scholarly journals An Efficient ORB based Face Recognition framework for Human-Robot Interaction

2018 ◽  
Vol 133 ◽  
pp. 913-923 ◽  
Author(s):  
Vinay A ◽  
Ajaykumar S Cholin ◽  
Aditya D Bhat ◽  
K N Balasubramanya Murthy ◽  
S Natarajan
Keyword(s):  
Face Recognition ◽  
Human Robot Interaction ◽  
Robot Interaction

scholarly journals FaceBots: Steps Towards Enhanced Long-Term Human-Robot Interaction by Utilizing and Publishing Online Social Information

2010 ◽  
Vol 1 (3) ◽  
Author(s):  
Nikolaos Mavridis ◽  
Michael Petychakis ◽  
Alexandros Tsamakos ◽  
Panos Toulis ◽  
Shervin Emami ◽  
...  
Keyword(s):  
Face Recognition ◽  
Social Information ◽  
Human Robot Interaction ◽  
Social Web ◽  
Online Information ◽  
Robot Interaction ◽  
Evaluation Methodologies ◽  
Episodic Memories ◽  
Early Interaction

AbstractThe overarching goal of the FaceBots project is to support the achievement of sustainable long-term human-robot relationships through the creation of robots with face recognition and natural language capabilities, which exploit and publish online information, and especially social information available on Facebook, and which achieve two significant novelties. The underlying experimental hypothesis is that such relationships can be significantly enhanced if the human and the robot are gradually creating a pool of episodic memories that they can co-refer to (“shared memories”), and if they are both embedded in a social web of other humans and robots they mutually know (“shared friends”). We present a description of system architecture, as well as important concrete results regarding face recognition and transferability of training, with training and testing sets coming from either one or a combination of two sources: an onboard camera which can provide sequences of images, as well as facebook-derived photos. Furthermore, early interaction-related results are presented, and evaluation methodologies as well as interesting extensions are discussed.

Control of Soap Bubble Ejection Robot Using Facial Expressions

2021 ◽  
Vol 11 (2) ◽  
pp. 1-16
Author(s):  
Naoya Hasegawa ◽  
Yoshihiko Takahashi
Keyword(s):  
Control System ◽  
Face Recognition ◽  
Facial Expressions ◽  
Facial Recognition ◽  
Emotional Responses ◽  
Human Robot Interaction ◽  
Experimental Results ◽  
Soap Bubble ◽  
Robot Interaction ◽  
Soap Bubbles

This research has developed a soap bubble ejection robot as an amusement system that reads emotions from human facial expressions and controls the ejection of soap bubbles to improve human-robot interaction. A subject's response to soap bubble ejection is read by a built-in face recognition sensor which sends data to a control system which in turn controls the next ejection. Soap bubbles are often used to research children's emotions/emotional responses. First, evaluation experiments of the control system were performed using face photographs that show human emotions. The experimental results revealed that soap bubbles were ejected in the case of indifference, and the ejection stopped in the case of joy. Through the experimental results, it was confirmed that the control system worked properly when face photographs were used and also verified the effectiveness of the facial recognition sensor. Secondly, evaluation experiments were conducted with an actual human, and it was confirmed from the results that the control system operates as designed.

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.

Sign in / Sign up

Export Citation Format

Share Document