Search Results for author:
Found 49 papers, 21 papers with code
Efficient Annotation of Medieval Charters
Diplomatics, the analysis of medieval charters, is a major field of research in which paleography is applied.
A Vessel-Segmentation-Based CycleGAN for Unpaired Multi-modal Retinal Image Synthesis
Unpaired image-to-image translation of retinal images can efficiently increase the training dataset for deep-learning-based multi-modal retinal registration methods.
Combining OCR Models for Reading Early Modern Printed Books
Moreover, we developed a system using local font group recognition in order to combine the output of multiple font recognition models, and show that while slower, this approach performs better not only on text lines composed of multiple fonts but on the ones containing a single font only as well.
WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models
Our proposed method is able to generate realistic word image samples from different writer styles, by using class index styles and text content prompts without the need of adversarial training, writer recognition, or text recognition.
AMD-HookNet for Glacier Front Segmentation
are present in the data), which exacerbates the difficulty of accurate segmentation.
Ranked #1 on
Calving Front Delineation In Synthetic Aperture Radar Imagery With Fixed Training Amount
on CaFFe
Calving Front Delineation In Synthetic Aperture Radar Imagery With Fixed Training Amount
ODOR: The ICPR2022 ODeuropa Challenge on Olfactory Object Recognition
The Odeuropa Challenge on Olfactory Object Recognition aims to foster the development of object detection in the visual arts and to promote an olfactory perspective on digital heritage.
Transfer Learning for Olfactory Object Detection
We investigate the effect of style and category similarity in multiple datasets used for object detection pretraining.
Writer Retrieval and Writer Identification in Greek Papyri
The analysis of digitized historical manuscripts is typically addressed by paleographic experts.
ArtFacePoints: High-resolution Facial Landmark Detection in Paintings and Prints
Facial landmark detection plays an important role for the similarity analysis in artworks to compare portraits of the same or similar artists.
A Multi-modal Registration and Visualization Software Tool for Artworks using CraquelureNet
For art investigations of paintings, multiple imaging technologies, such as visual light photography, infrared reflectography, ultraviolet fluorescence photography, and x-radiography are often used.
Multi-modal Retinal Image Registration Using a Keypoint-Based Vessel Structure Aligning Network
Our method extracts convolutional features from the vessel structure for keypoint detection and description and uses a graph neural network for feature matching.
ICC++: Explainable Image Retrieval for Art Historical Corpora using Image Composition Canvas
In this work, we present a novel approach called Image Composition Canvas (ICC++) to compare and retrieve images having similar compositional elements.
Exploring the Open World Using Incremental Extreme Value Machines
One particular machine learning problem in dynamic environments is open world recognition.
TorMentor: Deterministic dynamic-path, data augmentations with fractals
We propose the use of fractals as a means of efficient data augmentation.
Ranked #1 on
No real Data Binarization
on DIBCO and H_DIBCO 2009
SliTraNet: Automatic Detection of Slide Transitions in Lecture Videos using Convolutional Neural Networks
With the increasing number of online learning material in the web, search for specific content in lecture videos can be time consuming.
A Keypoint Detection and Description Network Based on the Vessel Structure for Multi-Modal Retinal Image Registration
Our method demonstrates the best registration performance on our and a public multi-modal dataset in comparison to competing methods.
First steps on Gamification of Lung Fluid Cells Annotations in the Flower Domain
Annotating data, especially in the medical domain, requires expert knowledge and a lot of effort.
Module-Power Prediction from PL Measurements using Deep Learning
While these areas can be easily identified from electroluminescense (EL) images, this is much harder for photoluminescence (PL) images.
SmartPatch: Improving Handwritten Word Imitation with Patch Discriminators
As of recent generative adversarial networks have allowed for big leaps in the realism of generated images in diverse domains, not the least of which being handwritten text generation.
How Will Your Tweet Be Received? Predicting the Sentiment Polarity of Tweet Replies
As a strong baseline, we propose a two-stage DL-based method: first, we create automatically labeled training data by applying a standard sentiment classifier to tweet replies and aggregating its predictions for each original tweet; our rationale is that individual errors made by the classifier are likely to cancel out in the aggregation step.
Ranked #1 on
Tweet-Reply Sentiment Analysis
on RETWEET
Deep Learning-based Patient Re-identification Is able to Exploit the Biometric Nature of Medical Chest X-ray Data
Our verification system is able to identify whether two frontal chest X-ray images are from the same person with an AUC of 0. 9940 and a classification accuracy of 95. 55%.
Pixel-wise Distance Regression for Glacier Calving Front Detection and Segmentation
In this work, we propose to mitigate the class-imbalance between the calving front class and the non-calving front class by reformulating the segmentation problem into a pixel-wise regression task.
