Search Results for author: Reinhard Koch

Found 24 papers, 13 papers with code

Restoration of Images with Wavefront Aberrations

no code implementations2 Apr 2017 Claudius Zelenka, Reinhard Koch

In most coherent imaging systems, especially in astronomy, the wavefront deformation is known.

Astronomy Image Restoration

2D and 3D Segmentation of uncertain local collagen fiber orientations in SHG microscopy

1 code implementation30 Jul 2019 Lars Schmarje, Claudius Zelenka, Ulf Geisen, Claus-C. Glüer, Reinhard Koch

Furthermore, we compare a variety of 2D and 3D methods such as classical approaches like Fourier analysis with state-of-the-art deep neural networks for the classification of local fiber orientations.

Segmentation

DRST: Deep Residual Shearlet Transform for Densely Sampled Light Field Reconstruction

no code implementations19 Mar 2020 Yuan Gao, Robert Bregovic, Reinhard Koch, Atanas Gotchev

Specifically, for an input sparsely-sampled EPI, DRST employs a deep fully Convolutional Neural Network (CNN) to predict the residuals of the shearlet coefficients in shearlet domain in order to reconstruct a densely-sampled EPI in image domain.

MorphoCluster: Efficient Annotation of Plankton images by Clustering

1 code implementation4 May 2020 Simon-Martin Schröder, Rainer Kiko, Reinhard Koch

By aggregating similar images into clusters, our novel approach to image annotation increases consistency, multiplies the throughput of an annotator and allows experts to adapt the granularity of their sorting scheme to the structure in the data.

Clustering General Classification +1

Panoptic Instance Segmentation on Pigs

no code implementations21 May 2020 Johannes Brünger, Maria Gentz, Imke Traulsen, Reinhard Koch

In recent years, methods based on deep learning have been introduced and have shown pleasingly good results.

Instance Segmentation Panoptic Segmentation +1

An Analysis by Synthesis Method that Allows Accurate Spatial Modeling of Thickness of Cortical Bone from Clinical QCT

no code implementations18 Sep 2020 Stefan Reinhold, Timo Damm, Sebastian Büsse, Stanislav N. Gorb, Claus-C. Glüer, Reinhard Koch

Quantitative computed tomography (QCT) permits the selective analysis of cortical bone, however the low spatial resolution of clinical QCT leads to an overestimation of the thickness of cortical bone (Ct. Th) and bone strength.

Beyond Cats and Dogs: Semi-supervised Classification of fuzzy labels with overclustering

1 code implementation3 Dec 2020 Lars Schmarje, Johannes Brünger, Monty Santarossa, Simon-Martin Schröder, Rainer Kiko, Reinhard Koch

We propose a novel loss to improve the overclustering capability of our framework and show on the common image classification dataset STL-10 that it is faster and has better overclustering performance than previous work.

General Classification Image Classification

Learning Stixel-based Instance Segmentation

no code implementations7 Jul 2021 Monty Santarossa, Lukas Schneider, Claudius Zelenka, Lars Schmarje, Reinhard Koch, Uwe Franke

Stixels have been successfully applied to a wide range of vision tasks in autonomous driving, recently including instance segmentation.

Autonomous Driving Instance Segmentation +2

S2C2 - An orthogonal method for Semi-Supervised Learning on ambiguous labels

no code implementations29 Sep 2021 Lars Schmarje, Monty Santarossa, Simon-Martin Schröder, Claudius Zelenka, Rainer Kiko, Jenny Stracke, Nina Volkmann, Reinhard Koch

Semi-Supervised Learning (SSL) can decrease the required amount of labeled image data and thus the cost for deep learning.

Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy

1 code implementation13 Oct 2021 Lars Schmarje, Johannes Brünger, Monty Santarossa, Simon-Martin Schröder, Rainer Kiko, Reinhard Koch

We propose a novel loss to improve the overclustering capability of our framework and show the benefit of overclustering for fuzzy labels.

Life is not black and white -- Combining Semi-Supervised Learning with fuzzy labels

no code implementations13 Oct 2021 Lars Schmarje, Reinhard Koch

We envision the incorporation of fuzzy labels into Semi-Supervised Learning and give a proof-of-concept of the potential lower costs and higher consistency in the complete development cycle.

Creating Realistic Ground Truth Data for the Evaluation of Calibration Methods for Plenoptic and Conventional Cameras

1 code implementation9 Mar 2022 Tim Michels, Arne Petersen, Reinhard Koch

Camera calibration methods usually consist of capturing images of known calibration patterns and using the detected correspondences to optimize the parameters of the assumed camera model.

Camera Calibration

Simulation of Plenoptic Cameras

2 code implementations9 Mar 2022 Tim Michels, Arne Petersen, Luca Palmieri, Reinhard Koch

Plenoptic cameras enable the capturing of spatial as well as angular color information which can be used for various applications among which are image refocusing and depth calculations.

Ray Tracing-Guided Design of Plenoptic Cameras

3 code implementations9 Mar 2022 Tim Michels, Reinhard Koch

The design of a plenoptic camera requires the combination of two dissimilar optical systems, namely a main lens and an array of microlenses.

Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimation

1 code implementation13 Jul 2022 Lars Schmarje, Vasco Grossmann, Claudius Zelenka, Sabine Dippel, Rainer Kiko, Mariusz Oszust, Matti Pastell, Jenny Stracke, Anna Valros, Nina Volkmann, Reinhard Koch

We propose a data-centric image classification benchmark with ten real-world datasets and multiple annotations per image to allow researchers to investigate and quantify the impact of such data quality issues.

Image Classification Noise Estimation

Opportunistic hip fracture risk prediction in Men from X-ray: Findings from the Osteoporosis in Men (MrOS) Study

no code implementations22 Jul 2022 Lars Schmarje, Stefan Reinhold, Timo Damm, Eric Orwoll, Claus-C. Glüer, Reinhard Koch

We show that FORM can correctly predict the 10-year hip fracture risk with a validation AUC of 81. 44 +- 3. 11% / 81. 04 +- 5. 54% (mean +- STD) including additional information like age, BMI, fall history and health background across a 5-fold cross validation on the X-ray and CT cohort, respectively.

Computed Tomography (CT)

Automated Classification of Nanoparticles with Various Ultrastructures and Sizes

no code implementations28 Jul 2022 Claudius Zelenka, Marius Kamp, Kolja Strohm, Akram Kadoura, Jacob Johny, Reinhard Koch, Lorenz Kienle

Accurately measuring the size, morphology, and structure of nanoparticles is very important, because they are strongly dependent on their properties for many applications.

Classification Image Generation

Annotating Ambiguous Images: General Annotation Strategy for Image Classification with Real-World Biomedical Validation on Vertebral Fracture Diagnosis

1 code implementation21 Jun 2023 Lars Schmarje, Vasco Grossmann, Claudius Zelenka, Reinhard Koch

While numerous methods exist to solve classification problems within curated datasets, these solutions often fall short in biomedical applications due to the biased or ambiguous nature of the data.

Image Classification

Mind the Exit Pupil Gap: Revisiting the Intrinsics of a Standard Plenoptic Camera

2 code implementations20 Feb 2024 Tim Michels, Daniel Mäckelmann, Reinhard Koch

Our work addresses the often-overlooked role of the main lens exit pupil in these models and specifically in the decoding process of standard plenoptic camera (SPC) images.

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