Recognition-Difficulty-Aware Hidden Images Based on Clue-map
Computer Graphics Forum, Wiley, 2016, 35(8):80-94.
Yandan Zhao, Hui Du, Xiaogang Jin
The pipeline of our approach.
A hidden image created by our method (left) , and its answer (right).
Abstract
Hidden images contain one or several concealed
foregrounds which can be recognized with the assistance of clues
preserved by artists. Experienced artists are trained for years to be
skilled enough to find appropriate hidden positions for a given image.
However, it is not an easy task for amateurs to quickly find these
positions when they try to create satisfactory hidden images. In this
paper, we present an interactive framework to suggest the hidden
positions and corresponding results. The suggested results generated by
our approach are sequenced according to the levels of their recognition
difficulties. To this end, we propose a novel approach for assessing the
levels of recognition difficulty of the hidden images and a new hidden
image synthesis method that takes spatial influence into account
to make the foreground harmonious with the local surroundings. During
the synthesis stage, we extract the characteristics of the foreground as
the clues based on the visual attention model. We validate the
effectiveness of our approach by performing two user studies, including
the quality of the hidden images and the suggestion accuracy.