Automatically filtering out objects based on user preferences

A computer program product for classifying objects, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:

• detecting, by a hardware processor, objects in a set of one or more images;
• tagging, by the hardware processor, each of the objects with multiple features, each of the multiple features describing a specific object attribute and having a range of values assigned to assist with a determination of an overall quality of the one or more images;
• specifying, by the hardware processor, a set of training examples by classifying the overall quality of at least some of the objects as being of an acceptable quality or an unacceptable quality, based on a user's domain knowledge about an application program that takes the objects as inputs;
• constructing, by the hardware processor, a plurality of first-level automatic classifiers using the set of training examples;
• and
• constructing, by the hardware processor, a second-level automatic classifier from outputs of the first-level automatic classifiers, the second-level automatic classifier for automatically providing a classification for at least some of the objects, the classification being either the acceptable quality or the unacceptable quality.

A computer processing system for classifying objects, comprising:

• a memory for storing program code;
• and
• a hardware processor for running the program code to
• detect objects in a set of one or more images;
• tag each of the objects with multiple features, each of the multiple features describing a specific object attribute and having a range of values assigned to assist with a determination of an overall quality of the one or more images;
• specify a set of training examples by classifying the overall quality of at least some of the objects as being of an acceptable quality or an unacceptable quality, based on a user's domain knowledge about an application program that takes the objects as inputs;
• construct a plurality of first-level automatic classifiers using the set of training examples;
• and
• construct a second-level automatic classifier from outputs of the first-level automatic classifiers, the second-level automatic classifier for automatically providing a classification for at least some of the objects, the classification being either the acceptable quality or the unacceptable quality.