PuSH - Publication Server of Helmholtz Zentrum München

Kiechle, M.* ; Storath, M.* ; Weinmann, A. ; Kleinsteuber, M.*

Model-based learning of local image features for unsupervised texture segmentation.

IEEE Trans. Image Process. 27, 1994-2007 (2018)
Postprint DOI
Open Access Green
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.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Corresponding Author
Keywords Feature Vector ; Geometric Optimization ; Mumford-shah Model ; Texture Segmentation ; Unsupervised Learning; Spectral Histograms; Classification; Filters; Sparse; Color
ISSN (print) / ISBN 1057-7149
e-ISSN 1941-0042
Journal IEEE Transactions on Image Processing
Quellenangaben Volume: 27, Issue: 4, Pages: 1994-2007 Article Number: , Supplement: ,
Publisher Institute of Electrical and Electronics Engineers (IEEE)
Publishing Place Piscataway
Non-patent literature Publications
Reviewing status Peer reviewed
Institute(s) Institute of Computational Biology (ICB)