Maleika Heenaye-Mamode Khan

Representation of Hand Dorsal Vein Features Using a Low Dimensional Representation Integrating Cholesky Decomposition

Dorsal hand vein pattern is a promising biometric which is attracting the attention of researchers, of late, to provide more secure identification system. Different approaches have been developed to extract the vein pattern. However, there is a need to find more efficient methods which can reduce matching time. In this work, Principle Component Analysis (PCA), which is a successful method applied on human faces and hand geometry, is being modified based on Cholesky decomposition to represent low dimensional features of the vein pattern. Cholesky decomposition is used to simplify the matrices and it is noticed that there is no loss of information regarding the matching of the eigenveins. The time taken for the processing phase is reduced by 6s which is desirable when developing biometric security system. The system was tested successfully on a database of 200 images with a threshold value of 0.9.

Impact of Changing Parameters when Preprocessing Dorsal Hand Vein Pattern

Abstract Dorsal hand vein biometric has been the driving force for many researchers lately. The latters have adopted several approaches for preprocessing the vein pattern, extracting its features and matching. Preprocessing steps play an important role in a biometric security system since it allows obtaining the features required for later stages.In line with this, the preprocessing steps of the dorsal hand vein pattern are being scrutinized in a view of procuringideal vein features. Recently more attention is being given to processing and matching stages of a biometric security system. It is therefore mandatory to investigate on the preprocessing factors that affect the performance of a biometric system. Thus, in this work, different preprocessing techniques are being investigated.A database of 500 images is considered for which same number of images and instances are used. Through experimentation, it is found that different techniques give different results which have an impact on the later stages. The result proves that a well-defined extracted vein pattern gives better performance and leads to a more secure biometric authentication system.

Investigating linear discriminant analysis (LDA) on dorsal hand vein images

Hand vein biometrics is gaining popularity over other biometrics due to its uniqueness and stability. However, the variations of images at image capture process pose a challenge in the performance of a biometric security system. Different processing techniques applied so far on dorsal hand vein images cannot represent the different orientation of the dorsal hand vein patterns at image capture. In this view, linear discriminant analysis (LDA) is adopted to represent oriented vein images. This method handles the within-class scatter and the between class-scatter between image sets compared to other methods like principal component analysis (PCA) and Independent component analysis (ICA). It maximizes the ratio of between-class scatter to the within-class scatter and guarantees the maximal separability between the data. In this work, images are captured at varied angles between 0° and 45°. Both PCA and LDA have been implemented to determine their behavior on varied angled images. After experimentations with the methods, it can be concluded that LDA outperforms PCA on images captured at varied angled.

Representation of Dorsal Hand Vein Pattern Using Local Binary Patterns (LBP)

In this revolutionized and digital world, the increasing need of security to protect individuals and information has led to a rise in developing biometric systems over traditional security systems such as pincode and password. Finding more reliable, practical and more acceptable biometrics and techniques are attracting the attention of researchers. Recently, hand vein pattern biometrics has gained increasing interest from both research communities and industries. Researchers are exploiting the different biometric phases by applying existing techniques or devising new ones to develop enhanced biometric systems. Up to now, most researchers have thinned the dorsal hand vein pattern and apply corresponding techniques for feature representation and matching. However, not many techniques have been explored with relation to considering the whole hand vein image. In this research work, local binary pattern, which is a powerful technique for representing texture description of an image, have been applied on dorsal hand vein images. This method outperforms existing vein representation techniques by having a recognition rate of 98.4% on a database of more than 1000 images. In addition, this proposed method has no effect on rotated images, which is desirable in any biometric security system.

Feature extraction techniques for dorsal hand vein pattern

So far many biometric systems such as fingerprint, palm print and iris have been developed for several years. Nowadays, many researchers are interested in developing new and more efficient biometric systems by using alternative features. In line with this, a newer characteristic that is dorsal hand vein patterns are used to identify an individual because its uniqueness, reliability, permanence and difficulty to forge. To develop a dorsal hand vein biometric security system, the hand vein images are first captured using an appropriate setup. Several preprocessing techniques are then applied to obtain a thinned version of the image. One challenging phase in biometric security system is the feature extraction phase. In this work, three feature extraction and representation techniques namely Hough lines transform, Pixel by Pixel Method and Directional Coding Method have been explored and implemented. These techniques are applied on 500 images obtained from 100 individuals of different age. For matching, Mahalanobis Distance and Correlation Percentage have been used. From the experimental results, it was deduced that Pixel by Pixel Method proved to be the best feature extraction technique with a False Rejection Rate (FRR) of 0.03%.

Analysing Factors Affecting Hand Biometrics during Image Capture

Abstract As more people are connected digitally, a highly automatic personal identification system is crucial. Dorsal hand vein biometric is an emerging biometric characteristic which is explored at its full swing. Although, researchers have deployed many hand biometrics using interesting techniques, it has not yet been accepted in many applications. Images capture is an important phase where the images obtained determine the performance of the biometric security system. Environmental factors and behavior of the subjects have an effect on image capture. In these work, different variables, that is, distance between camera and hand, the angle of deviation and the environmental temperature are controlled to capture images. The results are analysed and the effect of the variables have been depicted. It is deduced that image capture phase in biometric applications deserve more attention.

Using photomosaic and steganographic techniques for hiding information inside image mosaics

In this digital world, transferring sensitive data electronically has become inevitable. The objective of this work is to hide and retrieve confidential information in image mosaics. The photomosaic approach has been used for the creation of the mosaic and the least significant bit (LSB) technique has been adopted for the embedding of the hidden information. The construction of the photomosaic is done by selecting an image, splitting it into smaller images (tiles) of sizes 8×8, 16×16 and 32×32. These tiles are then compared from a very large amount of photos of the same sizes. Next, the user can either hide a secret image or a secret text into them. The final mosaic image contains secret information that is well-concealed and is impossible to find out with the naked eye. This technique is more robust compared to modifying the bits of the original image directly.