检索结果-内蒙古大学图书馆

A survey of historical document image datasets

学校读者我要写书评

暂无评论

A survey of historical document image datasets

作者： Nikolaidou, Konstantina Seuret, Mathias Mokayed, Hamam Liwicki, Marcus EISLAB Machine Learning Group Luleå University of Technology Aurorum 1 Norrbotten Luleå97187 Sweden Pattern Recognition Lab Computer Vision Group Friedrich-Alexander-Universität Martensstr. 3 Bavaria Erlangen91058 Germany

This paper presents a systematic literature review of image datasets for document image analysis, focusing on historical documents, such as handwritten manuscripts and early prints. Finding appropriate datasets for historical document analysis is a crucial prerequisite to facilitate research using different machine learning algorithms. However, because of the very large variety of the actual data (e.g., scripts, tasks, dates, support systems, and amount of deterioration), the different formats for data and label representation, and the different evaluation processes and benchmarks, finding appropriate datasets is a difficult task. This work fills this gap, presenting a meta-study on existing datasets. After a systematic selection process (according to PRISMA guidelines), we select 65 studies that are chosen based on different factors, such as the year of publication, number of methods implemented in the article, reliability of the chosen algorithms, dataset size, and journal outlet. We summarize each study by assigning it to one of three pre-defined tasks: document classification, layout structure, or content analysis. We present the statistics, document type, language, tasks, input visual aspects, and ground truth information for every dataset. In addition, we provide the benchmark tasks and results from these papers or recent competitions. We further discuss gaps and challenges in this domain. We advocate for providing conversion tools to common formats (e.g., COCO format for computer vision tasks) and always providing a set of evaluation metrics, instead of just one, to make results comparable across studies. © 2022, The Author(s).

关键词： Deterioration

Focal Depth Estimation: A Calibration-Free, Subject- and Daytime Invariant Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hosp, Benedikt W. Severitt, Björn Agarwala, Rajat Robust, Evgenia Rusak Sauer, Yannick Wahl, Siegfried ZEISS Vision Science Lab University of Tübingen Germany Machine Learning University of Tübingen Germany ZEISS Vision Care GmbH

In an era where personalized technology is increasingly intertwined with daily life, traditional eye-tracking systems and autofocal glasses face a significant challenge: the need for frequent, user-specific calibration, which impedes their practicality. This study introduces a groundbreaking calibration-free method for estimating focal depth, leveraging machine learning techniques to analyze eye movement features within short sequences. Our approach, distinguished by its innovative use of LSTM networks and domain-specific feature engineering, achieves a mean absolute error (MAE) of less than 10 cm, setting a new focal depth estimation accuracy standard. This advancement promises to enhance the usability of autofocal glasses and pave the way for their seamless integration into extended reality environments, marking a significant leap forward in personalized visual technology. © 2024, CC BY-SA.

关键词： Eye movements

Occlusion Resilient 3D Human Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Roy, Soumava Kumar Badanin, Ilia Honari, Sina Fua, Pascal Computer Vision Lab EPFL Switzerland Machine Learning and Optimization Lab EPFL Switzerland Samsung AI Center Toronto Canada

Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences. Temporal consistency has been extensively used to mitigate their impact but the existing algorithms in the literature do not explicitly model them. Here, we apply this by representing the deforming body as a spatio-temporal graph. We then introduce a refinement network that performs graph convolutions over this graph to output 3D poses. To ensure robustness to occlusions, we train this network with a set of binary masks that we use to disable some of the edges as in drop-out techniques. In effect, we simulate the fact that some joints can be hidden for periods of time and train the network to be immune to that. We demonstrate the effectiveness of this approach compared to state-of-the-art techniques that infer poses from single-camera sequences. © 2024, CC0.

关键词： Cameras

RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement

学校读者我要写书评

暂无评论

RecycleNet: Latent Feature Recycling Leads to Iterative Deci...

