Claims Analysis
Total Claims: 5
Claim 1
Independent Claim
269 words
A method of creating 3D facial models (M) starting from face images (I), which comprises the steps of: (a) providing at least one face image (I); (b) providing a 3-D facial model (M) having a vertex structure and comprising a number of surfaces chosen within the group formed by: a face surface (V), a right eye and left eye (OD, OS) surface upper teeth and lower teeth (DS, DL) surface, (c) choosing respective sets of homologous points among the vertices of the structure of said model (M) and on said at least one face image (I); and (d) modifying the structure of said model (M) so as to make the respective sets of homologous points coincide, the modification of the structure of said model (M) including at least one of the operations chosen within the group formed by: (d 1 ) making the width of the projection of the model (M) coincide with the width of said face image (I), (d 2 ) vertically registering the projection of the model (M) with said face image (I), and (d 3 ) performing a global, nonlinear transformation of the model (M) in the vertical direction in order to make the position of at least one characteristic feature of the model (M) coincide with an homologous characteristic feature of such face image (I), said modification of the structure of the model (M) being carried out in the form of a geometric operation performed by positioning said face image (I) and said model (M) in opposite and mirroring positions with respect to the origin (O) of a three-dimensional Cartesian system (X, Y, Z).
Claim 2
Independent Claim
269 words
A method of creating 3D facial models (M) starting from face images (I), which comprises the steps of: (a) providing at least one face image (I); (b) providing a 3-D facial model (M) having a vertex structure and comprising a number of surfaces chosen within the group formed by: a face surface (V), a right eye and left eye (OD, OS) surface upper teeth and lower teeth (DS, DL) surface, (c) choosing respective sets of homologous points among the vertices of the structure of said model (M) and on said at least one face image (I); and (d) modifying the structure of said model (M) so as to make the respective sets of homologous points coincide, the modification of the structure of said model (M) including at least one of the operations chosen within the group formed by: (d 1 ) making the width of the projection of the model (M) coincide with the width of said face image (I), (d 2 ) vertically registering the projection of the model (M) with said face image (I), and (d 3 ) performing a global, nonlinear transformation of the model (M) in the vertical direction in order to make the position of at least one characteristic feature of the model (M) coincide with an homologous characteristic feature of such face image (I), said modification of the structure of the model (M) being carried out in the form of a geometric operation performed by positioning said face image (I) and said model (M) in opposite and mirroring positions with respect to the origin (O) of a three-dimensional Cartesian system (X, Y, Z).
Claim 3
Dependent Claim
20 words
The method according to claim 1 which further comprises the step of applying a respective texture to said modified model.
Claim 4
Dependent Claim
104 words
The method according to claim 2 which includes the steps of: providing a plurality of said face images (I) corresponding to different points of sight of said face, creating the texture to be applied to said model (M) by generating, for each of said face images, a respective texture information in the form of right triangles of constant size, coupling two by two triangles relating to the texture information derived from a plurality of images so as to obtain, as a result of the coupling, respective rectangles, and applying said texture to said modified model in the form of a matrix of said rectangles.
Claim 5
Dependent Claim
81 words
The method according to claim 1 which includes the steps of computing at least one of the parameters chosen within the group including: distance α between said origin (O) and a center point of said model (M), and distance λ between said origin (O) and a the plane of said face image (Y) and of applying said texture to said modified model (M) through a process of texture binding performed on the basis of at least one of said distance parameters.