This paper presents an automated system for human face recognition in a real time background for ATM transaction. Now a days
taking money from the ATM has became a major threat. When we are inserting our debit card the system is asking for the pin number.
After typing the pin number the money that we need is been transacted. With the orginal debit card any one can take the money from
the ATM. Now a days unknown strange people are creating a duplicate debit card and they use it in the ATM and loot our money. To
eradicate this problem we are going for secured ATM transaction using face recognition. Now a days face recognition technique is
playing a vital role in the field of secured process. By following this technique we can avoid the strangers looting our money and thus
our money will be safer and secured. This process is carried out by matching the present captured face image to already stored
database image. When both the images gets matched up ATM transaction is been allowed. If the images doesn’t match up the
transaction is been denied. But this task is very difficult as the real time background subtraction in an image is still a challenge. To
detect real time human face, Principal Component Analysis (PCA) is used to recognize the faces detected with a high accuracy rate.
Once recognition is done with the matched face, then the input image will be marked and updated in the database. This project gives
much more solutions with accurate results in user interactive manner rather than existing normal transaction management systems.
The ease of deployment is due to wireless mode of communication. A prototype of the controller is implemented, and shows how the
controller can easily and flexibly control the appliances.