Automated reconstruction of tree structures using path classifiers and Mixed Integer Programming

Türetken, Engin; Benmansour, Fethallah; Fua, Pascal

doi:10.1109/cvpr.2012.6247722

Cited by 74 publications

(97 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In earlier work [41] we showed the advantage of using a path classifier and a mixed integer programming formulation to automatically trace such structures. Within this framework, machine learning is used to predict, based on image evidence, if a tubular path between two points in the image belongs to a curvilinear structure or not.…”

Section: A Datasetsmentioning

confidence: 99%

Domain Adaptation for Microscopy Imaging

Becker

Christoudias

Fua

2015

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Abstract-Electron and Light Microscopy imaging can now deliver high-quality image stacks of neural structures. However, the amount of human annotation effort required to analyze them remains a major bottleneck. While Machine Learning algorithms can be used to help automate this process, they require training data, which is time-consuming to obtain manually, especially in image stacks. Furthermore, due to changing experimental conditions, successive stacks often exhibit differences that are severe enough to make it difficult to use a classifier trained for a specific one on another. This means that this tedious annotation process has to be repeated for each new stack. In this paper we present a domain adaptation algorithm that addresses this issue by effectively leveraging labeled examples across different acquisitions and significantly reducing the annotation requirements. Our approach can handle complex, non-linear image feature transformations and scales to large microscopy datasets that often involve high-dimensional feature spaces and large 3D data volumes. We evaluate our approach on four challenging Electron and Light Microscopy applications that exhibit very different image modalities and where annotation is very costly. Across all applications we achieve a significant improvement over the state-of-the-art Machine Learning methods and demonstrate our ability to greatly reduce human annotation effort.

show abstract

Section: A Datasetsmentioning

confidence: 99%

Domain Adaptation for Microscopy Imaging

Becker

Christoudias

Fua

2015

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…However, a particularly important property of the road network is its connectedness. Several excellent contributions exist which aim at extraction of (curvy)linear structures by fitting low-cost paths between the seeds, which are pixels with locally minimum values of the cost function, such as tubular measure (Türetken et al, 2012). For combined evaluation of image and elevation data, proposed a pioneering approach for extraction of road superpixels.…”

Section: Previous Workmentioning

confidence: 99%

Variable Selection for Road Segmentation in Aerial Images

Warnke

Bulatov

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:For extraction of road pixels from combined image and elevation data, Wegner et al. (2015) proposed classification of superpixels into road and non-road, after which a refinement of the classification results using minimum cost paths and non-local optimization methods took place. We believed that the variable set used for classification was to a certain extent suboptimal, because many variables were redundant while several features known as useful in Photogrammetry and Remote Sensing are missed. This motivated us to implement a variable selection approach which builds a model for classification using portions of training data and subsets of features, evaluates this model, updates the feature set, and terminates when a stopping criterion is satisfied. The choice of classifier is flexible; however, we tested the approach with Logistic Regression and Random Forests, and taylored the evaluation module to the chosen classifier. To guarantee a fair comparison, we kept the segment-based approach and most of the variables from the related work, but we extended them by additional, mostly higher-level features. Applying these superior features, removing the redundant ones, as well as using more accurately acquired 3D data allowed to keep stable or even to reduce the misclassification error in a challenging dataset.

show abstract

“…In [25], the authors proposed an approach to classifying tubular paths, such as the one depicted in Fig. 5(top), as truly corresponding to linear structures or not.…”

Section: Path Classificationmentioning

confidence: 99%

“…We constructed our training and validation set by computing the gradient histogram features described in [25] for 5000 positive and 5000 negative randomly selected samples from two different volumes 3 . Similarly, a 30'000 path test set was generated.…”

Section: Path Classificationmentioning

confidence: 99%