A5058813180- Handwritten Text Recognition Techniques
- Anomaly Detection Techniques and Applications
- Cell Image Analysis Techniques
- Time Series Analysis and Forecasting
- Digital Media Forensic Detection
- Explainable Artificial Intelligence (XAI)
- Topic Modeling
- Machine Learning in Bioinformatics
- RNA and protein synthesis mechanisms
- AI in cancer detection
- Adversarial Robustness in Machine Learning
- Stock Market Forecasting Methods
- Natural Language Processing Techniques
- Text and Document Classification Technologies
- Digital Imaging for Blood Diseases
- Sentiment Analysis and Opinion Mining
- Advanced Neural Network Applications
- Power Line Communications and Noise
- Image Processing and 3D Reconstruction
- Image Processing Techniques and Applications
- Advanced Text Analysis Techniques
- Advanced Image and Video Retrieval Techniques
- Cutaneous Melanoma Detection and Management
- Machine Learning and Data Classification
- Generative Adversarial Networks and Image Synthesis
German Research Centre for Artificial Intelligence
2015-2025
University of Kaiserslautern
2011-2024
International Islamic University, Islamabad
2024
The University of Agriculture, Peshawar
2023
Saad Specialist Hospital
2023
Aga Khan University
2022
Deccan College of Medical Sciences
2022
Deutsches Forschungsnetz
2020-2021
Insiders Technologies (Germany)
2017
University of Glasgow
2007
Traditional distance and density-based anomaly detection techniques are unable to detect periodic seasonality related point anomalies which occur commonly in streaming data, leaving a big gap time series the current era of IoT. To address this problem, we present novel deep learning-based approach (DeepAnT) for is equally applicable non-streaming cases. DeepAnT capable detecting wide range anomalies, i.e., contextual discords data. In contrast methods where learned, uses unlabeled data...
This paper presents a novel end-to-end system for table understanding in document images called DeepDeSRT. In particular, the contribution of DeepDeSRT is two-fold. First, it deep learning-based solution detection images. Secondly, proposes approach structure recognition, i.e. identifying rows, columns, and cell positions detected tables. contrast to existing rule-based methods, which rely on heuristics or additional PDF metadata (like, example, print instructions, character bounding boxes,...
Light microscopy combined with well-established protocols of two-dimensional cell culture facilitates high-throughput quantitative imaging to study biological phenomena. Accurate segmentation individual cells in images enables exploration complex questions, but can require sophisticated processing pipelines cases low contrast and high object density. Deep learning-based methods are considered state-of-the-art for image typically vast amounts annotated data, which there is no suitable...
With the advancement of powerful image processing and machine learning techniques, CAD has become ever more prevalent in all fields medicine including ophthalmology. Since optic disc is most important part retinal fundus for glaucoma detection, this paper proposes a two-stage framework that first detects localizes then classifies it into healthy or glaucomatous. The stage based on RCNN responsible localizing extracting from while second uses Deep CNN to classify extracted In addition...
Abstract We present Segment Anything for Microscopy, a tool interactive and automatic segmentation tracking of objects in multi-dimensional microscopy data. Our method is based on Anything, vision foundation model image segmentation. extend it by training specialized models data that significantly improve quality wide range imaging conditions. also implement annotation tools (volumetric) tracking, speed up compared to established tools. work constitutes the first application microscopy,...
This paper presents a novel approach for the detection of tables present in documents, leveraging potential deep neural networks. Conventional approaches table rely on heuristics that are error prone and specific to dataset. In contrast, presented harvests data recognize arbitrary layout. Most prior only applicable PDFs, whereas, directly works images making it generally any format. The is based combination deformable CNN with faster R-CNN/FPN. has fixed receptive field which problematic...
Propensity of skin diseases to manifest in a variety forms, lack and maldistribution qualified dermatologists, exigency timely accurate diagnosis call for automated Computer-Aided Diagnosis (CAD). This study aims at extending previous works on CAD dermatology by exploring the potential Deep Learning classify hundreds diseases, improving classification performance, utilizing disease taxonomy. We trained state-of-the-art Neural Networks two largest publicly available image datasets, namely...
In this work, we present the Text Conditioned Auxiliary Classifier Generative Adversarial Network, (TAC-GAN) a text to image Network (GAN) for synthesizing images from their descriptions. Former approaches have tried condition generative process on textual data; but allying it usage of class information, known diversify generated samples and improve structural coherence, has not been explored. We trained presented TAC-GAN model Oxford-102 dataset flowers, evaluated discriminability with...
