Model-based learning of local image features for unsupervised texture segmentation
This work addresses the tedious manual feature selection for texture segmentation, particularly in domains like medical imaging, by providing an unsupervised method that is incremental in adapting existing segmentation models.
The authors tackled the problem of automatically learning local image features for unsupervised texture segmentation without requiring labeled training data, achieving a competitive rank on the Prague texture segmentation benchmark and effectiveness in segmenting histological images.
Features that capture well the textural patterns of a certain class of images are crucial for the performance of texture segmentation methods. The manual selection of features or designing new ones can be a tedious task. Therefore, it is desirable to automatically adapt the features to a certain image or class of images. Typically, this requires a large set of training images with similar textures and ground truth segmentation. In this work, we propose a framework to learn features for texture segmentation when no such training data is available. The cost function for our learning process is constructed to match a commonly used segmentation model, the piecewise constant Mumford-Shah model. This means that the features are learned such that they provide an approximately piecewise constant feature image with a small jump set. Based on this idea, we develop a two-stage algorithm which first learns suitable convolutional features and then performs a segmentation. We note that the features can be learned from a small set of images, from a single image, or even from image patches. The proposed method achieves a competitive rank in the Prague texture segmentation benchmark, and it is effective for segmenting histological images.