We propose a new edition of the competition on comics (ICPR2016-SSGCI, ICPR2018-SSGCI-3CG). In this edition, we would like to challenge the community to develop algorithms that will classify images of comic characters into their corresponding class. This problem lies between the characters detection in comic book images and the identification of individual character (character’s name). The visual distinctions between characters are often subtle, especially for characters in the same album, or in multiple albums of the same authors or the same style. Hence, it is difficult to address with today’s general-purpose object classification methods.
This competition is a result of a joint collaboration of various members (chair, executive, non-executive) of the following three technical committees (TC) of the International Association of Pattern Recognition (IAPR) and is very interesting for the research communities represented by these three TCs of IAPR: TC10, TC11, and TC15.