Prediction of Natural Image Saliency for Synthetic Images




Tytuł czasopisma

ISSN czasopisma

Tytuł tomu


Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press


Numerous saliency models are being developed with the use ofneural networks and are capable of combining various features and predicting the saliency values with great results. In fact, it might be difficult to replace the possibilities of artificial intelligence applied to algorithms responsible for predicting saliency. However, the low-level features are still important and should not be removed completely from new saliency models. This work shows that carefully chosen and integrated features, including a deep learning based one, can be used for saliency prediction. The integration is obtained by using Multiple Kernel Learning. This solution is quite effective, as compared to a few other models tested on the same dataset.


Słowa kluczowe

computer games, artificial intelligence, image saliency, Human Visual Attention, gry komputerowe, sztuczna inteligencja, istotność obrazu, uwaga wzrokowa człowieka


Rudak E., Rynkiewicz F., Daszuta M., Sturgulewski Ł., Lazarek J., Prediction of Natural Image Saliency for Synthetic Images. W: TEWI 2021 (Technology, Education, Knowledge, Innovation), Wojciechowski A. (Ed.), Napieralski P. (Ed.), Lipiński P. (Ed.)., Seria: Monografie PŁ;Nr 2378, Wydawnictwo Politechniki Łódzkiej, Łódź 2021, s. 155-169, ISBN 978-83-66741-10-2, DOI 10.34658/9788366741102.11.