Apparatus and method for recognizing expression of a face, image processing apparatus and system

An apparatus for recognizing expression of a face in a face region of an input image, comprising:

• a feature point detection unit configured to detect feature points of the face in the face region of the input image;
• a face shape determination unit configured to determine a face shape of the face in the face region based on the detected feature points;
• a face pose determination unit configured to determine a face pose of the face in the face region based on the detected feature points;
• a group determination unit configured to determine a group that the face in the face region belongs to based on the determined face shape, the determined face pose, pre-defined pose groups and pre-defined shape groups among the pre-defined pose groups, wherein the pre-defined pose groups represent angle ranges of rotation angles of faces in the pre-defined pose groups relative to coordinates;
• and
• an expression determination unit configured to determine an expression of the face in the face region based on at least one pre-generated model corresponding to the determined group and features extracted from at least one region in the face region, wherein the at least one of the regions are regions which are labeled out in the pre-generated models corresponding to the determined group.

A method for recognizing expression of a face in a face region of an input image, comprising:

• a feature point detection step of detecting feature points of the face in the face region of the input image;
• a face shape determination step of determining a face shape of the face in the face region based on the detected feature points;
• a group determination step of determining a group that the face in the face region belongs to based on the determined face shape and pre-defined shape groups;
• and
• an expression determination step of determining an expression of the face in the face region based on at least one pre-generated first model corresponding to the determined group and features extracted from at least one region in the face region, wherein the at least one of the regions are regions which are labeled out in the pre-generated first models corresponding to the determined group.

A method for recognizing expression of a face in a face region of an input image, comprising:

• a feature point detection step of detecting feature points of the face in the face region of the input image;
• a face shape determination step of determining a face shape of the face in the face region based on the detected feature points;
• a face pose determination step of determining a face pose of the face in the face region based on the detected feature points;
• a group determination step of determining a group that the face in the face region belongs to based on the determined face shape, the determined face pose, pre-defined pose groups and pre-defined shape groups among the pre-defined pose groups, wherein the pre-defined pose groups represent angle ranges of rotation angles of faces in the pre-defined pose groups relative to coordinates;
• and
• an expression determination step of determining an expression of the face in the face region based on at least one pre-generated model corresponding to the determined group and features extracted from at least one region in the face region, wherein the at least one of the regions are regions which are labeled out in the pre-generated models corresponding to the determined group.