Confidence criterion for speech balloon segmentation

Christophe Rigaud (1) , Van Nguyen (1) , Jean-Christophe Burie (1)

1 L3I - Laboratoire Informatique, Image et Interaction - EA 2118

This short paper investigates how to improve the confidence of speech balloon segmentation algorithms from comic book images. It comes from the need of precise indications about the quality of automatic processing in order to accept or not each segmented regions as a valid result, according to the application and without requiring any ground truth. We discuss several applications like result quality assessment for companies and automatic ground truth creation from high confidence results to train machine learning based systems.We present some ideas to combine several domain knowledge information (e.g. shape, text, etc.) and produce an improved confidence criterion.

Domaines: Traitement des images [eess.IV]; Performance et fiabilité [cs.PF]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Christophe Rigaud, Van Nguyen, Jean-Christophe Burie. Confidence criterion for speech balloon segmentation. 13th IAPR International Workshop on Graphics Recognition, Sep 2019, Sydney, Australia. ⟨hal-02305078⟩