Digital Image Processing

M. Mani Roja ¹, Sudhir Sawarkar ²

Affiliations
1 Amravati University, IN
2 Datta Meghe College of Engineering, Navi Mumbai, IN

Abstract

In this work, multimodal biometric system has been implemented by integrating signature, fingerprint and face templateswith very good accuracy rate. This paper analyses the performance of the proposed system under feature level fusion by integrating the extracted features from the biometric samples, score level fusion by fusing the match scores generated by the individual samples and decision level fusion with OR /AND logic. The signatures are acquired using WACOM digital pen tablet, fingerprints are collected using SecuGen Hamster fingerprint reader and webcam is used for acquiring the facial images. After pre processing of these samples, feature vectors from these templates are extracted using discrete cosine transform (DCT). These features are then examined first for their uni modal performances and then their combined performances under the three fusion schemes. Our experimental results on the image data set from 60 users confirm the usage of the proposed system in low security authentication as well as in high security authentication applications. On an average, the system needs around 0.08 seconds to authenticate a person under fusion schemes.

Keywords

Authentication, Biometrics, Discrete Cosine Transform and Image Fusion.

Full Text

     

Divya Jyoti ¹, Aman Chadha ¹, Pallavi Vaidya ¹, M. Mani Roja ²

Affiliations
1 Thadomal Shahani Engineering College, Mumbai, 400002, IN
2 Electronics and Telecommunication Engineering Department, Thadomal Shahani Engineering College, 400050, IN

Abstract

In the domain of Biometrics, recognition systems based on iris, fingerprint or palm print scans etc. are often considered more dependable due to extremely low variance in the properties of these entities with respect to time. However, over the last decade data processing capability of computers has increased manifold, which has made real-time video content analysis possible. This shows that the need of the hour is a robust and highly automated Face Detection and Recognition algorithm with credible accuracy rate. The proposed Face Detection and Recognition system using Discrete Wavelet Transform (DWT) accepts face frames as input from a database containing images from low cost devices such as VGA cameras, webcams or even CCTV‟s, where image quality is inferior. Face region is then detected using properties of L*a*b* color space and only Frontal Face is extracted such that all additional background is eliminated. Further, this extracted image is converted to grayscale and its dimensions are resized to 128 x 128 pixels. DWT is then applied to entire image to obtain the coefficients. Recognition is carried out by comparison of the DWT coefficients belonging to the test image with those of the registered reference image. On comparison, Euclidean distance classifier is deployed to validate the test image from the database. Accuracy for various levels of DWT Decomposition is obtained and hence, compared.

Keywords

Discrete Wavelet Transform, Face Detection, Face Recognition, Person Identification.

Full Text