Scribd
Upload
68 views4 pages

Anna University: Chennai 600 025: Bonafide Certificate

This bona fide certificate certifies that the project report titled "FACE RECOGNITION USING IMAGE PROCESSING AND NEURAL NETWORKS" was completed by the students Arun Jesus J, Deva S, and Arish Balaji S under the supervision of Ms. A R Rajini and Ms. K Jeyapriya. The project was submitted for examination and evaluated by internal and external examiners.

Uploaded by

Deva
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
68 views4 pages

Anna University: Chennai 600 025: Bonafide Certificate

This bona fide certificate certifies that the project report titled "FACE RECOGNITION USING IMAGE PROCESSING AND NEURAL NETWORKS" was completed by the students Arun Jesus J, Deva S, and Arish Balaji S under the supervision of Ms. A R Rajini and Ms. K Jeyapriya. The project was submitted for examination and evaluated by internal and external examiners.

Uploaded by

Deva
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

ANNA UNIVERSITY: CHENNAI 600 025

BONAFIDE CERTIFICATE
Certified that this project report FACE RECOGNITION USING IMAGE PROCESSING AND NEURAL NETWORKS is the bonafide work of ARUN JESUS J(41908106014),DEVA S(41908106023),ARISH BALAJI S

C(4190816010) who carried out the project work under my supervision.

SIGNATURE Ms A R RAJINI HEAD OF THE DEPARTMENT

SIGNATURE Ms K JEYAPRIYA SUPERVISOR Assistant professor

Electronics and Communication Engg Sri Sairam Engineering College West Tambaram Chennai-44

Electronics And Communication Engg Sri Sairam Engineering College West Tambaram Chennai-44

Submitted for the viva-voce examination held on.

------------------------Internal Examiner

------------------------External Examiner

ACKNOWLEDGEMENT
We take immense pleasure to thank our beloved Chairman M.J.F.Ln.LeoMuthu for providing us with excellent lab facilities to do the project. We also take this opportunity to thank our respected CEO Mr. J. Sai Prakash for his encouraging presence. We thank our dynamic Director Prof.V.R.RAJAMANICKAM for being a constant source of inspiration to us. We convey our sincere thanks to Principal Dr.C.V.JAYAKUMAR who motivated us throughout the course of the project.

We are very much grateful to our energetic Head of the Department Ms. A.R. RAJINI for helping us complete the project with perfection. We extend our heartfelt gratitude to our Project Coordinators Ms. K.LAKSHMI JOSHITA, asst. prof., and Mr. B. APPOON , asst. prof., for their constant guidance for our project.

We feel indebted to our Internal Guide Prof. Ms. K. JEYAPRIYA, asst. prof., who has done all the needful for the successful completion of our project. We thank all the Staff Members and Lab Assistants of the Department of Electronics and Communication Engineering, who encouraged us all the way. Finally we thank Almighty for His blessings to make this project a success.

ABSTRACT Face recognition is one of those challenging problems and up to date, there is no technique that provides a robust solution to all situations. This

technique uses an image-based approach towards artificial intelligence by removing redundant data from face images through image compression. A self-organizing map (SOM) using an unsupervised learning technique is used to classify the compressed image vectors obtained into groups to identify if the subject in the input image is present or not present in the image The main advantage of this technique is its high-speed

database.

processing capability and low computational requirements, in terms of both speed and memory utilization. The method is capable of rapid classification, requires only fast, approximate normalization and preprocessing, and consistently exhibits better classification performance. With 5 images per person the proposed method and eigenfaces result in 3.8% and 10.5% error respectively. The recognizer provides a measure of confidence in its output and classification error approaches zero when rejecting as few as 10% of the examples. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze computational complexity and discuss how new classes could be added to the trained recognizer.

You might also like