EEML 2012 – Experimental Economics in Machine Learning

Criteria Formation of Effective High-School Graduates Employment Based upon Data Mining Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 94 Yuliya Akhmayzyanova and Irina Bolodurina Image Processing Using Dynamical NK-Networks, Consisting of Binary Logical Elements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 95 Daria Puchkova Author Index . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 94 Online Random Forest for Interactive Image Segmentation Olga Barinova, Roman Shapovalov, Sergey Sudakov, Alexander Velizhev 1 Lomonosov Moscow State University {obarinova,shapovalov,avelizhev}@graphics.cs.msu.su 2 EligoVision Ltd. [email protected] Abstract. Many real-world applications require accurate segmentation of images into semantically-meaningful regions. In many cases one needs to obtain accurate segment maps for a large dataset of images that depict objects of certain semantic categories. As current state-of-the art methods for semantic image segmentation do not yet achieve the accuracy required for their use in real-world applications, they are not applicable in this case. The standard solution would be to apply interactive segmentation methods, however their use for a large number of images would be laborious and time-consuming. In this work we present an online learning framework for interactive semantic image segmentation that simplifies processing of such image datasets. This framework learns to recognize and segment user-defined target categories using the ground truth segmentations provided by user. While the user is working on ground truth image segmentation, our framework combines online-learned category models with the standard stroke-propagation mechanisms that are typically used in interactive segmentation methods. Our implementation of this framework in a software system has specific interface features that minimize the required amount of user input. We evaluate the implementation on several datasets from completely different domains (Sowerby dataset containing 7 different semantic categories, sheep & cows dataset containing 3 categories, and 6 different flower datasets with 2 categories each). Usage of our system requires substantially less user effort compared to the traditional interactive segmentation methods. Many real-world applications require accurate segmentation of images into semantically-meaningful regions. In many cases one needs to obtain accurate segment maps for a large dataset of images that depict objects of certain semantic categories. As current state-of-the art methods for semantic image segmentation do not yet achieve the accuracy required for their use in real-world applications, they are not applicable in this case. The standard solution would be to apply interactive segmentation methods, however their use for a large number of images would be laborious and time-consuming. In this work we present an online learning framework for interactive semantic image segmentation that simplifies processing of such image datasets. This framework learns to recognize and segment user-defined target categories using the ground truth segmentations provided by user. While the user is working on ground truth image segmentation, our framework combines online-learned category models with the standard stroke-propagation mechanisms that are typically used in interactive segmentation methods. Our implementation of this framework in a software system has specific interface features that minimize the required amount of user input. We evaluate the implementation on several datasets from completely different domains (Sowerby dataset containing 7 different semantic categories, sheep & cows dataset containing 3 categories, and 6 different flower datasets with 2 categories each). Usage of our system requires substantially less user effort compared to the traditional interactive segmentation methods.