检索结果-内蒙古大学图书馆

Text Detection and Recognition in the Wild: A Review

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Raisi, Zobeir Naiel, Mohamed A. Fieguth, Paul Wardell, Steven Zelek, John Vision and Image Processing Lab and Department of Systems Design Engineering University of Waterloo ONN2L 3G1 Canada ATS Automation Tooling Systems Inc. CambridgeONN3H 4R7 Canada

Detection and recognition of text in natural im-ages are two main problems in the field of computer vision that have a wide variety of applications in analysis of sports videos, autonomous driving, industrial automation, to name a few. They face common challenging problems that are factors in how text is represented and affected by several environmental conditions. The current state-of-the-art scene text detection and/or recognition methods have exploited the witnessed advancement in deep learning architectures and reported a superior accuracy on benchmark datasets when tackling multi-resolution and multi-oriented text. However, there are still several remaining challenges affecting text in the wild images that cause existing methods to underperform due to there models are not able to generalize to unseen data and the insufficient labeled data. Thus, unlike previous surveys in this field, the objectives of this survey are as follows: first, offering the reader not only a review on the recent advancement in scene text detection and recognition, but also presenting the results of conducting extensive experiments using a unified evaluation framework that assessespre-trained models of the selected methods on challenging cases, and applies the same evaluation criteria on these techniques. Second, identifying several existing challenges for detecting or recognizing text in the wild images, namely, in-plane-rotation, multi-oriented and multi-resolution text, perspective distortion, illumination reflection, partial occlusion, complex fonts, and special characters. Finally, the paper also presents insight into the potential research directions in this field to address some of the mentioned challenges that are still encountering scene text detection and recognition techniques. Copyright © 2020, The Authors. All rights reserved.

关键词： Surveys

An inverse problem approach to computational active depth from defocus 9

学校读者我要写书评

暂无评论

An inverse problem approach to computational active depth fr...

9th International Conference on Inverse Problems in engineering, ICIPE 2017

作者： Ma, A. Wong, A. Vision and Image Processing Lab Systems Design Engineering University of Waterloo 200 University Ave W WaterlooONN2L 3G1 Canada

A novel methodology for inferring depth measurements using active quasi-random colored point projection patterns is presented by recourse to computational inverse modelling within the context of depth from defocus. The forward problem is considered that when capturing objects using a camera, light reflected off of objects at different depths will result in blurry observations in the acquired image, whereas the inverse problem seeks to estimate the depth from the knowledge of the blurry observations. In the proposed approach, a colored quasi-random point projection pattern is projected onto the scene of interest, and each projection point in the image captured by a cellphone camera is analyzed using an inverse model to estimate the depth at that point. The proposed method has a relatively simple setup, consisting of a camera and a projector, and enables depth inference from a single capture. We conclude with qualitative and quantitative results that highlight the strong potential for enabling active depth sensing in a simple, efficient manner. © Published under licence by IOP Publishing Ltd.

关键词： Inverse problems

Auto-Detection of Safety Issues in Baby Products

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Bleaney, Graham Kuzyk, Matthew Man, Julian Mayanloo, Hossein Tizhoosh, H.R. Systems Design Engineering University of Waterloo WaterlooON Canada KIMIA Lab University of Waterloo ON Canada

Every year, thousands of people receive consumer product related injuries. Research indicates that online customer reviews can be processed to autonomously identify product safety issues. Early identification of safety issues can lead to earlier recalls, and thus fewer injuries and deaths. A dataset of product reviews from *** was compiled, along with *** complaints and recall descriptions from the Consumer Product Safety Commission (CPSC) and European Commission Rapid Alert system. A system was built to clean the collected text and to extract relevant features. Dimensionality reduction was performed by computing feature relevance through a Random Forest and discarding features with low information gain. Various classifiers were analyzed, including Logistic Regression, SVMs, Naïve-Bayes, Random Forests, and an Ensemble classifier. Experimentation with various features and classifier combinations resulted in a logistic regression model with 66% precision in the top 50 reviews surfaced. This classifier outperforms all benchmarks set by related literature and consumer product safety professionals. Copyright © 2018, The Authors. All rights reserved.

