Ilaria Xausa received BSc and MSc degrees in mathematics from the University of Padova. Afterward, she became a risk model developer at Generali insurance. In June 2015, she completed the PhD at Volkswagen where she developed formal methods for the safety verification of driver assistance systems, in collaboration with the University of Munich and the University of Paris VI.
The combination of her academic and industrial background finds its motivation in the desire for and the curiosity about novel approaches to describing the complexity seen in real-life systems. During her experience in industry, Ilaria discovered the power of mathematical models to solve practical problems and the need for computationally efficient tools to solve engineering problems.
Project: Automatic Crop of Images
This project consists of creating a Mathematica function that successfully crops an image. A successful crop changes the composition of an image by emphasizing the most important image content, for instance removing distracting elements. An effective crop focuses the viewer’s attention on the content of the image, while a poor crop is distracting. The risk is to miss other important features in an image and then generate inefficient crops.
For cropping an image, three important steps need to be considered. First, a model for explicit representation of important image content is needed. Next, crops are generated following general rules for creating attractive crops. Finally, the best crop is chosen by combining the possible crop rules.
- Cheng, M., Mitra, N. J., Huang, X., Torr, P. H., & Hu, S. (2015). Global contrast based salient region detection. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 37(3), 569-582.
- Hou, X., Harel, J., & Koch, C. (2012). Image signature: Highlighting sparse salient regions. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 34(1), 194-201.
- Santella, A., Agrawala, M., DeCarlo, D., Salesin, D., & Cohen, M. (2006, April). Gaze-based interaction for semi-automatic photo cropping. In Proceedings of the SIGCHI conference on Human Factors in computing systems (pp. 771-780). ACM.