Methods and systems for image classification

A method implemented by computer means for classifying images, the method comprising:

• using an image preprocessor, extracting image data representing at least one image feature of an image to obtain a first tensor representing the extracted image data,
• using a metadata preprocessor, processing metadata representing contextual information of the image to obtain a second tensor representing the processed metadata,
• using a combinator, combining the first tensor and the second tensor to obtain a combination result, and
• providing the combination result to an image classification layer of an artificial neural network to obtain a classification result.

A computer system for classifying images, the computer system comprising:

• an image preprocessor configured to extract image data representing at least one image feature of an image to obtain a first tensor representing the extracted image data,
• a metadata preprocessor configured to process metadata representing contextual information of the image to obtain a second tensor representing the processed metadata,
• a combinator configured to combine the first tensor and the second tensor to obtain a combination result, and
• an artificial neural network comprising an image classification layer configured to obtain a classification result from the combination result.