Khaled Ahmed Nagaty

Fingerprints classification using artificial neural networks: a combined structural and statistical approach

This paper describes a fingerprint classification algorithm using Artificial Neural Networks (ANN). Fingerprints are classified into six categories: arches, tented arches, left loops, right loops, whorls and twin loops. The algorithm extracts a string of symbols using the block directional image of a fingerprint, which represents the set of structural features for this image. The moment representing the statistical feature of the pattern is computed for this string and its Euclidean Distance Measures (EDM) are computed by using this moment. Our discrimination system uses a multilayer artificial neural network composed of six subnetworks one for each class. The classifier was tested on 1,500 images of good quality in the Egyptian Fingerprints database; images with poor quality were rejected. In the six-class problem the network achieved 95% classification accuracy. In the five-class problem when we place whorls and twin loops together in the same category the classification accuracy was around 99%. In the four-class problem when we place arches and tented arches in the same class the classification accuracy was 99%.

On learning to estimate the block directional image of a fingerprint using a hierarchical neural network

This paper presents a hierarchical neural network architecture for computing fingerprints block directional images. Two separately trained neural networks are connected in series. First, the fingerprint image is divided into 16x16 blocks, each block is submitted to the first network which is a back propagation neural network. It has four counters in its output layer one for each direction to count the main directional codes in each fingerprint block. The output of this network is considered the feature vector for the fingerprint block, which is then submitted to the second network. The second network is a self-organized feature maps neural network uses an unsupervised learning strategy to group the fingerprint blocks into distinct directional classes. In this scheme, there is more than one sub-class for each directional class, an agglomerative hierarchical cluster algorithm for merging two clusters is used to merge two classes if their corresponding distances are below a specified threshold. Results obtained with a real world data set indicate the effectiveness of the proposed architecture.

A robust content-based image retrieval system using multiple features representations

The similarity measurements and the representation of the visual features are two important issues in content-based image retrieval (CBIR). In this paper, we compared between the combination of wavelet-based representations of the texture feature and the color feature with and without using the color layout feature. To represent the color information, we used global color histogram (GCH) beside the color layout feature and with respect to the texture information; we used Haar and Daubechies wavelets. Based on some commonly used Euclidean and Non-Euclidean similarity measures, we tested different categories of images and measured the retrieval accuracy when combining such techniques. The experiments showed that the combination of GCH and 2-D Haar wavelet transform using the cosine distance gives good results while the best results obtained when adding the color layout feature to this combination by using the Euclidean distance. The results reflected the importance of using the spatial information beside the color feature itself and the importance of choosing good similarity distance measurements.

An adaptive hybrid energy-based fingerprint matching technique

In this paper we present a new adaptive hybrid energy-based fingerprint matching system, which combines both minutiae information available in a fingerprint with the information of the local ridges in their vicinity. A more continuous representation of fingerprints can be obtained by using an energy-based rectangular tessellation with non-overlapped squared cells. However, a fixed tessellation is not efficient in handling non-linear deformations in fingerprints for which we propose an adaptive matching technique that uses dynamic rectangular tessellation to handle them. Each time a match is not found the dynamic tessellation increases its cell size until there is a match or cell size is greater than image size where the fingerprint is rejected. The basic idea of this system is to divide the fingerprint-matching problem into several small sub-problems that involve the use of cell energy minimization for which an iterative schema is devised. At each minimization step this schema optimizes its local energy according to the previous estimate and the observed image features. Minutiae and local ridges in their vicinity, produce different amounts of energy which form the energy vectors of the fingerprint image. In this work, we focus on the difficult problem of recognizing known fingerprints while rejecting unknown ones. Our system was tested on FVC2000 benchmark database of fingerprints and showed promising results. We show that matching performance can be improved by using energy vectors and adaptive matching, where adaptive matching reduces the effect of intra-class variations between different impressions of the same fingerprint image and energy vectors can efficiently represent fingerprints by using both information extracted from the minutiae and their local surrounding ridges.

DNA-based cryptographic methods for data hiding in DNA media

Information security can be achieved using cryptography, steganography or a combination of them, where data is firstly encrypted using any of the available cryptography techniques and then hid into any hiding medium. Recently, the famous genomic DNA has been introduced as a hiding medium, known as DNA steganography, due to its notable ability to hide huge data sets with a high level of randomness and hence security. Despite the numerous cryptography techniques, to our knowledge only the vigenere cipher and the DNA-based playfair cipher have been combined with the DNA steganography, which keeps space for investigation of other techniques and coming up with new improvements. This paper presents a comprehensive analysis between the DNA-based playfair, vigenere, RSA and the AES ciphers, each combined with a DNA hiding technique. The conducted analysis reports the performance diversity of each combined technique in terms of security, speed, hiding capacity in addition to both key size and data size. Moreover, this paper proposes a modification of the current combined DNA-based playfair cipher technique, which makes it not only simple and fast but also provides a significantly higher hiding capacity and security. The conducted extensive experimental studies confirm such outstanding performance in comparison with all the discussed combined techniques.

