Personal Style and Non-Negative Matrix Factorization Based Exaggerative Expressions of Face
نویسندگان
چکیده
An intriguing tactic for achieving facial expressions beyond realistic approaches has gradually drawn lots of attention in the fields of video games, avatars, teleconference, human-computer interface and computer animation. However, most researches on facial expressions tend to remain faithful to the trend in realistic expressions rather than exaggerating expressions to take into account personal styles. In the work presented here, we propose a method for exaggeration of facial expressions created by exaggeration mapping that transforms facial motions into exaggerated motions. The exaggeration mapping is derived from non-negative matrix factorization. As if each individual has an identical personality, a conceptual mapping of personal styles for exaggeration of facial expressions needs to be considered. By conducting experiments, we have shown the validity of the exaggeration mapping and simulations of facial expressions.
منابع مشابه
Iterative Weighted Non-smooth Non-negative Matrix Factorization for Face Recognition
Non-negative Matrix Factorization (NMF) is a part-based image representation method. It comes from the intuitive idea that entire face image can be constructed by combining several parts. In this paper, we propose a framework for face recognition by finding localized, part-based representations, denoted “Iterative weighted non-smooth non-negative matrix factorization” (IWNS-NMF). A new cost fun...
متن کاملSynthesis of Exaggerative Line-drawing Caricature
We developed a novel system consisting of two modules, statistics-based synthesis and nonphotorealistic rendering (NPR), to synthesize caricatures of exaggerative facial features and other particular characteristics, such as beards or nevus. The statistics-based synthesis module can exaggerate shapes and positions of facial features based on non-linear exaggerative rates determined automaticall...
متن کاملVoice-based Age and Gender Recognition using Training Generative Sparse Model
Abstract: Gender recognition and age detection are important problems in telephone speech processing to investigate the identity of an individual using voice characteristics. In this paper a new gender and age recognition system is introduced based on generative incoherent models learned using sparse non-negative matrix factorization and atom correction post-processing method. Similar to genera...
متن کاملA new approach for building recommender system using non negative matrix factorization method
Nonnegative Matrix Factorization is a new approach to reduce data dimensions. In this method, by applying the nonnegativity of the matrix data, the matrix is decomposed into components that are more interrelated and divide the data into sections where the data in these sections have a specific relationship. In this paper, we use the nonnegative matrix factorization to decompose the user ratin...
متن کاملNon-negative matrix factorization framework for face recognition
Non-negative Matrix Factorization (NMF) is a part-based image representation method which adds a non-negativity constraint to matrix factorization. NMF is compatible with the intuitive notion of combining parts to form a whole face. In this paper, we propose a framework of face recognition by adding NMF constraint and classifier constraints to matrix factorization to get both intuitive features...
متن کامل