On Mathews Correlation Coefficient and Improved Distance Map Loss for Automatic Glacier Calving Front Segmentation in SAR Imagery
Moreover, we propose an improvement to the distance map-based binary cross-entropy (BCE) loss function.
Bayesian U-Net for Segmenting Glaciers in SAR Imagery
It is therefore important to precisely monitor the position of the calving front.
Synthetic Glacier SAR Image Generation from Arbitrary Masks Using Pix2Pix Algorithm
Supervised machine learning requires a large amount of labeled data to achieve proper test results.
Glacier Calving Front Segmentation Using Attention U-Net
An essential climate variable to determine the tidewater glacier status is the location of the calving front position and the separation of seasonal variability from long-term trends.
Enhancing Human Pose Estimation in Ancient Vase Paintings via Perceptually-grounded Style Transfer Learning
(2) To improve the already strong results further, we created a small dataset (ClassArch) consisting of ancient Greek vase paintings from the 6-5th century BCE with person and pose annotations.
Joint Super-Resolution and Rectification for Solar Cell Inspection
Visual inspection of solar modules is an important monitoring facility in photovoltaic power plants.
ICFHR 2020 Competition on Image Retrieval for Historical Handwritten Fragments
In particular, we investigate the performance of large-scale retrieval of historical document fragments in terms of style and writer identification.
Deep Learning-based Pipeline for Module Power Prediction from EL Measurements
However, knowledge of the power at maximum power point is important as well, since drops in the power of a single module can affect the performance of an entire string.
Understanding Compositional Structures in Art Historical Images using Pose and Gaze Priors
These compositions are useful in analyzing the interactions in an image to study artists and their artworks.
The Notary in the Haystack -- Countering Class Imbalance in Document Processing with CNNs
In classification, notarial instruments are distinguished from other documents, while the notary sign is separated from the certificate in the segmentation task.
Proof of Concept: Automatic Type Recognition
The type used to print an early modern book can give scholars valuable information about the time and place of its production as well as its producer.
Re-ranking for Writer Identification and Writer Retrieval
We show that a re-ranking step based on k-reciprocal nearest neighbor relationships is advantageous for writer identification, even if only a few samples per writer are available.
Recognizing Characters in Art History Using Deep Learning
We present experiments and analysis on three different models and show that the model trained on domain related data gives the best performance for recognizing character.
Spatio-Temporal Handwriting Imitation
Then, a method for online handwriting synthesis is used to produce a new realistic-looking text primed with the online input sequence.
Weakly Supervised Segmentation of Cracks on Solar Cells using Normalized Lp Norm
To this end, we apply normalized Lp normalization to aggregate the activation maps into single scores for classification.
ICDAR 2019 Competition on Image Retrieval for Historical Handwritten Documents
This competition investigates the performance of large-scale retrieval of historical document images based on writing style.
Deep Generalized Max Pooling
Global pooling layers are an essential part of Convolutional Neural Networks (CNN).
Fast and robust detection of solar modules in electroluminescence images
We compare our method to the state of the art and show that it is superior in presence of perspective distortion while the performance on images, where the module is roughly coplanar to the detector, is similar to the reference method.
Automatic Classification of Defective Photovoltaic Module Cells in Electroluminescence Images
Both approaches are trained on 1, 968 cells extracted from high resolution EL intensity images of mono- and polycrystalline PV modules.
Adversarial and Perceptual Refinement for Compressed Sensing MRI Reconstruction
In addition, we introduce a semantic interpretability score, measuring the visibility of the region of interest in both ground truth and reconstructed images, which allows us to objectively quantify the usefulness of the image quality for image post-processing and analysis.
Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings
Embedding data into vector spaces is a very popular strategy of pattern recognition methods.
Hyper-Hue and EMAP on Hyperspectral Images for Supervised Layer Decomposition of Old Master Drawings
In this work, we propose an image processing pipeline that operates on hyperspectral images to separate such layers.
Towards Arbitrary Noise Augmentation - Deep Learning for Sampling from Arbitrary Probability Distributions
Our model has high sampling efficiency and is easily applied to any probability distribution, without the need of further analytical or numerical calculations.
Encoding CNN Activations for Writer Recognition
The encoding of local features is an essential part for writer identification and writer retrieval.
Image Registration for the Alignment of Digitized Historical Documents
In this work, we conducted a survey on different registration algorithms and investigated their suitability for hyperspectral historical image registration applications.
Sketch Layer Separation in Multi-Spectral Historical Document Images
High-resolution imaging has delivered new prospects for detecting the material composition and structure of cultural treasures.
Unsupervised Feature Learning for Writer Identification and Writer Retrieval
The focus lies on the ICDAR17 competition dataset on historical document writer identification (Historical-WI).
