Search Results for author: Tobias Böttger

Found 5 papers, 0 papers with code

MVTec D2S: Densely Segmented Supermarket Dataset

no code implementations ECCV 2018 Patrick Follmann, Tobias Böttger, Philipp Härtinger, Rebecca König, Markus Ulrich

The dataset covers several challenges highly relevant in the field, such as a limited amount of training data and a high diversity in the test and validation sets.

Data Augmentation Instance Segmentation +4

Efficiently Tracking Homogeneous Regions in Multichannel Images

no code implementations16 Aug 2017 Tobias Böttger, Christina Eisenhofer

We present a method for tracking Maximally Stable Homogeneous Regions (MSHR) in images with an arbitrary number of channels.

Object Tracking

Derivate-based Component-Trees for Multi-Channel Image Segmentation

no code implementations4 May 2017 Tobias Böttger, Dominik Gutermuth

We introduce a local flooding-based immersion for the derivate-based component-tree construction which is linear in the number of pixels.

Image Segmentation Optical Character Recognition (OCR) +2

Cannot find the paper you are looking for? You can Submit a new open access paper.