Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
4 results
Search Results
Item Restricted Facial Profile Recognition Using Comparative Soft Biometrics(University of Southampton, 2024-08-15) Alamri, Malak; Mahmoodi, SasanThe identification of suspects in surveillance footage is crucial for maintaining public safety, preventing crime, conserving police resources, and aiding forensic investigations. Although eyewitness testimonies are valuable assets in numerous criminal cases, it is presently rather challenging to identify individuals in real-world closed-circuit television (CCTV) footage solely based on eyewitness descriptions. As a result, there has been a significant rise in the interest of using soft biometrics, which are physical and behavioural attributes that are used to semantically describe people under adverse surveillance conditions. Traditional biometrics are used when images or videos are available. Nevertheless, in certain instances, only eyewitness testimonies are available. In such scenarios, soft biometrics are applied to transform the eyewitness testimony into a collection of features that can be utilised for automated recognition. Furthermore, when images, videos and eyewitness testimonies are available, the fusion of soft biometrics with traditional biometrics becomes essential. The objective of this thesis is to investigate the integration of soft biometrics with traditional biometrics, enabling the search of video footage and biometric data based on descriptive information to identify suspects. The existing literature on facial soft biometrics mainly focuses on the frontal face, However this approach fails to acknowledge the importance of facial profiles, which have been demonstrated to be highly accurate. It is crucial to consider facial profiles because there are situations in which only these profiles are captured in images and videos from surveillance and security cameras. In such instances, existing facial recognition algorithms designed for frontal views are ineffective, emphasising the necessity for recognition systems specifically tailored for profile faces. This thesis builds upon previous research on using soft biometrics for human recognition, with a specific emphasis on the potential of soft biometrics in identifying facial profiles. Soft biometrics involves crowdsourcing human annotations through ordered and similarity comparisons. Advanced machine learning techniques are also used to estimate comparative attributes from images. In addition, we analyse the attribute’s correspondence between the traditional biometric and soft biometric based on facial profiles. Therefore, we have bridged the gap between human perception and computer vision for facial profile biometric. In comparison to prior work on facial profiles, the developed approaches have demonstrated a higher level of performance. Our findings indicate that the performance of the system further improves after fusing the semantic and visual spaces. Furthermore, this thesis examines the bilateral symmetry of human facial profiles and develops a method for extracting features from facial profiles, inspired by the few-shot learning framework. Our algorithm, which is based on few-shot learning, achieves an impressive level of accuracy even when working with datasets containing a large number of subjects and low number of samples per subject.37 0Item Restricted A Cognimetric Authentication Tool (CAT): Temporal Analysis of Touch Dynamics(University of Sussex, 2024) Alwhibi, Munirah; Cheng, PeterMuch research in touch biometric authentication is grounded in a pragmatic, data-driven methodology, involving the collection and analysis of touch data to train machine learning models. In contrast, this research explores the integration of established theories of human cognition and interactive behaviour to inform the design of a Cognimetric Authentication Tool (CAT). In the field of cognitive science, time related measures are widely used to differentiate individuals during task performance. This investigation analyses two temporal measures of swipe and scroll interactions: touch durations (touch) and durations between touches (gap). An existing dataset, comprising interactions from 41 participants engaged in two realistic and cognitively demanding tasks—reading Wikipedia articles (read) and comparing image pairs (compare)—is utilised. The goal of this research is to develop methods for capturing, modelling and comparing participant behaviours for potential authentication applications. It adopts histograms to model and compare temporal behaviours based on the shapes of frequency distributions of each measure within each task. The metric Absolute Distribution Difference (ADD) is introduced by this research to quantify the consistency of temporal behaviour within participants and its distinctiveness across participants. The analysis reveals that intra-participant variations (inconsistency) are overshadowed by inter-participant differences (distinctiveness), which is necessary for authentication. However, the intricate relationship between them emphasises a trade-off; neither is independently sufficient for authentication. Trained only on genuine user’s behaviour, CAT drops error rates to around 10% for a single measure and halving to 5% when combining two measures. To accomplish this, CAT utilises 4 user profiles per participant, tailored to each measure and task, and consisting of the average behaviour of a participant and their personal inconsistency thresholds. This multi-level personalisation approach can compensate for the natural variability and context-dependent nature of human behaviour, and it extends to the fusion functions. Through the research, two sampling techniques are employed: initially, using the entire document as a sample, and subsequently, adopting action-based sampling (a