This work focuses on facial processing, which refers to artificial intelligence (AI) systems that take facial images or videos as input data and perform some AI-driven processing to obtain higher-level information (e.g. a person's identity, emotions, demographic attributes) or newly generated imagery (e.g. with modified facial attributes). Facial processing tasks, such as face detection, face identification, facial expression recognition or facial attribute manipulation, are generally studied as separate research fields and without considering a particular scenario, context of use or intended purpose. This paper studies the field of facial processing in a holistic manner. It establishes the landscape of key computational tasks, applications and industrial players in the field in order to identify the 60 most relevant applications adopted for real-world uses. These applications are analysed in the context of the new proposal of the European Commission for harmonised rules on AI (the AI Act) and the 7 requirements for Trustworthy AI defined by the European High Level Expert Group on AI. More particularly, we assess the risk level conveyed by each application according to the AI Act and reflect on current research, technical and societal challenges towards trustworthy facial processing systems. 

/pdf/the-landscape-of-facial-processing-applications-in-the-3c0ybrrf.pdf

The landscape of facial processing applications in the context of the European AI Act and the development of trustworthy systems

Head pose assessment can reveal important clinical information on human motor control. Quantitative assessment have the potential to objectively evaluate head pose and movements’ specifics, in order to monitor the progression of a disease or the effectiveness of a treatment. Optoelectronic camera-based motion-capture systems, recognized as a gold standard in clinical biomechanics, have been proposed for head pose estimation. However, these systems require markers to be positioned on the person’s face which is impractical for everyday clinical practice. Furthermore, the limited access to this type of equipment and the emerging trend to assess mobility in natural environments support the development of algorithms capable of estimating head orientation using off-the-shelf sensors, such as RGB cameras. Although artificial vision is a popular field of research, limited validation of human pose estimation based on image recognition suitable for clinical applications has been performed. This paper first provides a brief review of available head pose estimation algorithms in the literature. Current state-of-the-art head pose algorithms designed to capture the facial geometry from videos, OpenFace 2.0, MediaPipe and 3DDFA_V2, are then further evaluated and compared. Accuracy is assessed by comparing both approaches to a baseline, measured with an optoelectronic camera-based motion-capture system. Results reveal a mean error lower or equal to 5.6∘ for 3DDFA_V2 depending on the plane of movement, while the mean error reaches 14.1∘ and 11.0∘ for OpenFace 2.0 and MediaPipe, respectively. This demonstrates the superiority of the 3DDFA_V2 algorithm in estimating head pose, in different directions of motion, and suggests that this algorithm can be used in clinical scenarios.

/pdf/evaluation-of-various-state-of-the-art-head-pose-estimation-1u5el2lq.pdf

Evaluation of Various State of the Art Head Pose Estimation Algorithms for Clinical Scenarios

Comprehensive evaluation of eco-environmental resources in the main grain-producing areas of China

Impact of Jupyter Notebook as a tool to enhance the learning process in chemical engineering modules

The paper presents results of experimental studies of a vibration-driven propulsion system for mobile worm-like robots. The propulsion system is made from standard electromagnetic relays of small ratings. Such the relatively simple design can be used to develop students’ skills in experimental works. Besides, this construction also makes it easy to understand the basics of vibration-driven worm-like robots and the principles of their control. The locomotion of the worm-like robot was implemented on a horizontal surface inside linear guides. The paper describes the simplest open-loop control system. The main parameters that affect the speed of locomotion were studied. It was found that the average speed of directional movement is on the order of 1 mm per second. The magnitude of the applied voltage practically does not influence the average speed. On the other hand, an increase in frequency leads to a near directly proportional increase in the average speed. 

Rapid-Prototyping of Vibration-Driven Propulsion System for Robots and its Investigation

Jupyter notebooks are recently emerging as a valuable pedagogical resource in academy, being adopted in educational institutions worldwide. This is mainly due to their ability to combine the expressiveness of traditional explanations from textbooks, with the interaction capabilities of software applications, which provides numerous benefits for both students and lecturers of different fields. One of the areas that could benefit from their adoption is such of mobile robotics, whose recent popularity has resulted in an increasing demand of trained practitioners with a solid theoretical and practical background. Therefore, there is a need of high quality learning materials adapted to modern tools and methodologies. With that in mind, this work explores how the introduction of Jupyter notebooks in undergraduate mobile robotic courses contributes to improve both teaching and learning experiences. For that, we first present a series of (publicly available) educational notebooks encompassing a variety of topics relevant for robotics, with a particular emphasis in the study of mobile robots and commonly used sensors. Those documents have been built from the ground up to take advantage of the Jupyter Notebook framework, bridging the typical gap between theoretical frame and interactive code. We also present a case study describing the notebooks usage in undergraduate courses at University of Malaga, including a discussion on the promising results and findings obtained.

Jupyter Notebooks in Undergraduate Mobile Robotics Courses: Educational Tool and Case Study

Assistive robots collaborating with people demand strong Human-Robot interaction capabilities. In this way, recognizing the person the robot has to interact with is paramount to provide a personalized service and reach a satisfactory end-user experience. To this end, face recognition: a non-intrusive, automatic mechanism of identification using biometric identifiers from an user's face, has gained relevance in the recent years, as the advances in machine learning and the creation of huge public datasets have considerably improved the state-of-the-art performance. In this work we study different open-source implementations of the typical components of state-of-the-art face recognition pipelines, including face detection, feature extraction and classification, and propose a recognition system integrating the most suitable methods for their utilization in assistant robots. Concretely, for face detection we have considered MTCNN, OpenCV's DNN, and OpenPose, while for feature extraction we have analyzed InsightFace and Facenet. We have made public an implementation of the proposed recognition framework, ready to be used by any robot running the Robot Operating System (ROS). The methods in the spotlight have been compared in terms of accuracy and performance in common benchmark datasets, namely FDDB and LFW, to aid the choice of the final system implementation, which has been tested in a real robotic platform.

/pdf/a-face-recognition-system-for-assistive-robots-15rcmkwtd5.pdf

A Face Recognition System for Assistive Robots

Face recognition is a technology with great potential in the field of robotics, due to its prominent role in human-robot interaction (HRI). This interaction is a keystone for the successful deployment of robots in areas requiring a customized assistance like education and healthcare, or assisting humans in everyday tasks. These unconstrained environments present additional difficulties for face recognition, extreme head pose variability being one of the most challenging. In this paper, we address this issue and make a fourfold contribution. First, it has been designed a tool for gathering an uniform distribution of head pose images from a person, which has been used to collect a new dataset of faces, both presented in this work. Then, the dataset has served as a testbed for analyzing the detrimental effects this problem has on a number of state-of-the-art methods, showing their decreased effectiveness outside a limited range of poses. Finally, we propose an optimization method to mitigate said negative effects by considering key pose samples in the recognition system's set of known faces. The conducted experiments demonstrate that this optimized set of poses significantly improves the performance of a state-of-the-art, cutting-edge system based on Multitask Cascaded Convolutional Neural Networks (MTCNNs) and ArcFace.

Samuel-Felipe Baltanas

Papers

Jupyter Notebooks in Undergraduate Mobile Robotics Courses: Educational Tool and Case Study

A Face Recognition System for Assistive Robots

Improving the Head Pose Variation Problem in Face Recognition for Mobile Robots.