IEEE/CVF Winter Conference on Applications of Computer vision (WACV)

作者： Koehler, Gregor Wald, Tassilo Ulrich, Constantin Zimmerer, David Jaeger, Paul F. Franke, Joerg K. H. Kohl, Simon Isensee, Fabian Maier-Hein, Klaus H. German Canc Res Ctr DKFZ Heidelberg Div Med Image Comp Heidelberg Germany Helmholtz Informat & Data Sci Sch Hlth Karlsruhe Germany Helmholtz Informat & Data Sci Sch Hlth Heidelberg Germany DKFZ Helmholtz Imaging Heidelberg Germany DKFZ Natl Ctr Tumor Dis NCT NCT Heidelberg Heidelberg Germany DKFZ Interact Machine Learning Grp Heidelberg Germany DKFZ Appl Comp Vision Lab Heidelberg Germany Univ Freiburg Machine Learning Lab Freiburg Germany Latent Labs latentlabs com London England Univ Heidelberg Hosp Pattern Anal & Learning Grp Heidelberg Germany

ISBN: (纸本)9798350318920;9798350318937

Despite the remarkable success of deep learning systems over the last decade, a key difference still remains between neural network and human decision-making: As humans, we can not only form a decision on the spot, but also ponder, revisiting an initial guess from different angles, distilling relevant information, arriving at a better decision. Here, we propose RecycleNet, a latent feature recycling method, instilling the pondering capability for neural networks to refine initial decisions over a number of recycling steps, where outputs are fed back into earlier network layers in an iterative fashion. This approach makes minimal assumptions about the neural network architecture and thus can be implemented in a wide variety of contexts. Using medical image segmentation as the evaluation environment, we show that latent feature recycling enables the network to iteratively refine initial predictions even beyond the iterations seen during training, converging towards an improved decision. We evaluate this across a variety of segmentation benchmarks and show consistent improvements even compared with top-performing segmentation methods. This allows trading increased computation time for improved performance, which can be beneficial, especially for safety-critical applications.

关键词： Algorithms Algorithms and algorithms Applications Biomedical / healthcare / medicine formulations Image recognition and understanding machine learning architectures

Poison-Aware Open-Set Fungi Classification: Reducing the Risk of Poisonous Confusion 25

学校读者我要写书评

暂无评论

Poison-Aware Open-Set Fungi Classification: Reducing the Ris...

25th Working Notes of the Conference and labs of the Evaluation Forum, CLEF 2024

作者： Wolf, Stefan Thelen, Philipp Beyerer, Jürgen Vision and Fusion Lab Karlsruhe Institute of Technology KIT Vincenz-Prießnitz-Straße 3 Karlsruhe76131 Germany Fraunhofer IOSB Institute of Optronics System Technologies and Image Exploitation Fraunhoferstrasse 1 Karlsruhe76131 Germany Fraunhofer Center for Machine Learning Germany

The FungiCLEF 2024 challenge aims to foster research in the field of application-oriented fine-grained open-set classification. Particularly, it sets the challenge to optimize fungi species classification while recognizing unknown species with the evaluation of multiple metrics targeting the problems of actual use-cases, e.g., the risk of a highly detrimental confusion of a poisonous species for an edible species. To develop a well-performing approach, we focus on reducing this particular risk by introducing multiple improvements. The major improvements are a poisonous reranking which prevents predicting an edible species while a significant chance of the sample being poisonous exists and a genus loss which provides additional training information improving the regularization of the feature space. The advancements provide a large improvement in terms of poisonous confusion but also in terms of overall classification accuracy. With this approach, we achieved the 1st place in the challenge's main metric. Code is available at https://***/stefanwolf/fungi2024. © 2024 Copyright for this paper by its authors.

关键词： Invertebrates

Artists Identification Using Convolutional Sparse Autoencoder

学校读者我要写书评

暂无评论

Artists Identification Using Convolutional Sparse Autoencode...

International Conference on Computing, Engineering, and Design (ICCED)

作者： Vinnia Kemala Putri Felix Indra Kurniadi Machine Learning and Computer Vision Lab Universitas Indonesia Depok Indonesia School of Engineering and Technology Tanri Abeng University Jakarta Indonesia

ISBN: (数字)9781728120942

ISBN: (纸本)9781728120959

This paper describes a method to identify artists with a similar painting technique using a semi-unsupervised learning approach. In this paper, we compared Van Gogh and Paul Gauguin since both use impasto painting technique. The contribution of this paper lies in the use of Convolutional Sparse Autoencoder to classify Van Gogh and Paul Gauguin's paintings. The dataset consists of 450 Paul Gauguin's paintings and 716 Van Gogh's paintings. The best result was achieved by using 100 hidden neurons with test accuracy 63.85%, precision 64.12%, and recall 63.85%.

