Efficient 3D face recognition based on PCA

Using Matlab

Nonfiction, Computers, Advanced Computing, Engineering, Computer Engineering
Cover of the book Efficient 3D face recognition based on PCA by Yagnesh Parmar, GRIN Publishing
View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart
Author: Yagnesh Parmar ISBN: 9783656302346
Publisher: GRIN Publishing Publication: November 5, 2012
Imprint: GRIN Publishing Language: English
Author: Yagnesh Parmar
ISBN: 9783656302346
Publisher: GRIN Publishing
Publication: November 5, 2012
Imprint: GRIN Publishing
Language: English

Project Report from the year 2012 in the subject Engineering - Computer Engineering, Gujarat University, course: Electronics and communication, language: English, abstract: This thesis describes a face recognition system that overcomes the problem of changes in gesture and mimics in three-dimensional (3D) range images. Here, we propose a local variation detection and restoration method based on the two-dimensional (2D) principal component analysis (PCA). The depth map of a 3D facial image is first smoothed using median filter to minimize the local variation. The detected face shape is cropped & normalized to a standard image size of 101x101 pixels and the forefront nose point is selected to be the image center. Facial depthvalues are scaled between 0 and 255 for translation and scaling-invariant identification. The preprocessed face image is smoothed to minimize the local variations. The 2DPCA is applied to the resultant range data and the corresponding principal-(or eigen-) images are used as the characteristic feature vectors of the subject to find his/her identity in the database of pre-recorded faces. The system's performance is tested against the GavabDB facial databases. Experimental results show that the proposed method is able to identify subjects with different gesture and mimics in the presence of noise in their 3D facial image.

View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart

Project Report from the year 2012 in the subject Engineering - Computer Engineering, Gujarat University, course: Electronics and communication, language: English, abstract: This thesis describes a face recognition system that overcomes the problem of changes in gesture and mimics in three-dimensional (3D) range images. Here, we propose a local variation detection and restoration method based on the two-dimensional (2D) principal component analysis (PCA). The depth map of a 3D facial image is first smoothed using median filter to minimize the local variation. The detected face shape is cropped & normalized to a standard image size of 101x101 pixels and the forefront nose point is selected to be the image center. Facial depthvalues are scaled between 0 and 255 for translation and scaling-invariant identification. The preprocessed face image is smoothed to minimize the local variations. The 2DPCA is applied to the resultant range data and the corresponding principal-(or eigen-) images are used as the characteristic feature vectors of the subject to find his/her identity in the database of pre-recorded faces. The system's performance is tested against the GavabDB facial databases. Experimental results show that the proposed method is able to identify subjects with different gesture and mimics in the presence of noise in their 3D facial image.

More books from GRIN Publishing

Cover of the book African American Vernacular English - Origins and Features by Yagnesh Parmar
Cover of the book How and why has Wal-Mart established its current international presence? An explanation by Yagnesh Parmar
Cover of the book Beitrag zum Jahr der Mathematik 2008 by Yagnesh Parmar
Cover of the book Das Apostelkonzil - Eine neue Religion blüht auf by Yagnesh Parmar
Cover of the book Ideas of 'Managing' Natives in Stevenson's 'The Beach of Falesá' and Buchan's 'Prester John' by Yagnesh Parmar
Cover of the book Football As An Urban Phenomenon by Yagnesh Parmar
Cover of the book The problem of Du and Sie in the German Language. An approach. by Yagnesh Parmar
Cover of the book Contemporary Immigration Policy in Canada and Germany by Yagnesh Parmar
Cover of the book Wir selbst sind Zeit by Yagnesh Parmar
Cover of the book Ethics as an Ascetic Experience - Power, Language and the Ambiguity of the Visible in Michel Foucault by Yagnesh Parmar
Cover of the book New insights on Winogradsky Columns: Simulation of Contaminated Subsurface Systems for Low Cost, Sustainable Bioremediation by Yagnesh Parmar
Cover of the book Options for Variable Compensation by Yagnesh Parmar
Cover of the book How To Scare A Monster - The Philosophy of Monsters, Inc. by Yagnesh Parmar
Cover of the book Identifying organisational strategy by Yagnesh Parmar
Cover of the book Mezzanine Financing by Yagnesh Parmar
We use our own "cookies" and third party cookies to improve services and to see statistical information. By using this website, you agree to our Privacy Policy