System and method for predicting the file size of images subject to transformation by scaling and a change of quality-controlling parameters

A system for predicting a file size of an image subject to transformation by resolution scaling and a change of at least one quality-controlling parameter of the image from a set of one or more quality-controlling parameters, the system comprising:

• a processor;
• and
• a non-transitory computer readable medium having computer readable instructions stored thereon for execution by the processor, causing the processor to:
• (a) partition a set of training images into classes of images based on characteristics of the training images in the set of training images;
• (b) for each class, pre-compute an array of relative file size predictions for the training images subject to training transformations by resolution scaling and change of said one or more quality-controlling parameters for the training images;
• for the image subject to the transformation:
• (c) obtain a file size of the image before the transformation, information regarding the change of said at least one quality-controlling parameter of the image, and a resolution scaling factor to be applied to the image during the transformation;
• (d) determine a corresponding class of images in the set of training images, and a corresponding pre-computed array of relative file size predictions;
• and
• (e) predict the file size of the image after the transformation using the file size of the image before the transformation, the information regarding the change of said at least one quality-controlling parameter of the image, the resolution scaling factor, and the corresponding precomputed array of relative file size predictions.

A method for predicting a file size of an image subject to transformation by resolution scaling and a change of at least one quality-controlling parameter of the image from a set of one or more quality-controlling parameters, the method comprising:

• employing at least one processor for:
• (a) partitioning a set of training images into classes of images based on characteristics of the training images in the set of training images;
• (b) for each class, pre-computing an array of relative file size predictions for the training images subject to training transformations by resolution scaling and change of said one or more quality-controlling parameters for the training images;
• for the image subject to the transformation:
• (c) obtaining a file size of the image before the transformation, information regarding the change of said at least one quality-controlling parameter of the image, and a resolution scaling factor to be applied to the image during the transformation;
• (d) determining a corresponding class of images in the set of training images, and a corresponding pre-computed array of relative file size predictions;
• and
• (e) predicting the file size of the image after the transformation using the file size of the image before the transformation, the information regarding the change of said at least one quality-controlling parameter of the image, the resolution scaling factor, and the corresponding precomputed array of relative file size predictions.