Generation of Facial Expression Emphasized with Cartoon Techniques Using a Cellular-Phone-Type Teleoperated Robot with a Mobile Projector
21 Jul 2013-pp 391-400
TL;DR: Facial expressions are generated using Elfoid’s head-mounted mobile projector to overcome the problem of compactness and a lack of sufficiently small actuator motors and are emphasized using cartoon techniques.
Abstract: We propose a method for generating facial expressions emphasized with cartoon techniques using a cellular-phone-type teleoperated android with a mobile projector. Elfoid is designed to transmit the speaker’s presence to their communication partner using a camera and microphone, and has a soft exterior that provides the look and feel of human skin. To transmit the speaker’s presence, Elfoid sends not only the voice of the speaker but also emotional information captured by the camera and microphone. Elfoid cannot, however, display facial expressions because of its compactness and a lack of sufficiently small actuator motors. In this research, facial expressions are generated using Elfoid’s head-mounted mobile projector to overcome the problem. Additionally, facial expressions are emphasized using cartoon techniques: movements around the mouth and eyes are emphasized, the silhouette of the face and shapes of the eyes are varied by projection effects, and color stimuli that induce a particular emotion are added. In an experiment, representative face expressions are generated with Elfoid and emotions conveyed to users are investigated by subjective evaluation.
Citations
More filters
TL;DR: The paper proceeds to warn about a tendency to fetishize technical objects, which entails the danger of focusing too much attention on the latter while foregoing to consider power relations and normative settings working in the background.
Abstract: The paper investigates a recent debate on ‘new animism’ in anthropology and related fields with regard to social robots. The conceptual potential of neo-animistic thought, especially when combined with Bruno Latour’s critique of modernity, is demonstrated and exemplified by referring to a phenomenon tentatively called Japanese techno-animism. In this context, Japan figures both as an actual place with specific traditions and idiosyncrasies and as a model of thought allowing to concretize several theoretical arguments, including a softening of the nature-culture boundary. The paper proceeds to warn about a tendency to fetishize technical objects, which entails the danger of focusing too much attention on the latter while foregoing to consider power relations and normative settings working in the background. This critical argument is supported by a discussion of the Elfoid prototype, which is a smartphone-social robot hybrid, developed in the Hiroshi Ishiguro Laboratory. Missing from the debate on ‘new animism’ is a consideration of the risk of fetishization which can be understood as a kind of corrupted animism (Alf Hornborg). Thus, the conceptual affordances of neo-animistic theory have to be confronted with potential blind spots that become evident when approached from a critically modern perspective.
8 citations
01 Jan 2015
TL;DR: This chapter investigates different approaches to complexity reduction in social robotics, among them experiments that compared human mime artists (theatrical robots) with actual robots in the interaction with autistic children and the implementation of cartoon techniques to model emotions in the generation of projected facial expressions.
Abstract: Recently designers at the Hiroshi Ishiguro Laboratory (ATR, Kyoto) decided to shift their focus away from highly-lifelike androids to very minimalistic appearances like that of the Telenoid, Elfoid and Hugvie models. Instead of trying to simulate the appearance and behavior of actual human beings, the decision was to sidestep the Uncanny Valley problem by restricting the robots to a functional minimum in human likeness. This chapter investigates different approaches to complexity reduction in social robotics, among them experiments that compared human mime artists (theatrical robots) with actual robots in the interaction with autistic children and the implementation of cartoon techniques to model emotions in the generation of projected facial expressions. The notion of complexity reduction is discussed with respect to its merits (especially from a systems theoretical framework) and to its drawbacks. Beyond ethical considerations, the chapter argues that the research on social robotics is linked with the cybernetic hypothesis (as formulated by Tiqqun), a contemporary mode of governance and regulation that privileges certain kinds of subjectification via communication and discourages others.
8 citations
01 Aug 2019
TL;DR: This paper achieves the extraction of facial structure features and explicit geometry features using sequence-to-sequence model and incorporates the matching threshold loss as a penalty term to constrain the exaggerated expression of facial features.
Abstract: Exaggerated portrait caricatures can represent peoples explicit facial characteristics. Recently, there have been increasing interests in exaggerated portrait caricatures generation from the real face images. However, existing methods randomly exaggerate facial features and the effects are not diversified. In this paper, we achieve the extraction of facial structure features and explicit geometry features using sequence-to-sequence model. The extracted facial structure features can be well applied to caricatures generation. In order to avoid destroying the recognition of the characters from exaggerating the input face, we also incorporate the matching threshold loss as a penalty term to constrain the exaggerated expression of facial features. Experiment results on the collected dataset indicate the proposed method can finally get satisfied result.
2 citations
22 Jun 2014
TL;DR: In this research, facial expressions are recognized by a machine learning technique and displayed using a mobile projector installed in Elfoid’s head to convey emotions.