conventional technique). In their current state, both sampling techniques are eligible for delayed authentication, as second factor authentication. Similarly, two fusion methods are employed: measures are combined within the same tasks (a conventional technique), and across tasks, providing complementing aspects of task-specific behaviours. Both sampling and fusion techniques prove effective particularly in relation to the previous research conducted with this dataset.12 0Item Restricted The Effect of Using Biometric Credential in Authentication Process on Password Memorability(Saudi Digital Library, 2021-12-31) Alhamed, Abdulrahman Salem; Bhatia, SajalAuthentication is a process to make sure with the utmost certainty that users is who is pretending to be. Passwords are the most common authentication mechanism “something user know” that defenses against unauthorized access to com puters and personal information. Another common authentication mechanism is bio-metrics credential “something user are” like Face-id, Fingerprint, Voice recognition. However, due to the nature of biometrics that users do not create or remember it. Biometrics being more convenience then, users stop using passwords for a while. With increase online accounts’ number and password complexity rules, users struggle to create a different password for each account and remember each one that created differently. Consequently, for these challenges, there has been increasing in insecure users’ behaviors such as using predictable data, personal information, dictionary words, or a unified password. These habits expose users and organizations to intensive risk. Password memorability increasing is an important factor to reduce users’ insecure behaviors. A survey was conducted to measure the effect of using biometrics for a while on the ability to remember passwords and found that the majority of users were affected and would like to user a method to help them generate password. So, VowPass was proposed to facilitate secure password generation which not only improved memorability but also reduces the chances of a successful dictionary and brute attack.24 0Item Restricted Machine Learning Methods for Human Identification from Dorsal Hand Images(2023-06-27) Alghamdi, Mona; Angelov, Plamen; Rahmani, HusseinPerson identification is a process that uniquely identifies an individual based on physical or behavioural traits. This study investigates methods for the analysis of images of the human hand, focusing on their uniqueness and potential use for human identification. The human hand has significant and distinctive characteristics, and is highly complex and interesting, yet it has not been explored in much detail, particularly in the context of the contemporary high level of digitalisation and, more specifically, the advances in artificial intelligence (AI), machine learning (ML) and computer vision (CV). This research area is highly multi-disciplinary, involving anatomists, anthropologists, bioinformaticians, image analysts and, increasingly, computer scientists. A growing pool of advanced methods based on AI, ML and CV can benefit and relate directly to a better representation of the human hand in computer analysis. Historically, the research methods in this area relied on ‘handcrafted’ features such as the local binary pattern (LBP) and histogram of gradient (HOG) extraction, which necessitated human intervention. However, such approaches struggle to encode the human hand in variable conditions effectively, because of the change in camera viewpoint, hand pose, rotation, image quality, and self-occlusion. Thus, their performance is limited. Recently, there has been a surge of interest in deep learning neural network (DLNN) approaches, specifically convolutional neural networks (CNNs), due to the highly accurate results achieved in many applications and the wide availability of images. This work investigates advanced methods based on ML and DLNN for segmenting hand images with various rotation changes into different patches (e.g., knuckles and fingernails). The thesis focuses on developing ML methods like pre-trained CNN models on the 'ImageNet' dataset to learn the underlying structure of the human hand by extracting robust features from hand images with diverse conditions of rotation, and image quality. Also, this study investigates fine-tuning the pre-trained models of DLNN on subsets of hand images, as well as using various similarity metrics to find the best match of the individual’s hand. Furthermore, this work explores different types of ensemble learning or fusions, those of different region and similarity metrics to improve human identification results. This thesis also presents a study of a Siamese network on sub-images or segments of human dorsal hands for identification tasks. All presented approaches are compared with the state-of-the-art methods. This study advances the understanding of variations in and the uniqueness of humans using patches of their hands (e.g., different types of knuckles and fingernails). Lastly, it compares the matching performances of the left- and right-hand patches using various hand datasets and investigates whether the fingernail produces better identification results than the knuckles. This research shows that the proposed framework for person identification based on hand components led to better person identification results. The framework consists of vital feature extractions based on deep learning neural network (DLNN) and similarity metrics. These elements enhanced the performance. Also, the fingernails' shape performed better than other hand components, including the base, major, and minor knuckles. The left hand can be more distinguishable to individuals than the right hand. The fine-tuning of the hand components and ensemble learning improved the identification results.38 0