Delving deeper into the whorl of flower segmentation

Abstract

We describe an algorithm for automatically segmenting flowers in colour photographs. This is a challenging problem because of the sheer variety of flower classes, the variability within a class and within a particular flower, and the variability of the imaging conditions – lighting, pose, foreshortening, etc. The method couples two models – a colour model for foreground and background, and a light generic shape model for the petal structure. This shape model is tolerant to viewpoint changes and petal deformations, and applicable across many different flower classes. The segmentations are produced using a MRF cost function optimized using graph cuts. We show how the components of the algorithm can be tuned to overcome common segmentation errors, and how performance can be optimized by learning parameters on a training set. The algorithm is evaluated on 13 flower classes and more than 750 examples. Performance is assessed against ground truth trimap segmentations. The algorithms is also compared to several previous approaches for flower segmentation.