Abstract: We propose an emotion transmission system using a cellular phone-type teleoperated robot with a mobile projector. Elfoid has a soft exterior that provides the look and feel of human skin and is designed to transmit a speaker’s presence to their communication partner using a camera and microphone. To transmit the speaker’s presence, Elfoid transmits not only the voice of the speaker but also their facial expression as captured by the camera. In this research, facial expressions are recognized by a machine learning technique. Elfoid cannot, however, physically display facial expressions because of its compactness and a lack of sufficiently small actuator motors. The recognized facial expressions are displayed using a mobile projector installed in Elfoid’s head to convey emotions. We build a prototype system and experimentally evaluate its subjective usability.
24 Aug 2014
TL;DR: In this study, tracking accuracy can be improved by changing the features and classifiers for parts of the face, and the accuracy of landmark locations was compared with the conventional method.
Abstract: We present local feature evaluation for a constrained local model (CLM) framework. We target facial images captured by a mobile camera such as a smartphone. When recognizing facial images captured by a mobile camera, changes in lighting conditions and image degradation from motion blur are considerable problems. CLM is effective for recognizing a facial expression because partial occlusions can be handled easily. In the CLM framework, the optimization strategy is local expert-based deformable model fitting. The likelihood of alignment at a particular landmark location is acquired beforehand using the local features of a large number of images and is used for estimating model parameters. In this learning phase, the features and classifiers used have a great influence on the accuracy of estimation in landmark locations. In our study, tracking accuracy can be improved by changing the features and classifiers for parts of the face. In the experiments, the likelihood map was generated using various features and classifiers, and the accuracy of landmark locations was compared with the conventional method.
Cites background from "Generation of Facial Expression Emp..."
...Furthermore, many blurred images are included because Elfoid is assumed to be used in the hand as a mobile phone....
[...]
...Figure 1 shows a cellphone-type tele-operated communication medium called Elfoid [2]....
[...]
...Elfoid has a camera within its body and the speaker’s facial movements can be estimated through an accurate facial recognition approach....
[...]
...Elfoid is designed to transmit the speaker’s presence to the communication partner using a camera and microphone....
[...]
...When we recognize facial images captured by a mobile camera within Elfoid, changes in lighting conditions and image degradation from motion blur are considerable problems....
[...]
References
More filters
Abstract: We describe a new method of matching statistical models of appearance to images. A set of model parameters control modes of shape and gray-level variation learned from a training set. We construct an efficient iterative matching algorithm by learning the relationship between perturbations in the model parameters and the induced image errors.
6,200 citations
01 Jan 1978
3,840 citations
"Generation of Facial Expression Emp..." refers background in this paper
...There have been a considerable number of studies on basic human emotions [3–6]....
[...]
...According to the facial action coding system (FACS) [6], which describes relationships between emotion and facial movement, movements around the mouth and eyes play important roles....
[...]
...According to FACS [6], which describes relationships between...
[...]
...[6] defined basic facial expressions for anger, disgust, fear, happiness, sadness and surprise....
[...]
TL;DR: The main purpose of the present paper is to give the exact tables for making two-sided comparisons, and a method is given for adjusting the tabulated values to cover the situation where the variance of the control mean is smaller than thevariance of the treatment means.
Abstract: Some time ago, a multiple comparison procedure for comparing several treatments simultaneously with a control or standard treatment was introduced by the present author (Dunnett [1955]). The procedure was designed to be used either to test the significance of the differences between each of the treatments and the control with a stated value 1 - P for the joint significance level, or to set confidence limits on the true values of the treatment differences from the control with a stated value P for the joint confidence coefficient. Thus the procedure has the property of controlling the experimentwise, rather than the per-comparison, error rate associated with the comparisons, in common with the multiple comparison procedures of Tukey [unpublished] and Scheffe [1953]. In the earlier paper, tables were provided enabling up to nine treatments to be compared with a control with joint confidence coefficient either .95 or .99. Tables for both one-sided and two-sided comparisons were given but, as explained in the paper, the two-sided values were inexact for the case of more than two comparisons as a result of an approximation which had to be made in the computations. The main purpose of the present paper is to give the exact tables for making two-sided comparisons. The necessary computations were done on a General Precision LGP-30 electronic computer, by a method described in section 3 below. The tables are given here as Tables II and III; these replace Tables 2a and 2b, respectively, of the previous paper. In addition to providing the exact values, a method is given for adjusting the tabulated values to cover the situation where the variance of the control mean is smaller than the variance of the treatment means, as occurs for example when a greater number of observations is allocated to the control than to any of the test treatments. Furthermore, the number of treatments which may be simultaneously compared with a control has been extended to twenty. 482
2,823 citations
"Generation of Facial Expression Emp..." refers methods in this paper
...Dunnett’s test [14] is used to compare the average scores....
[...]
Book•
01 Jan 1980
2,139 citations
"Generation of Facial Expression Emp..." refers background in this paper
...There have been a considerable number of studies on basic human emotions [3–6]....
[...]