关键词： Consumer products

A review of uncertainty quantification in deep learning: Techniques, applications and challenges

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Abdar, Moloud Pourpanah, Farhad Hussain, Sadiq Rezazadegan, Dana Liu, Li Ghavamzadeh, Mohammad Fieguth, Paul Cao, Xiaochun Khosravi, Abbas Rajendra Acharya, U. Makarenkov, Vladimir Nahavandi, Saeid Deakin University Australia College of Mathematics and Statistics Guangdong Key Lab. of Intelligent Information Processing Shenzhen University Shenzhen518060 China Dibrugarh University Dibrugarh India Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia Center for Machine Vision and Signal Analysis University of Oulu Oulu Finland Google research United States Department of Systems Design Engineering University of Waterloo Waterloo Canada State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China Department of Electronics and Computer Engineering Ngee Ann Polytechnic Clementi Singapore Department of Computer Science University of Quebec in Montreal MontrealQC Canada

—Uncertainty quantification (UQ) plays a pivotal role in the reduction of uncertainties during both optimization and decision making, applied to solve a variety of real-world applications in science and engineering. Bayesian approximation and ensemble learning techniques are two of the most widely-used UQ methods in the literature. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc. This study reviews recent advances in UQ methods used in deep learning, investigates the application of these methods in reinforcement learning, and highlight the fundamental research challenges and directions associated with the UQ field. Copyright © 2020, The Authors. All rights reserved.

关键词： Image segmentation

Simultaneous induction of SSMVEP and SMR using a gaiting video stimulus: A novel hybrid brain-computer interface

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Xin Xu, Guanghua Ravi, Aravind Pearce, Sarah Jiang, Ning The Department of Systems Design Engineering Engineering Bionics Lab University of Waterloo WaterlooONN2L3G1 Canada School of Mechanical Engineering Xi'an Jiaotong University Xi'an Shaanxi710049 China Cognixion Inc. TorontoONM5H 1K5 Canada

We proposed a novel visual stimulus for brain-computer interface. The stimulus is in the form gaiting sequence of a human. The hypothesis is that observing such a visual stimulus would simultaneously induce 1) steady-state motion visual evoked potential (SSMVEP) in the occipital area, similarly to an SSVEP stimulus;and 2) sensorimotor rhythm (SMR) in the primary sensorimotor area, because such action observation (AO) could activate the mirror neuron system. Canonical correlation analysis (CCA) was used to detect SSMVEP from occipital EEG, and event-related spectral perturbations (ERSP) were used to identify SMR in the EEG from the sensorimotor area. The results showed that the proposed visual gaiting stimulus-induced SSMVEP, with classification accuracies of 88.9 ± 12.0% in a four-class scenario. More importantly, it induced clear and sustained event-related desynchronization/synchronization (ERD/ERS) in the EEG from the sensorimotor area, while no ERD/ERS in the sensorimotor area could be observed when the other two SSVEP stimuli were used. Further, for participants with sufficiently clear SSMVEP pattern (classification accuracy > 85%), the ERD index values in mu-beta band induced by the proposed gaiting stimulus were statistically different from that of the other two types of stimulus. Therefore, a novel BCI based on the proposed stimulus has potential in neurorehabilitation applications because it simultaneously has the high accuracy of an SSMVEP (~90% accuracy in a four-class setup) and the ability to activate sensorimotor cortex. And such potential will be further explored in future studies. Copyright © 2019, The Authors. All rights reserved.

关键词： Brain computer interface

Comparing LBP, HOG and Deep Features for Classification of Histopathology Images

学校读者我要写书评

暂无评论

Comparing LBP, HOG and Deep Features for Classification of H...