An Enhanced Histogram Matching Approach Using the Retinal Filter's Compression Function for Illumination Normalization in Face Recognition

Although many face recognition techniques have been proposed, recent evaluations in FRVT2006 conclude that relaxing the illumination condition has a dramatic effect on their recognition performance. Among many illumination normalization approaches, histogram matching (HM) is considered one of the most common image-processing-based approaches to cope with illumination. This paper introduces a new illumination normalization approach based on enhancing the image resulting from the HM using the gamma correction and the Retinal filters compression function; we call it GAMMA-HM-COMP approach. Rather than many other approaches, the proposed one proves its flexibility to different face recognition methods and the suitability for real-life systems in which perfect aligning of the face is not a simple task. The efficiency of the proposed approach is empirically demonstrated using both a PCA-based (Eigenface) and a frequency-based (Spectroface) face recognition methods on both aligned and non-aligned versions of Yale B database. It leads to average increasing in recognition rates ranges from 4 ~ 7 % over HM alone.

An energy-based fingerprint matching system

In this paper, we present a new energy-based fingerprint matching system which uses both minutiae information available in a fingerprint with the information of the local ridges in their vicinity. The basic idea of this system is to divide the fingerprint matching problem into several small sub-problems that involve the use of image energy minimization for which an iterative schema is devised. At each minimization step this schema optimizes its local energy according to the previous estimate and the observed image features. Energy vectors are produced which represent the fingerprint image. Our system was tested on NIST 4 fingerprints and showed promising results.

An Enhanced DNA-based Steganography Technique with a Higher Hiding Capacity

DNA-based Steganography is one of the promising techniques to secure data exchange, where data is hidden into a real DNA sequence. For the sake of security, some steganography techniques encrypt data before hiding it which strengthen the technique’s steganalysis. One of the widely used encryption techniques is the DNAbased playfair cipher. This technique intensively requires a long list of preprocessing steps in addition to extra bits which must be added to guarantee successful decryption. Nevertheless, the succeeding hiding step suffers from a limited capacity, which turns this current DNA-based Steganography technique into a complex, inefficient, and time consuming process. In this paper, we propose a new DNA-based Steganography algorithm to simplify the current technique as well as achieve higher hiding capacity. In the proposed algorithm, we enhance the commonly used playfair cipher by defining a novel short sequence of preprocessing steps and getting rid of the extra overhead bits. We also utilize a more efficient technique to enhance the hiding phase. The proposed approach is not only simple and fast but also provides a significantly higher hiding capacity with a high security. The conducted extensive experimental studies confirm the outstanding performance of the proposed algorithm.

Apparel coordination based on contour and dominant colours matching

The paper proposes a mobile application for clothing coordination, which could be of great benefit for stores and people seek for fashion advices. The application matches apparel image input with, previously saved apparel images, and then provides the user with the possible matching suggestions based on the apparel outline and dominating colors. For this purpose two Region of Interest (ROI) extraction components were developed, to facilitate apparel outline classification and color extraction. Two-level binary support vector machines were trained for apparels classification into top, skirt or pair of trousers. K-means algorithm was used for recognizing the apparels dominant colors. The colour matching is offered through analogous and complementary matching; K-nearest neighbor algorithm was adopted for this purpose. The application was developed and tested on Android 2.2 (Froyo) and the results showed that: (1) the application is able to classify apparels at high accuracy, (2) The proposed color recognition and matching strategies outperform the current ones.

A Secured Hybrid Cloud Architecture for mHealth Care

This chapter presents a secure mHealth application which is based on hybrid cloud architecture combined with cryptographic techniques to protect data privacy, integrity and security of patients and health care givers and with role based access control to authenticate and authorize cloud users. Hybrid cloud platform combines the advantages of both the private cloud which guarantees privacy and safety of data and the public cloud which provides a platform for reduced services costs. Integrating cryptography and role based access control with hybrid cloud computing ensures the safety of patients’ medical records and enables user authentication and authorization for access control. This integrated technology can provide mHealth care the required safety and privacy to flourish.