Method and apparatus for recognizing object, and method and apparatus for training recognizer

Abstract

A recognition method includes receiving an input image; and recognizing a plurality of elements associated with the input image using a single recognizer pre-trained to recognize a plurality of elements simultaneously.

What is claimed is: 
     
         1 . A recognition method comprising:
 receiving an input image including a face region; and   recognizing a plurality of elements of the input image using a single recognizer including a neural network (NN) to recognize the plurality of elements,   the plurality of elements including elements associated with the face region.   
     
     
         2 . The recognition method of  claim 1 , wherein the plurality of elements comprise:
 an identity (ID) that identifies the face region; and   at least one attribute associated with the face region.   
     
     
         3 . The recognition method of  claim 1 , wherein the plurality of elements comprise a plurality of attributes associated with the face region. 
     
     
         4 . The recognition method of  claim 1 , wherein the plurality of elements comprise at least one of:
 a gender corresponding to the face region;   an age corresponding to the face region;   an ethnic group corresponding to the face region;   an attractiveness corresponding to the face region;   a facial expression corresponding to the face region; or   an emotion corresponding to the face region.   
     
     
         5 . The recognition method of  claim 1 , wherein the recognizing includes calculating feature values corresponding to the plurality of elements based on pre-learned weights between nodes included in the neural network. 
     
     
         6 . The recognition method of  claim 1 , wherein the recognizing includes generating a plurality of feature images based on the input image,
 wherein the plurality of feature images comprises at least one of:   a color channel image from which illumination noise is removed;   an oriented-gradient magnitude channel image;   a skin probability channel image; or   a local binary pattern channel image.   
     
     
         7 . The recognition method of  claim 1 , wherein the recognizing comprises:
 acquiring a plurality of part images corresponding to parts of a face included in the input image; and   generating a plurality of feature images corresponding to each of the plurality of part images.   
     
     
         8 . A method of training a recognizer, the method comprising:
 receiving a training image; and   training a recognizer configured to recognize a plurality of elements of an input image that includes a face region, based on the training image and a plurality of elements labeled in the training image, such that the recognizer includes a neural network (NN) to recognize the plurality of elements of the input image,   the plurality of elements of the input image including elements associated with the face region.   
     
     
         9 . The method of  claim 8 , wherein the plurality of elements comprise:
 an identity (ID) that identifies the face region; and   at least one attribute associated with the face region.   
     
     
         10 . The method of  claim 8 , wherein the plurality of elements comprise a plurality of attributes associated with the face region. 
     
     
         11 . The method of  claim 8 , wherein the plurality of elements comprise at least one of:
 a gender corresponding to the face region;   an age corresponding to the face region;   an ethnic group corresponding to the face region;   an attractiveness corresponding to the face region;   a facial expression corresponding to the face region; or   an emotion corresponding to the face region.   
     
     
         12 . The method of  claim 8 , wherein the training comprises calculating losses corresponding to the plurality of elements. 
     
     
         13 . The method of  claim 12 , wherein the training includes training the recognizer to learn weights between nodes included in the neural network based on the losses. 
     
     
         14 . The method of  claim 8 , wherein the recognizer comprises a neural network, and
 the training includes activating nodes included in the neural network based on a stochastic piecewise linear (PWL) model.   
     
     
         15 . The method of  claim 8 , wherein the training comprises generating a plurality of feature images based on the training image,
 wherein the plurality of feature images comprises at least one of:   a color channel image from which illumination noise is removed;   an oriented-gradient magnitude channel image;   a skin probability channel image; or   a local binary pattern channel image.   
     
     
         16 . The method of  claim 8 , wherein the training comprises:
 acquiring a plurality of part images corresponding to parts of a face included in the training image.   
     
     
         17 . The method of  claim 16 , wherein different elements are labeled in the plurality of part images. 
     
     
         18 . A non-transitory computer-readable medium comprising program code that, when executed by a processor, performs functions according to the method of  claim 1 . 
     
     
         19 . A recognition apparatus comprising:
 a memory storing instructions; and   one or more processors configured to execute the instructions such that the one or more processors are configured to,
 receive an input image including a face region; and 
 recognize a plurality of elements of the input image using a recognizer including a neural network (NN) to recognize the plurality of elements, 
 the plurality of elements including elements associated with the face region. 
   
     
     
         20 . An apparatus for training a recognizer, the apparatus comprising:
 a memory storing instructions; and   one or more processors configured to execute the instructions such that the one or more processors are configured to,
 receive a training image; and 
 train a recognizer configured to recognize a plurality of elements of an input image that includes a face region, based on the training image and a plurality of elements labeled in the training image, such that the recognizer includes a neural network (NN) to recognize the plurality of elements of the input image, 
   the plurality of elements of the input image including elements associated with the face region.