person face detection through image
we depict an experiment to the face recognition problem by combining eigenfaces and neural network. Eigenfaces are applied to extract the relevant information in a face image, which are important for identification.
2025-06-28 16:34:26 - Adil Khan
person face detection through image
Project Area of Specialization Computer ScienceProject Summarywe depict an experiment to the face recognition problem by combining eigenfaces and neural network.
Eigenfaces are applied to extract the relevant information in a face image, which are important for
identification.
The objective of face recognition is, from the image processing , to find a series of data of the same face in a set of training images in a database. Through image processing it will mention the name and data of the person we train the model to recognize the name.
Project Implementation MethodThe 5 Levels of Autonomous Vehicles
Level 0 – No face detect
Level 1 – Face detection
Level 2 – Model training
Level 3 – Comparison of faces.
Level 4 – Comparison of face with available data.
Level 5 – Result.
Are to recognize suspected person samoung them if any person changed physically it will recognize also but shows accuracy level low.
Technical Details of Final Deliverable100 of GB data is collected and process by system. system will manage the data and store them in
available memory in res berry pie storage.in image format with date and time which also can
rename by the user through the Linux operating system.
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 37980 | |||
| raspberry pi 4 | Equipment | 1 | 14000 | 14000 |
| camera panasonic | Equipment | 1 | 6000 | 6000 |
| power suply | Equipment | 1 | 1480 | 1480 |
| sd card | Equipment | 1 | 1300 | 1300 |
| casing and cooling fan | Equipment | 1 | 4600 | 4600 |
| router and node mcu microcontroller | Equipment | 1 | 3800 | 3800 |
| pcb and solding | Equipment | 1 | 6000 | 6000 |
| other component | Equipment | 1 | 800 | 800 |