scispace - formally typeset
Search or ask a question
Author

Marcus Liwicki

Bio: Marcus Liwicki is an academic researcher from University of Fribourg. The author has contributed to research in topics: Handwriting recognition & Feature extraction. The author has an hindex of 23, co-authored 154 publications receiving 1685 citations. Previous affiliations of Marcus Liwicki include German Research Centre for Artificial Intelligence & Kyushu University.


Papers
More filters
Proceedings ArticleDOI
11 Apr 2017
TL;DR: An exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half is presented.
Abstract: We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half. Existing approaches, such as the DeepDoc-Classifier, apply standard Convolutional Network architectures with transfer learning from the object recognition domain. The contribution of the paper is threefold: First, it investigates recently introduced very deep neural network architectures (GoogLeNet, VGG, ResNet) using transfer learning (from real images). Second, it proposes transfer learning from a huge set of document images, i.e. 400; 000 documents. Third, it analyzes the impact of the amount of training data (document images) and other parameters to the classification abilities. We use two datasets, the Tobacco-3482 and the large-scale RVL-CDIP dataset. We achieve an accuracy of 91:13% for the Tobacco-3482 dataset while earlier approaches reach only 77:6%. Thus, a relative error reduction of more than 60% is achieved. For the large dataset RVL-CDIP, an accuracy of 90:97% is achieved, corresponding to a relative error reduction of 11:5%.

73 citations

Proceedings ArticleDOI
01 Nov 2017
TL;DR: The proposed approach outperforms all previously reported structural and deep learning based methods with a final accuracy of 83.24% on Tobacco-3482 dataset, leading to a relative error reduction of 25% when compared to a previous Convolutional Neural Network (CNN) based approach (DeepDocClassifier).
Abstract: This paper presents an approach for real-time training and testing for document image classification. In production environments, it is crucial to perform accurate and (time-)efficient training. Existing deep learning approaches for classifying documents do not meet these requirements, as they require much time for training and fine-tuning the deep architectures. Motivated from Computer Vision, we propose a two-stage approach. The first stage trains a deep network that works as feature extractor and in the second stage, Extreme Learning Machines (ELMs) are used for classification. The proposed approach outperforms all previously reported structural and deep learning based methods with a final accuracy of 83.24% on Tobacco-3482 dataset, leading to a relative error reduction of 25% when compared to a previous Convolutional Neural Network (CNN) based approach (DeepDocClassifier). More importantly, the training time of the ELM is only 1.176 seconds and the overall prediction time for 2,482 images is 3.066 seconds. As such, this novel approach makes deep learning-based document classification suitable for large-scale real-time applications.

62 citations

Proceedings ArticleDOI
09 Jun 2010
TL;DR: A new database of online handwritten documents with different contents such as text, drawings, diagrams, formulas, tables, lists, and markings is presented to serve as a standard dataset for the development, training, testing and comparison of methods in the field of handwritten document analysis.
Abstract: In this paper we present a new database of online handwritten documents with different contents such as text, drawings, diagrams, formulas, tables, lists, and markings. It was designed to serve as a standard dataset for the development, training, testing and comparison of methods in the field of handwritten document analysis. The database can serve as a basis for layout analysis, and different segmentation and recognition tasks considering online or just offline information. Its size is 1,000 documents produced by approximately 200 writers including a total of 329,849 online strokes. Few constraints were imposed on the writers when creating the documents. Nonetheless, the database has a stable distribution of the different content types. A software tool was developed to allow easy access to the documents which are stored in InkML. In this paper we also present two experiments which show the challenge this database poses. They may figure as references for further research in this area.

61 citations

Journal ArticleDOI
TL;DR: A sketch-based system, namely the a.SCatch system, for querying a floor plan repository, and a novel complete system for floor plan analysis, which extracts the semantics from existing floor plans.

53 citations

Proceedings ArticleDOI
22 Aug 2015
TL;DR: The proposed approach significantly outperforms standard binarization approaches both for F-Measure and OCR accuracy with the availability of enough training samples.
Abstract: We propose to address the problem of Document Image Binarization (DIB) using Long Short-Term Memory (LSTM) which is specialized in processing very long sequences. Thus, the image is considered as a 2D sequence of pixels and in accordance to this a 2D LSTM is employed for the classification of each pixel as text or background. The proposed approach processes the information using local context and then propagates the information globally in order to achieve better visual coherence. The method is robust against most of the document artifacts. We show that with a very simple network without any feature extraction and with limited amount of data the proposed approach works reasonably well for the DIBCO 2013 dataset. Furthermore a synthetic dataset is considered to measure the performance of the proposed approach with both binarization and OCR groundtruth. The proposed approach significantly outperforms standard binarization approaches both for F-Measure and OCR accuracy with the availability of enough training samples.

52 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: This historical survey compactly summarizes relevant work, much of it from the previous millennium, review deep supervised learning, unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.

14,635 citations

Journal ArticleDOI
TL;DR: This paper presents the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling, and observes that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.
Abstract: Several variants of the long short-term memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks have become the state-of-the-art models for a variety of machine learning problems. This has led to a renewed interest in understanding the role and utility of various computational components of typical LSTM variants. In this paper, we present the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling. The hyperparameters of all LSTM variants for each task were optimized separately using random search, and their importance was assessed using the powerful functional ANalysis Of VAriance framework. In total, we summarize the results of 5400 experimental runs ( $\approx 15$ years of CPU time), which makes our study the largest of its kind on LSTM networks. Our results show that none of the variants can improve upon the standard LSTM architecture significantly, and demonstrate the forget gate and the output activation function to be its most critical components. We further observe that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.

4,746 citations

01 Jan 1979
TL;DR: This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis and addressing interesting real-world computer Vision and multimedia applications.
Abstract: In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to: • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information. Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

1,758 citations

Journal ArticleDOI
TL;DR: The recent advance of deep learning based sensor-based activity recognition is surveyed from three aspects: sensor modality, deep model, and application and detailed insights on existing work are presented and grand challenges for future research are proposed.

1,334 citations

Proceedings ArticleDOI
23 Aug 2020
TL;DR: The LayoutLM is proposed to jointly model interactions between text and layout information across scanned document images, which is beneficial for a great number of real-world document image understanding tasks such as information extraction from scanned documents.
Abstract: Pre-training techniques have been verified successfully in a variety of NLP tasks in recent years. Despite the widespread use of pre-training models for NLP applications, they almost exclusively focus on text-level manipulation, while neglecting layout and style information that is vital for document image understanding. In this paper, we propose the LayoutLM to jointly model interactions between text and layout information across scanned document images, which is beneficial for a great number of real-world document image understanding tasks such as information extraction from scanned documents. Furthermore, we also leverage image features to incorporate words' visual information into LayoutLM. To the best of our knowledge, this is the first time that text and layout are jointly learned in a single framework for document-level pre-training. It achieves new state-of-the-art results in several downstream tasks, including form understanding (from 70.72 to 79.27), receipt understanding (from 94.02 to 95.24) and document image classification (from 93.07 to 94.42). The code and pre-trained LayoutLM models are publicly available at https://aka.ms/layoutlm.

388 citations