourage the existing smart home manufacturer to produce a more affordable and extensible smart home system. ? The motivation is to develop a low cost security system to solve the issues exist on market product. ? Anyway there are a few problems that are still exist on security product on market. The issues like the face detection only will start to function when someone press the doorbell.

 DISADVANTAGE :

 ? When the captured image resolution is low, the accuracy seemed to drop because the image captures has not enough data to be processed. By using a hierarchical approach to this problem is reduced. ? The problem with the image representation is its high dimensionality. ? However, face detection is more challenging because of some unstable characteristics, for example, glasses and beard will impact the detecting effectiveness. ? The system security on market with low budget have the problem like the face detection only will start to function when someone press the doorbell.

 PROPOSED SYSTEM :

 • They proposed that a low cost alternative for DSP kits for image processing using Raspberry pi board with Open-cv package. • In this proposed work the platform for image processing is or algorithm for face recognition is implemented on principal component analysis. • Also their proposed work implements home security system captures information and transmits it via a 3G Dongle to a Smart phone using web application. • Their paper conducts a study to optimize the time complexity of PCA (Eigen faces) that does not affects the recognition performance applying their proposed enhanced algorithm.

 ADVANTAGE :

 ? To overcome these problems, the system used adaboost algorithm implemented using Haar classifiers for face detection and PCA algorithm for face recognition implemented using face recognizer function of OpenCV. ? Also as the threshold value is increased the false recognition of the person increases thus deteriorating the performance. ? The cascaded classifier used by OpenCV is Haar cascade classifier which is trained on thousands of human faces. The training data is stored in an xml file which is later used by the classifier to detect faces. ? Also the SMTP and Dropbox service are used for added security and remote access features.