On autonomous control method for facial caricature generation based on a model of visual illusion-experimental modeling of visual illusion

Murakami, Kazuhito; Takai, Miwa; Koshimizu, Hiroyasu

doi:10.1109/aim.1997.652887

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the viewpointofcomputer vision, it is important to brush up the technique of drawing, and it is more important to clarify how the human vision extracts the feature points ofthe face and recognizes them in advance. In the conventional systems or researches concerning facial deformation for facial feature extraction [2,3], caricaturing has been discussed in the viewpoint of the relalion only between the model and the caricaPthst, and the flow of information also has been treated as one-way from caiicaturist to the gallery As the caricature varies according to who draws the caricature, the evaluation varies according to who observes it [4]. From these analytical considerations, facial caricatuiing should be discussed from the multiple viewpoints of these three relations among the model, the caricaturist and the galleiy as shown in Fig.l.…”

Section: Introductionmentioning

confidence: 99%

Interactive facial caricaturing system based on eye camera

2003

View full text Add to dashboard Cite

Face is the most effective visual media for supporting human interface and communication. We have proposed a typical KANSEI machine vision system to generate the facial caricature so far. The basic principle of this system uses the "mean face assumption" to extract individual features of a given face. This system did not provide for feedback from the galleiy of the caricature; therefore, to allow for such feedbaclç in this paper, we propose a caricaturing system by using KANSEI visual information acquiid from the Eye-camera mounted on the head of a gallery because it is well known that the gaze distribution repisents not only where but also how he is looking at the face. The caiicatures created in this way could be based on several measures which are provided fmm the distiibulion of the number of fixations to the facial parts, the number of times the gaze came to a particular area of the face, and the matiix of the tnmsitions from a facial region to the other. These measures of the galleiy's KANSEI information were used to create caricatures with feedback from the galleiy.

show abstract

Section: Introductionmentioning

confidence: 99%

Interactive facial caricaturing system based on eye camera

2003

View full text Add to dashboard Cite

show abstract

“…As one of the most simple expressions, let the individuality feature be the deviation P 0 S and its weight b e b, then caricature Q can be simply described as Q = P + b C (P 0 S) + b G (P 0 S) (4) S = average(P 1 ; P 2 ; ::::; P M ):…”

Section: Basic Formalism Of Caricature Generationmentioning

confidence: 99%

“…In the conventional systems or researches concerning facial deformation or facial feature extraction [2,3], caricaturing has been discussed in the viewpoint of the relation only between the model and the caricaturist, and the ow of information also has been treated as one-way from the caricaturist to the gallery. As the caricature varies according to who draws the caricature, the evaluation varies who observes it [4]. From these analytical considerations, facial caricaturing should be discussed from multiple viewpoints of these three relations among the model, the caricaturist and the gallery as shown in Fig.1.…”

Section: Introductionmentioning

confidence: 99%

Dynamic facial caricaturing system based on the gaze direction of gallery

Murakami

Tominaga²,

Koshimizu³

Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580)

Self Cite

View full text Add to dashboard Cite

Facial caricaturing is a representation process of human visual impression onto a paper or other media. Facial caricaturing should be discussed f r om multiple viewpoints of three r elations among the model, the caricaturist and the gallery. Furthermore, some kinds of interactive mechanism should be r equired b etween the caricaturist and the gallery.In this paper, we propose a dynamic caricaturing system. In our system, the utilization of in-betweening method r ealizes the generation mechanism from the caricaturist to the gallery, and on the contrary, the utilization of eye-camera vision realizes the feedback mechanism from the gallery to the caricaturist. This is an original and unique point of our system. The gallery mounts an eye-camera on the head, and the system reects visual characteristics of the gallery directly onto the works of facial caricature. After observing the image of the model and analyzing the gaze direction and distribution, the system deforms some characteristic and impressive facial parts more strongly than other non-impressive facial parts, and generates the caricature which is suited especially for the gallery. In this paper, we demonstrate experimentally the eectivity of this method to integrate these kinds of viewpoints.

show abstract