Title: Cyber SecurityPlatform Solution Based on the Facial Image and Fingerprint

Issue Number: Vol. 8, No. 2
Year of Publication: Jun - 2019
Page Numbers: 166-176
Authors: Sulaiman Alshebli, Fatih Kurugollu, Mahmoud Shafik
Journal Name: International Journal of Cyber-Security and Digital Forensics (IJCSDF)
- Hong Kong
DOI:  http://dx.doi.org/10.17781/P002603


The recognition system based on the iris images are costly and required high resolution optical sensors and camera system beside the presence of the individual at the time of authentication and verification. The fingerprint recognition system may not be as complicated as iris recognition system but the requirement individual physical contact at the time of identification has limited usage. The face image may change in certain degree such as appearance but shape and structure of face skeleton , location of eyes, mouth, and nose are remain unchanged. Due to this remarkable characteristic and ability to generate the face image features with near perfect identifiers and lack of requirement for physical contact with recognition system has made the facial recognition system remarkable. Thus, the development of a complex facial recognition system extracted from the facial image could be used to identify the unauthorized users, hackers, and greatly improve the cyber security. The extracted features can be obtained from processing of the information stored on videos or facial images which captured from the scene even withoutcontact. Many recognition systems have been developed over the last fifty years, but one of the most accurate and fastest methods for identifying faces is based on the Eigen Analysis of face features. In this research program a hybrid technique for personal recognition based on facial image and fingerprint, using Discrete Wavelet Transform (DWT), is proposed and applied on Face image as well as Fingerprint image to create a compressed coded version of the information Then, Singular Value Decomposition (SVD) is applied on the coded image to find the Singular Values (SVs) of the coded image as the recognition feature. Once each SVs vector is formed, both vectors will be merged to obtain final feature vectors for recognition. The feature vectors will be used to compare against all other feature vectors stored inside the database to find the best match or no match. Three-level cryptography (scrambling, transformation, and XOR operation with secret key) will be used to secure the features vectors prior to storage on the databases or the cloud computing facilities. All feature vectors are stored inside our Face Image database. During the identification process the algorithm will calculate all sub image features and form a feature vector to be compared with existing feature vectors inside the database. The Euclidean Minimum Distance has been used to obtain the best match for the target image among the source images, and print the closest images or no match message.The initial research results and findings clearly indicates that the new hybrid method for individual recognition based on the DWT and SVD has greater results compared with DCT, DWT, or PCA methods.