System and method for face recognition

A face recognition system (20) comprising:

• one or more processors (60);
• an image capturing subsystem (110) operable by the one or more processors (60), wherein the image capturing subsystem (110) is configured to capture one or more images of faces of one or more users using an image capturing device;
• a feature extraction subsystem (90) operable by the one or more processors (60), wherein the feature extraction subsystem (90) is configured to extract one or more features from the one or more images of the faces captured by the image capturing subsystem (110) and store in a local database, wherein the extraction of the one or more features from the one or more images of faces captured by the image capturing subsystem comprises of using at least one of Principal Component Analysis (PCA), Fisher Linear Discriminant Analysis (FLD), Fast Pixel Based Matching (FPBM), wherein the local database stores time of the day-based features and images and environment-based features and images, and wherein the one or more features pre-stored in the local database remains in the local database for a certain interval of time;
• a feature comparison subsystem (130) operable by the one or more processors (60), wherein the feature comparison subsystem (110) is configured to compare the one or more features extracted by the feature extraction subsystem (90) with one or more features pre-stored in the local database;
• a feature transmission subsystem (140) operable by the one or more processors (60), wherein the feature transmission subsystem (140) is configured to:
• transmit the one or more images and the one or more features extracted by the feature extraction subsystem (90) to a remote server when the one or more features extracted by the feature extraction subsystem (90) are absent in the local database, and
• compare the one or more features corresponding to the one or more images transmitted by the feature transmission subsystem (140) to the one or more features pre-stored in the remote server to obtain one or more matched features for face recognition of the one or more users;
• and
• a feature regeneration subsystem (150) operable by the one or more processors (60), wherein the feature regeneration subsystem (150) is configured to regenerate the one or more matched features corresponding to the one or more images in the local database from the remote server.