IOT based Facial Recognition Door Lock System
Sometimes unknown person may also enter, this cannot be avoided but at all times everyone will not be aware of the intruder. For this type of situation this model proposes a solution. If the captured image is an unauthenticated person, then an SMS will be automatically generated to the user that an
2025-06-28 16:33:25 - Adil Khan
IOT based Facial Recognition Door Lock System
Project Area of Specialization Internet of ThingsProject SummarySometimes unknown person may also enter, this cannot be avoided but at all times everyone will not be aware of the intruder. For this type of situation this model proposes a solution. If the captured image is an unauthenticated person, then an SMS will be automatically generated to the user that an Unauthenticated Person Has Entered Home and the door will remain closed itself. Face recognition system has been developed in order to study the potential application for automated door access control. Among the other biometric techniques, face recognition approach possess one great advantage which is user friendliness. The technique of Eigen faces has been applied into the system which makes the system more secure. A cost effective and SMS operated home security system has been designed and tested with the GSM network. As future efforts, improving the reliability and robustness in both the recognition and detection process can be concentrated more.The Face recognition algorithm is applied on a wide variety of images taken under different lighting conditions and with different backgrounds. The images also have pose variation, emotions etc. The training set contained different set of people belonging to different races. The various stages in the algorithm are explained using the training set of RGB images. Now convert RGB image into gray image for preprocessing steps. First of all train the gray size image. Now normalized the training set using many pre-processing steps. The mean image of normalized training sets is determined. Eigen faces of normalized training set is calculated. The reconstructed image from input image is used for recognizing, it is in database or not.
Project ObjectivesThe goal of this project is basically to try to do something like the Smart phones unlock system by face recognition. However, we’ll do it for home or office security. Our project will mainly focus on the following objectives:
For face recognition, an image will be captured by pi camera and preprocessed by Raspberry pi like converting, resizing and cropping. Then face detection and recognition are performed. Once the face is recognized by the classifier based on pre-stored image library, the door will automatically unlock by the system.
To achieve the first goal, we will assemble hardware
To achieve the second goal, we will connect hardware to the system
To achieve our third goal, we will do code and tested it again and again
In this, we are using the LBPH (Local Binary Pattern Histogram) Algorithm. This algorithm will give us more accurate results when we compare to other types of algorithms such as Fisher Face, Eigen Faces Algorithms in base paper. This LBPH Algorithm will take number of images as you wish in different angles and check those all images at the time of face no recognition. In our case, we are taking 20 images of a person with different angles and it will be stored in our date base. For this algorithm, we are using VNC viewer to run raspbian os for detecting images from the data base. At first, we have to save images by using data sets and after that, we will train that faces to algorithm then it stores into the data base. At first, it converts color images to gray scale images and then it converts into pixels for detecting this will divides the image into various pieces then it stores the values of each pixel. If pixels are less then it will be represented as 0 and pixels which are high will be 1 then it will be arranged in 3 x 3 matrix format for recognizing the new images on screen compared to data base stored images. Here are some different variations of faces that is capture.
Benefits of the ProjectSecurity
Technical Details of Final DeliverableThis project wil deliver the best security for the homes and offices
Final Deliverable of the Project Hardware SystemCore Industry SecurityOther IndustriesCore Technology Internet of Things (IoT)Other TechnologiesSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 17000 | |||
| Raspberry pi 3 b+ | Equipment | 1 | 6650 | 6650 |
| Electronic Door lock | Equipment | 1 | 1000 | 1000 |
| 2 channel relay | Equipment | 1 | 150 | 150 |
| Casing of raspberry pi | Equipment | 1 | 550 | 550 |
| 16gb SD card for raspberry pi | Equipment | 1 | 850 | 850 |
| HDMI connector | Equipment | 1 | 150 | 150 |
| Power supply for door lock | Equipment | 1 | 250 | 250 |
| Jumper wires | Equipment | 24 | 120 | 2880 |
| Wooden Door model | Equipment | 1 | 2000 | 2000 |
| HD web camera for face detection | Equipment | 1 | 2000 | 2000 |
| Power supply connector | Equipment | 1 | 20 | 20 |
| Report printing with file | Miscellaneous | 1 | 500 | 500 |