scispace - formally typeset
Search or ask a question
Author

Michael Blumenstein

Bio: Michael Blumenstein is an academic researcher from University of Technology, Sydney. The author has contributed to research in topics: Feature extraction & Handwriting recognition. The author has an hindex of 37, co-authored 328 publications receiving 4764 citations. Previous affiliations of Michael Blumenstein include Commonwealth Scientific and Industrial Research Organisation & Australian Artificial Intelligence Institute.


Papers
More filters
Proceedings ArticleDOI
01 Aug 2017
TL;DR: The experimental results show that VGG16 with Faster R-CNN perform better than other architectures on the training dataset, and visual analysis of the test dataset is also presented.
Abstract: The object detection is a challenging problem in computer vision with various potential real-world applications. The objective of this study is to evaluate the deep learning based object detection techniques for detecting drones. In this paper, we have conducted experiments with different Convolutional Neural Network (CNN) based network architectures namely Zeiler and Fergus (ZF), Visual Geometry Group (VGG16) etc. Due to sparse data available for training, networks are trained with pre-trained models using transfer learning. The snapshot of trained models is saved at regular interval during training. The best models having high mean Average Precision (mAP) for each network architecture are used for evaluation on the test dataset. The experimental results show that VGG16 with Faster R-CNN perform better than other architectures on the training dataset. Visual analysis of the test dataset is also presented.

130 citations

Proceedings ArticleDOI
03 Aug 2003
TL;DR: This research describes neural network-based techniques for segmented character recognition that may be applied to the segmentation and recognition components of an off-line handwritten word recognition system.
Abstract: High accuracy character recognition techniques can provide useful information for segmentation-based handwritten word recognition systems. This research describes neural network-based techniques for segmented character recognition that may be applied to the segmentation and recognition components of an off-line handwritten word recognition system. Two neural architectures along with two different feature extraction techniques were investigated. A novel technique for character feature extraction is discussed and compared with others in the literature. Recognition results above 80% are reported using characters automatically segmented from the CEDAR benchmark database as well as standard CEDAR alphanumerics.

125 citations

Journal ArticleDOI
TL;DR: The big picture of application areas of 3DVWs presented in this review could be of value and offer insights to both the health care community and researchers.
Abstract: Background: A three-dimensional virtual world (3DVW) is a computer-simulated electronic 3D virtual environment that users can explore, inhabit, communicate, and interact with via avatars, which are graphical representations of the users. Since the early 2000s, 3DVWs have emerged as a technology that has much to offer the health care sector. Objective: The purpose of this study was to characterize different application areas of various 3DVWs in health and medical context and categorize them into meaningful categories. Methods: This study employs a systematic literature review on the application areas of 3DVWs in health care. Our search resulted in 62 papers from five top-ranking scientific databases published from 1990 to 2013 that describe the use of 3DVWs for health care specific purposes. We noted a growth in the number of academic studies on the topic since 2006. Results: We found a wide range of application areas for 3DVWs in health care and classified them into the following six categories: academic education, professional education, treatment, evaluation, lifestyle, and modeling. The education category, including professional and academic education, contains the largest number of papers (n=34), of which 23 are related to the academic education category and 11 to the professional education category. Nine papers are allocated to treatment category, and 8 papers have contents related to evaluation. In 4 of the papers, the authors used 3DVWs for modeling, and 3 papers targeted lifestyle purposes. The results indicate that most of the research to date has focused on education in health care. We also found that most studies were undertaken in just two countries, the United States and the United Kingdom. Conclusions: 3D virtual worlds present several innovative ways to carry out a wide variety of health-related activities. The big picture of application areas of 3DVWs presented in this review could be of value and offer insights to both the health care community and researchers.

120 citations

Proceedings ArticleDOI
18 Sep 2011
TL;DR: A signature verification competition on datasets with two scripts (Dutch and Chinese) in which questions were asked to compare questioned signatures against a set of reference signatures and methods used by Forensic Handwriting Examiners (FHEs) were applied.
Abstract: The Netherlands Forensic Institute and the Institute for Forensic Science in Shanghai are in search of a signature verification system that can be implemented in forensic casework and research to objectify results. We want to bridge the gap between recent technological developments and forensic casework. In collaboration with the German Research Center for Artificial Intelligence we have organized a signature verification competition on datasets with two scripts (Dutch and Chinese) in which we asked to compare questioned signatures against a set of reference signatures. We have received 12 systems from 5 institutes and performed experiments on online and offline Dutch and Chinese signatures. For evaluation, we applied methods used by Forensic Handwriting Examiners (FHEs) to assess the value of the evidence, i.e., we took the likelihood ratios more into account than in previous competitions. The data set was quite challenging and the results are very interesting.

111 citations

Proceedings ArticleDOI
14 May 2017
TL;DR: This paper presents a review of various state-of-the-art deep learning-based techniques proposed for human action recognition on three types of datasets, namely, single viewpoint, multiple viewpoint and RGB-depth videos.
Abstract: Video-based human action recognition has become one of the most popular research areas in the field of computer vision and pattern recognition in recent years. It has a wide variety of applications such as surveillance, robotics, health care, video searching and human-computer interaction. There are many challenges involved in human action recognition in videos, such as cluttered backgrounds, occlusions, viewpoint variation, execution rate, and camera motion. A large number of techniques have been proposed to address the challenges over the decades. Three different types of datasets namely, single viewpoint, multiple viewpoint and RGB-depth videos, are used for research. This paper presents a review of various state-of-the-art deep learning-based techniques proposed for human action recognition on the three types of datasets. In light of the growing popularity and the recent developments in video-based human action recognition, this review imparts details of current trends and potential directions for future work to assist researchers.

109 citations


Cited by
More filters
01 Jun 2012
TL;DR: SPAdes as mentioned in this paper is a new assembler for both single-cell and standard (multicell) assembly, and demonstrate that it improves on the recently released E+V-SC assembler and on popular assemblers Velvet and SoapDeNovo (for multicell data).
Abstract: The lion's share of bacteria in various environments cannot be cloned in the laboratory and thus cannot be sequenced using existing technologies. A major goal of single-cell genomics is to complement gene-centric metagenomic data with whole-genome assemblies of uncultivated organisms. Assembly of single-cell data is challenging because of highly non-uniform read coverage as well as elevated levels of sequencing errors and chimeric reads. We describe SPAdes, a new assembler for both single-cell and standard (multicell) assembly, and demonstrate that it improves on the recently released E+V-SC assembler (specialized for single-cell data) and on popular assemblers Velvet and SoapDeNovo (for multicell data). SPAdes generates single-cell assemblies, providing information about genomes of uncultivatable bacteria that vastly exceeds what may be obtained via traditional metagenomics studies. SPAdes is available online ( http://bioinf.spbau.ru/spades ). It is distributed as open source software.

10,124 citations

01 Jan 2006

3,012 citations

Reference EntryDOI
15 Oct 2004

2,118 citations

09 Mar 2012
TL;DR: Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems as mentioned in this paper, and they have been widely used in computer vision applications.
Abstract: Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

2,069 citations