Face Recognition based on Diagonal DCT Coefficients and Image Processing Techniques

نویسنده

  • Gurpreet Kaur
چکیده

The presented paper presents the statistical analysis of the diagonal dct coefficients of facial images in order to identify the face from the data base. The dct coefficients matrix contains the frequency variations of facial images in three parts; the lower half of the matrix that contains the low frequency elements that make up the flashy part of the face, the upper half that contain the high frequency elements in form of noise and diagonal elements that contain the maximum information about the features of the facial image. The diagonal elements or dct coefficients are then analyzed statistically in terms of mean deviation, standard deviation and covariance to identify the given face. The statistical analysis of dct coefficients gives the freedom of face variations among the same face images. The dct coefficients do not vary much if the same person’s face is photographed at different conditions.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Face Recognition Using Double Dimension Reduction

In this paper a new approach to face recognition is presented that achieves double dimension reduction making the system computationally efficient with better recognition results. In pattern recognition techniques, discriminative information of image increases with increase in resolution to a certain extent, consequently face recognition results improve with increase in face image resolution an...

متن کامل

A New Approach to Face Recognition Using Dual Dimension Reduction

In this paper a new approach to face recognition is presented that achieves double dimension reduction, making the system computationally efficient with better recognition results and out perform common DCT technique of face recognition. In pattern recognition techniques, discriminative information of image increases with increase in resolution to a certain extent, consequently face recognition...

متن کامل

Face Recognition using DCT based Energy Discriminant Mask

It has been observed that the variations among the images of the same face due to illumination and viewing direction are almost always larger than image variations. One person, with the same facial expression, can appear strikingly different when light source direction and viewpoint vary. These variations are emphasized by additional factors such as facial expressions, perspiration, hair style,...

متن کامل

Diagonally Assisted DCT Technique for Face Recognition: DA-DCT

Face is a multidimensional intricate structure that demands good computing technique for recalling it. This paper proposes a new diagonally assisted face recognition technique using Discrete Cosine Transform (DCT). Proposed work divides an image into matrix to apply DCT. Working scheme i.e. DA-DCT selects diagonal coefficient to retain low, moderate and high frequency coefficients for each bloc...

متن کامل

A MATLAB based Face Recognition System using Image Processing and Neural Networks

Automatic recognition of people is a challenging problem which has received much attention during recent years due to its many applications in different fields. 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 paper presents a new technique for human face recognition. This technique uses an image-...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012