International Joint Conference on Neural Networks

作者： Taha J. Alhindi Shivam Kalra Ka Hin Ng Anika Afrin Hamid R. Tizhoosh Systems Design Engineering University of Waterloo Canada Electrical and Computer Engineering University of Waterloo Canada Kimia Lab University of Waterloo Canada

Medical image analysis has become a topic under the spotlight in recent years. There is a significant progress in medical image research concerning the usage of machine learning. However, there are still numerous questions and problems awaiting answers and solutions, respectively. In the present study, comparison of three classification models is conducted using features extracted using local binary patterns, the histogram of gradients, and a pre-trained deep network. Three common image classification methods, including support vector machines, decision trees, and artificial neural networks are used to classify feature vectors obtained by different feature extractors. We use KIMIA Path960, a publicly available dataset of 960 histopathology images extracted from 20 different tissue scans to test the accuracy of classification and feature extractions models used in the study, specifically for the histopathology images. SVM achieves the highest accuracy of 90.52% using local binary patterns as features which surpasses the accuracy obtained by deep features, namely 81.14%.

关键词： Feature extraction Support vector machines Machine learning Histograms Cancer Decision trees Neural networks

Toward the universal quantum cloner limit for designing compact photonic CNOT gate

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Gueddana, Amor Lakshminarayanan, Vasudevan Green & Smart Communication Systems Lab Gres'Com Engineering School of Communication of Tunis Sup'Com University of Carthage Ghazela Technopark Ariana2083 Tunisia Theoretical & Experimental Epistemology Lab TEEL School of Optometry and Vision Science University of Waterloo 200 University Avenue West WaterlooONN2l 3G1 Canada Department of Physics Department of Electrical and Computer Engineering Department of Systems Design Engineering University of Waterloo 200 University Avenue West WaterlooONN2l 3G1 Canada

We suggest a near deterministic compact model of a photonic CNOT gate based on a quantum dot trapped in a double sided optical microcavity and a universal cloner. Our design surpasses the cloner optimal limit of 5/6 and we show that it provides fidelity around 91 % in the weak coupling regime. Copyright © 2019, The Authors. All rights reserved.

关键词： Semiconductor quantum dots

PolyNeuron: Automatic neuron discovery via learned polyharmonic spline activations

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Hryniowski, Andrew Wong, Alexander Video and Image Processing Lab Systems Design Engineering University of Waterloo Waterloo Artificial Intelligence Institute WaterlooON DarwinAI Corp. WaterlooON

Automated deep neural network architecture design has received a significant amount of recent attention. However, this attention has not been equally shared by one of the fundamental building blocks of a deep neural network, the neurons. In this study, we propose PolyNeuron, a novel automatic neuron discovery approach based on learned polyharmonic spline activations. More specifically, PolyNeuron revolves around learning polyharmonic splines, characterized by a set of control points, that represent the activation functions of the neurons in a deep neural network. A relaxed variant of PolyNeuron, which we term PolyNeuron-R, loosens the constraints imposed by PolyNeuron to reduce the computational complexity for discovering the neuron activation functions in an automated manner. Experiments show both PolyNeuron and PolyNeuron-R lead to networks that have improved or comparable performance on multiple network architectures (LeNet-5 and ResNet-20) using different datasets (MNIST and CIFAR10). As such, automatic neuron discovery approaches such as PolyNeuron is a worthy direction to explore. Copyright © 2018, The Authors. All rights reserved.

关键词： Neurons

A dataset and preliminary results for umpire pose detection using SVM classification of deep features

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Ravi, Aravind Venugopal, Harshwin Paul, Sruthy Tizhoosh, Hamid R. Department of Systems Design Engineering University of Waterloo Canada Department of Electrical and Computer Engineering University of Waterloo Canada Kimia Lab University of Waterloo Canada

In recent years, there has been increased interest in video summarization and automatic sports highlights generation. In this work, we introduce a new dataset, called SNOW, for umpire pose detection in the game of cricket. The proposed dataset is evaluated as a preliminary aid for developing systems to automatically generate cricket highlights. In cricket, the umpire has the authority to make important decisions about events on the field. The umpire signals important events using unique hand signals and gestures. We identify four such events for classification namely SIX, NO BALL, OUT and WIDE based on detecting the pose of the umpire from the frames of a cricket video. Pre-trained convolutional neural networks such as Inception V3 and VGG19 networks are selected as primary candidates for feature extraction. The results are obtained using a linear SVM classifier. The highest classification performance was achieved for the SVM trained on features extracted from the VGG19 network. The preliminary results suggest that the proposed system is an effective solution for the application of cricket highlights generation. Copyright © 2018, The Authors. All rights reserved.

关键词： Video recording