Method and system for training artificial neural network based image classifier using class-specific relevant features

A system for updating an artificial neural network (ANN) based image classifier using class-specific relevant features, the system comprising:

• a processor;
• and
• a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which, on execution, causes the processor to:
• receive the ANN based image classifier, training image dataset, and a plurality of features of the training image dataset;
• determine a relative relevance value of each of the plurality of features corresponding to each of a set of classes, based on the ANN based image classifier;
• segregate a set of co-occurring features from the plurality of features for each of the set of classes, based on the training image dataset and the ANN based image classifier;
• identify an imbalance in the class-specific relevant features for each of the set of classes based on the relative relevance value of each of the plurality of features corresponding to each of the set of classes;
• and
• update the ANN based image classifier based on the imbalance in the class-specific relevant features and the set of co-occurring features, for each of the set of classes.

A non-transitory computer-readable medium for updating an artificial neural network (ANN) based image classifier using class-specific relevant features, having stored thereon, a set of computer-executable instructions causing a computer comprising one or more processors to perform steps comprising:

• receiving the ANN based image classifier, training image dataset, and a plurality of features of the training image dataset;
• determining a relative relevance value of each of the plurality of features corresponding to each of a set of classes, based on the ANN based image classifier;
• segregating a set of co-occurring features from the plurality of features for each of the set of classes, based on the training image dataset and the ANN based image classifier;
• identifying an imbalance in the class-specific relevant features for each of the set of classes based on the relative relevance value of each of the plurality of features corresponding to each of the set of classes;
• and
• updating the ANN based image classifier based on the imbalance in the class-specific relevant features and the set of co-occurring features, for each of the set of classes.