关键词： Neurons Painting Convolution Art Testing Kernel Transforms

learning a Shape-Conditioned Agent for Purely Tactile In-Hand Manipulation of Various Objects

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Pitz, Johannes Röstel, Lennart Sievers, Leon Burschka, Darius Bäuml, Berthold Learning AI for Dextrous Robots Lab Technical University of Munich Germany Germany Machine Vision and Perception Group Technical University of Munich Germany

Reorienting diverse objects with a multi-fingered hand is a challenging task. Current methods in robotic in-hand manipulation are either object-specific or require permanent supervision of the object state from visual sensors. This is far from human capabilities and from what is needed in real-world applications. In this work, we address this gap by training shape-conditioned agents to reorient diverse objects in hand, relying purely on tactile feedback (via torque and position measurements of the fingers’ joints). To achieve this, we propose a learning framework that exploits shape information in a reinforcement learning policy and a learned state estimator. We find that representing 3D shapes by vectors from a fixed set of basis points to the shape’s surface, transformed by its predicted 3D pose, is especially helpful for learning dexterous in-hand manipulation. In simulation and real-world experiments, we show the reorientation of many objects with high success rates, on par with state-of-the-art results obtained with specialized single-object agents. Moreover, we show generalization to novel objects, achieving success rates of ∼90% even for non-convex shapes. Website: https://***/manipulation/iros24 Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

SESAME: Semantic editing of scenes by adding, manipulating or erasing objects

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ntavelis, Evangelos Romero, Andrés Kastanis, Iason van Gool, Luc Timofte, Radu Computer Vision Lab. ETH Zurich Switzerland Robotics and Machine Learning CSEM SA Switzerland PSI ESAT KU Leuven Belgium

Recent advances in image generation gave rise to powerful tools for semantic image editing. However, existing approaches can either operate on a single image or require an abundance of additional information. They are not capable of handling the complete set of editing operations, that is addition, manipulation or removal of semantic concepts. To address these limitations, we propose SESAME, a novel generator-discriminator pair for Semantic Editing of Scenes by Adding, Manipulating or Erasing objects. In our setup, the user provides the semantic labels of the areas to be edited and the generator synthesizes the corresponding pixels. In contrast to previous methods that employ a discriminator that trivially concatenates semantics and image as an input, the SESAME discriminator is composed of two input streams that independently process the image and its semantics, using the latter to manipulate the results of the former. We evaluate our model on a diverse set of datasets and report state-of-the-art performance on two tasks: (a) image manipulation and (b) image generation conditioned on semantic labels. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

Transformer-based Fine-Grained Fungi Classification in an Open-Set Scenario

学校读者我要写书评

暂无评论

Transformer-based Fine-Grained Fungi Classification in an Op...

2022 Conference and labs of the Evaluation Forum, CLEF 2022

作者： Wolf, Stefan Beyerer, Jürgen Vision and Fusion Lab Karlsruhe Institute of Technology KIT c/o Technologiefabrik Haid-und-Neu-Str. 7 Karlsruhe76131 Germany Fraunhofer IOSB Institute of Optronics System Technologies and Image Exploitation Fraunhoferstrasse 1 Karlsruhe76131 Germany Fraunhofer Center for Machine Learning Germany

Fine-grained fungi classification describes the task of estimating the species of a fungus. The FungiCLEF 2022 challenge started a competition for the best solution to solve this task in an open-set scenario. For our solution, we employ a modern transformer-based classification architecture, use a class-balanced training scheme to handle the class-imbalance and apply heavy data augmentation. We approach the open-set scenario by using the final confidence scores as an indicator for unknown species. With this classification model, we were able to achieve an F1 score of 80.6 and 77.5 on the challenge’s public and private test set, respectively. This resulted in achieving the 7th place in the FungiCLEF 2022 challenge. We provide code at https://***/wolfstefan/fungi-classification. © 2022 Copyright for this paper by its authors.

关键词： Fungi