Model-based learning of local image features for unsupervised texture segmentation
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 ima...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
January 26, 2018
|
| In: |
IEEE transactions on image processing
Year: 2018, Volume: 27, Issue: 4, Pages: 1994-2007 |
| ISSN: | 1941-0042 |
| DOI: | 10.1109/TIP.2018.2792904 |
| Online Access: | Resolving-System, Volltext: https://doi.org/10.1109/TIP.2018.2792904 Resolving-System, Volltext: https://ieeexplore.ieee.org/document/8255629 
|
| Author Notes: | Martin Kiechle, Martin Storath, Andreas Weinmann, and Martin Kleinsteuber |
| Summary: | 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 paper, 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 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. |
|---|---|
| Item Description: | Gesehen am 21.10.2019 |
| Physical Description: | Online Resource |
| ISSN: | 1941-0042 |
| DOI: | 10.1109/TIP.2018.2792904 |