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

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 659
Author(s):  
Samuel-Felipe Baltanas ◽  
Jose-Raul Ruiz-Sarmiento ◽  
Javier Gonzalez-Jimenez
Keyword(s):  
Neural Networks ◽  
Face Recognition ◽  
State Of The Art ◽  
Optimization Method ◽  
Limited Range ◽  
Human Robot Interaction ◽  
Head Pose ◽  
Negative Effects ◽  
Robot Interaction ◽  
Pose Variation

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.

scholarly journals Question-aware memory network for multi-hop question answering in human–robot interaction

2021 ◽  
Author(s):  
Xinmeng Li ◽  
Mamoun Alazab ◽  
Qian Li ◽  
Keping Yu ◽  
Quanjun Yin
Keyword(s):  
Question Answering ◽  
State Of The Art ◽  
Human Robot Interaction ◽  
Knowledge Graph ◽  
Robot Interaction ◽  
Natural Language Question ◽  
Memory Network ◽  
The Given ◽  
Fine Tune ◽  
Language Question

AbstractKnowledge graph question answering is an important technology in intelligent human–robot interaction, which aims at automatically giving answer to human natural language question with the given knowledge graph. For the multi-relation question with higher variety and complexity, the tokens of the question have different priority for the triples selection in the reasoning steps. Most existing models take the question as a whole and ignore the priority information in it. To solve this problem, we propose question-aware memory network for multi-hop question answering, named QA2MN, to update the attention on question timely in the reasoning process. In addition, we incorporate graph context information into knowledge graph embedding model to increase the ability to represent entities and relations. We use it to initialize the QA2MN model and fine-tune it in the training process. We evaluate QA2MN on PathQuestion and WorldCup2014, two representative datasets for complex multi-hop question answering. The result demonstrates that QA2MN achieves state-of-the-art Hits@1 accuracy on the two datasets, which validates the effectiveness of our model.

scholarly journals User-centred design of humanoid robots’ communication

2020 ◽  
Vol 12 (1) ◽  
pp. 58-73
Author(s):  
Sofia Thunberg ◽  
Tom Ziemke
Keyword(s):  
Mental Models ◽  
Participatory Design ◽  
Humanoid Robot ◽  
State Of The Art ◽  
Design Method ◽  
Humanoid Robots ◽  
Human Robot Interaction ◽  
Robot Interaction ◽  
Design Concepts ◽  
Design Ideas

AbstractInteraction between humans and robots will benefit if people have at least a rough mental model of what a robot knows about the world and what it plans to do. But how do we design human-robot interactions to facilitate this? Previous research has shown that one can change people’s mental models of robots by manipulating the robots’ physical appearance. However, this has mostly not been done in a user-centred way, i.e. without a focus on what users need and want. Starting from theories of how humans form and adapt mental models of others, we investigated how the participatory design method, PICTIVE, can be used to generate design ideas about how a humanoid robot could communicate. Five participants went through three phases based on eight scenarios from the state-of-the-art tasks in the RoboCup@Home social robotics competition. The results indicate that participatory design can be a suitable method to generate design concepts for robots’ communication in human-robot interaction.

Performance Analysis of Pose Invariant Face Recognition Approaches in Unconstrained Environments

2015 ◽  
Vol 5 (1) ◽  
pp. 66-81 ◽  
Author(s):  
M. Parisa Beham ◽  
S. M. Mansoor Roomi ◽  
J. Alageshan ◽  
V. Kapileshwaran
Keyword(s):  
Face Recognition ◽  
Nearest Neighbor ◽  
State Of The Art ◽  
Recognition Algorithm ◽  
K Nearest Neighbor ◽  
Research Issues ◽  
Histograms Of Oriented Gradients ◽  
Recognition Phase ◽  
The Face ◽  
Pose Variation

Face recognition and authentication are two significant and dynamic research issues in computer vision applications. There are many factors that should be accounted for face recognition; among them pose variation is a major challenge which severely influence in the performance of face recognition. In order to improve the performance, several research methods have been developed to perform the face recognition process with pose invariant conditions in constrained and unconstrained environments. In this paper, the authors analyzed the performance of a popular texture descriptors viz., Local Binary Pattern, Local Derivative Pattern and Histograms of Oriented Gradients for pose invariant problem. State of the art preprocessing techniques such as Discrete Cosine Transform, Difference of Gaussian, Multi Scale Retinex and Gradient face have also been applied before feature extraction. In the recognition phase K- nearest neighbor classifier is used to accomplish the classification task. To evaluate the efficiency of pose invariant face recognition algorithm three publicly available databases viz. UMIST, ORL and LFW datasets have been used. The above said databases have very wide pose variations and it is proved that the state of the art method is efficient only in constrained situations.

Sign in / Sign up

Export Citation Format

Share Document