We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task document image classification to finally reduce error by more than half. Existing approaches, such as DeepDoc-Classifier, apply standard Convolutional Network architectures with transfer learning from object recognition domain. The contribution paper is threefold: First, it investigates recently introduced very deep neural network (GoogLeNet, VGG, ResNet) using (from real...
This paper presents a novel framework for the demystification of convolutional deep learning models time-series analysis. is step toward making informed/explainable decisions in domain time series, powered by learning. There have been numerous efforts to increase interpretability image-centric neural network models, where learned features are more intuitive visualize. Visualization series significantly challenging, as there no direct interpretation filters and inputs compared with imaging...
Time series forecasting is one of the challenging problems for humankind. Traditional methods using mean regression models have severe shortcomings in reflecting real-world fluctuations. While new probabilistic rush to rescue, they fight with technical difficulties like quantile crossing or selecting a prior distribution. To meld different strengths these fields while avoiding their weaknesses as well push boundary state-of-the-art, we introduce ForGAN - step ahead generative adversarial...
The need for robust unsupervised anomaly detection in streaming data is increasing rapidly the current era of smart devices, where enormous are gathered from numerous sensors. These sensors record internal state a machine, external environment, and interaction machines with other humans. It prime importance to leverage this information order minimize downtime machines, or even avoid completely by constant monitoring. Since each device generates different type data, it normally case that...
This paper proposes a novel complete system for automated floor plan analysis. Besides applying and improving state-of-the-art processing methods, we introduce preprocessing e.g., the differentiation between thick, medium, thin lines removal of components outside convex hull outer walls. Especially latter method increases performance final system. In our experiments on reference data set compare approach to other approaches available in literature. We show that outperforms previous systems....
This paper presents an automatic system for analyzing and labeling architectural floor plans. In order to detect the locations of rooms, proposed systems extracts both, structural semantic information from given Furthermore, OCR is applied on text layer retrieve meaningful room labeling. Finally, a novel post-processing split rooms into several sub-regions if share same physical room. Our fully evaluated publicly available dataset our experiments, we could clearly outperform other...
This paper presents a novel method for the analysis of tabular structures in document images using potential deformable convolutional networks. In order to assess suitability model task table structure recognition, most prior methods have been tested on smaller ICDAR-13 recognition dataset comprising just 156 tables. We curated new image-based dataset, TabStructDB <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> , 1081 tables densely...
Scarcity of large publicly available retinal fundus image datasets for automated glaucoma detection has been the bottleneck successful application artificial intelligence towards practical Computer-Aided Diagnosis (CAD). A few small that are research community usually suffer from impractical capturing conditions and stringent inclusion criteria. These shortcomings in already limited choice existing make it challenging to mature a CAD system so can perform real-world environment. In this...
Computational Fluid Dynamics (CFD) simulation by the numerical solution of Navier-Stokes equations is an essential tool in a wide range applications from engineering design to climate modeling. However, computational cost and memory demand required CFD codes may become very high for flows practical interest, such as aerodynamic shape optimization. This expense associated with complexity fluid flow governing equations, which include non-linear partial derivative terms that are difficult...
This paper documents how an ethically aligned co-design methodology ensures trustworthiness in the early design phase of artificial intelligence (AI) system component for healthcare. The explains decisions made by deep learning networks analyzing images skin lesions. trustworthy AI developed here used a holistic approach rather than static ethical checklist and required multidisciplinary team experts working with designers their managers. Ethical, legal, technical issues potentially arising...
This paper presents the results of ICDAR 2015 competition on signature verification and writer identification for on- off-line skilled forgeries jointly organized by PR-researchers Forensic Handwriting Examiners (FHEs). The aim is to bridge gap between recent technological developments forensic casework. Two modalities (signatures handwritten text) are considered training evaluation data collected provided FHEs PR-researchers. Four tasks defined four different languages; Bengali...
Based on the recent advancements in domain of semantic segmentation, Fully-Convolutional Networks (FCN) have been successfully applied for task table structure recognition past. We analyze efficacy segmentation networks this purpose and simplify problem by proposing prediction tiling based consistency assumption which holds tabular structures. For an image dimensions H × W, we predict a single column rows (ŷ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML"...
With the Internet of Things (IoT) devices becoming an integral part human life, need for robust anomaly detection in streaming data has also been elevated. Dozens distance-based, density-based, kernel-based, and cluster-based algorithms have proposed area detection. Recently, because robustness deep neural networks (DNN), different learning-based methods proposed. all these rapid developments, there exists a small number comparative studies methods. Even those studies, comparison is done...