An End-to-End Automated License Plate Recognition System Using YOLO Based Vehicle and License Plate Detection with Vehicle Classification.

An accurate and robust Automatic License Plate Recognition (ALPR) method proves surprising versatility in an Intelligent Transportation and Surveillance (ITS) system. However, most of the existing approaches often use prior knowledge or fixed pre-and-post processing rules and are thus limited by poor generalization in complex real-life conditions. In this paper, we leverage a YOLO-based end-to-end generic ALPR pipeline for vehicle detection (VD), license plate (LP) detection and recognition without exploiting prior knowledge or additional steps in inference. We assess the whole ALPR pipeline, starting from vehicle detection to the LP recognition stage, including a vehicle classifier for emergency vehicles and heavy trucks. We used YOLO v2 in the initial stage of the pipeline and remaining stages are based on the state-of-the-art YOLO v4 detector with various data augmentation and generation techniques to obtain LP recognition accuracy on par with current proposed methods. To evaluate our approach, we used five public datasets from different regions, and we achieved an average recognition accuracy of 90.3% while maintaining an acceptable frames per second (FPS) on a low-end GPU.

A Survey of Alzheimer's Disease Early Diagnosis Methods for Cognitive Assessment.

Dementia is a syndrome that is characterised by the decline of different cognitive abilities. A high rate of deaths and high cost for detection, treatments, and patients care count amongst its consequences. Although there is no cure for dementia, a timely diagnosis helps in obtaining necessary support, appropriate medication, and maintenance, as far as possible, of engagement in intellectual, social, and physical activities. The early detection of Alzheimer Disease (AD) is considered to be of high importance for improving the quality of life of patients and their families. In particular, Virtual Reality (VR) is an expanding tool that can be used in order to assess cognitive abilities while navigating through a Virtual Environment (VE). The paper summarises common AD screening and diagnosis techniques focusing on the latest approaches that are based on Virtual Environments, behaviour analysis, and emotions recognition, aiming to provide more reliable and non-invasive diagnostics at home or in a clinical environment. Furthermore, different AD diagnosis evaluation methods and metrics are presented and discussed together with an overview of the different datasets.

Assessing the Effectiveness of Automated Emotion Recognition in Adults and Children for Clinical Investigation.

Recent success stories in automated object or face recognition, partly fuelled by deep learning artificial neural network (ANN) architectures, have led to the advancement of biometric research platforms and, to some extent, the resurrection of Artificial Intelligence (AI). In line with this general trend, inter-disciplinary approaches have been taken to automate the recognition of emotions in adults or children for the benefit of various applications, such as identification of children's emotions prior to a clinical investigation. Within this context, it turns out that automating emotion recognition is far from being straightforward, with several challenges arising for both science (e.g., methodology underpinned by psychology) and technology (e.g., the iMotions biometric research platform). In this paper, we present a methodology and experiment and some interesting findings, which raise the following research questions for the recognition of emotions and attention in humans: (a) the adequacy of well-established techniques such as the International Affective Picture System (IAPS), (b) the adequacy of state-of-the-art biometric research platforms, (c) the extent to which emotional responses may be different in children and adults. Our findings and first attempts to answer some of these research questions are based on a mixed sample of adults and children who took part in the experiment, resulting in a statistical analysis of numerous variables. These are related to both automatically and interactively captured responses of participants to a sample of IAPS pictures.

Evaluation of different chrominance models in the detection and reconstruction of faces and hands using the growing neural gas network.

Physical traits such as the shape of the hand and face can be used for human recognition and identification in video surveillance systems and in biometric authentication smart card systems, as well as in personal health care. However, the accuracy of such systems suffers from illumination changes, unpredictability, and variability in appearance (e.g. occluded faces or hands, cluttered backgrounds, etc.). This work evaluates different statistical and chrominance models in different environments with increasingly cluttered backgrounds where changes in lighting are common and with no occlusions applied, in order to get a reliable neural network reconstruction of faces and hands, without taking into account the structural and temporal kinematics of the hands. First a statistical model is used for skin colour segmentation to roughly locate hands and faces. Then a neural network is used to reconstruct in 3D the hands and faces. For the filtering and the reconstruction we have used the growing neural gas algorithm which can preserve the topology of an object without restarting the learning process. Experiments conducted on our own database but also on four benchmark databases (Stirling's, Alicante, Essex, and Stegmann's) and on deaf individuals from normal 2D videos are freely available on the BSL signbank dataset. Results demonstrate the validity of our system to solve problems of face and hand segmentation and reconstruction under different environmental conditions.

Real Time Hand Movement Trajectory Tracking for Enhancing Dementia Screening in Ageing Deaf Signers of British Sign Language.

Real time hand movement trajectory tracking based on machine learning approaches may assist the early identification of dementia in ageing Deaf individuals who are users of British Sign Language (BSL), since there are few clinicians with appropriate communication skills, and a shortage of sign language interpreters. Unlike other computer vision systems used in dementia stage assessment such as RGBD video with the aid of depth camera, activities of daily living (ADL) monitored by information and communication technologies (ICT) facilities, or X-Ray, computed tomography (CT), and magnetic resonance imaging (MRI) images fed to machine learning algorithms, the system developed here focuses on analysing the sign language space envelope (sign trajectories/depth/speed) and facial expression of deaf individuals, using normal 2D videos. In this work, we are interested in providing a more accurate segmentation of objects of interest in relation to the background, so that accurate real-time hand trajectories (path of the trajectory and speed) can be achieved. The paper presents and evaluates two types of hand movement trajectory models. In the first model, the hand sign trajectory is tracked by implementing skin colour segmentation. In the second model, the hand sign trajectory is tracked using Part Affinity Fields based on the OpenPose Skeleton Model [1, 2]. Comparisons of results between the two different models demonstrate that the second model provides enhanced improvements in terms of tracking accuracy and robustness of tracking. The pattern differences in facial and trajectory motion data achieved from the presented models will be beneficial not only for screening of deaf individuals for dementia, but also for assessment of other acquired neurological impairments associated with motor changes, for example, stroke and Parkinson's disease.

Fast 2D/3D object representation with growing neural gas.

This work presents the design of a real-time system to model visual objects with the use of self-organising networks. The architecture of the system addresses multiple computer vision tasks such as image segmentation, optimal parameter estimation and object representation. We first develop a framework for building non-rigid shapes using the growth mechanism of the self-organising maps, and then we define an optimal number of nodes without overfitting or underfitting the network based on the knowledge obtained from information-theoretic considerations. We present experimental results for hands and faces, and we quantitatively evaluate the matching capabilities of the proposed method with the topographic product. The proposed method is easily extensible to 3D objects, as it offers similar features for efficient mesh reconstruction.

Autonomous Growing Neural Gas for applications with time constraint: optimal parameter estimation.

This paper aims to address the ability of self-organizing neural network models to manage real-time applications. Specifically, we introduce fAGNG (fast Autonomous Growing Neural Gas), a modified learning algorithm for the incremental model Growing Neural Gas (GNG) network. The Growing Neural Gas network with its attributes of growth, flexibility, rapid adaptation, and excellent quality of representation of the input space makes it a suitable model for real time applications. However, under time constraints GNG fails to produce the optimal topological map for any input data set. In contrast to existing algorithms, the proposed fAGNG algorithm introduces multiple neurons per iteration. The number of neurons inserted and input data generated is controlled autonomous and dynamically based on a priory or online learnt model. A detailed study of the topological preservation and quality of representation depending on the neural network parameter selection has been developed to find the best alternatives to represent different linear and non-linear input spaces under time restrictions or specific quality of representation requirements.