Online citations, reference lists, and bibliographies.

Deep Learning Vs. Traditional Computer Vision

Niall O' Mahony, S. Campbell, Anderson Carvalho, Suman Harapanahalli, G. Velasco-Hernández, L. Krpalkova, D. Riordan, J. Walsh
Published 2019 · Computer Science

Cite This
Download PDF
Analyze on Scholarcy
Share
Deep Learning has pushed the limits of what was possible in the domain of Digital Image Processing. However, that is not to say that the traditional computer vision techniques which had been undergoing progressive development in years prior to the rise of DL have become obsolete. This paper will analyse the benefits and drawbacks of each approach. The aim of this paper is to promote a discussion on whether knowledge of classical computer vision techniques should be maintained. The paper will also explore how the two sides of computer vision can be combined. Several recent hybrid methodologies are reviewed which have demonstrated the ability to improve computer vision performance and to tackle problems not suited to Deep Learning. For example, combining traditional computer vision techniques with Deep Learning has been popular in emerging domains such as Panoramic Vision and 3D vision for which Deep Learning models have not yet been fully optimised.
This paper references
10.1155/2017/8348671
High Performance Implementation of 3D Convolutional Neural Networks on a GPU
Qiang Lan (2017)
10.1007/s11263-015-0816-y
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky (2015)
10.1007/s11263-014-0795-4
Scene Understanding by Reasoning Stability and Safety
Bo Zheng (2014)
10.1007/978-3-319-66709-6_28
Optical Flow-Based 3D Human Motion Estimation from Monocular Video
Thiemo Alldieck (2017)
10.1007/11744023_34
Machine Learning for High-Speed Corner Detection
E. Rosten (2006)
10.1007/s11263-018-1070-x
Augmented Reality Meets Computer Vision: Efficient Data Generation for Urban Driving Scenes
Hassan Abu Alhaija (2018)
A guide to convolution arithmetic for deep learning
Vincent Dumoulin (2016)
10.1109/ISSC.2016.7528449
Adaptive process control and sensor fusion for process analytical technology
Niall O' Mahony (2016)
10.1155/2018/4276291
A Classifier Graph Based Recurring Concept Detection and Prediction Approach
Y. Sun (2018)
Efficient Training of Small Kernel Convolutional Neural Networks using Fast Fourier Transform
Tyler Highlander (2015)
10.5220/0005823306900697
Pixel-wise Ground Truth Annotation in Videos - An Semi-automatic Approach for Pixel-wise and Semantic Object Annotation
Julius Schöning (2016)
Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images
E. Karami (2017)
10.1109/ISSC.2017.7983607
Improving controller performance in a powder blending process using predictive control
Niall O' Mahony (2017)
10.1145/2945078.2945148
Real time 360° video stitching and streaming
Rodrigo Marques Almeida da Silva (2016)
10.1214/009053604000000760
The Hough transform estimator
A. Goldenshluger (2004)
10.1109/IROS.2018.8593795
Hybrid Bayesian Eigenobjects: Combining Linear Subspace and Deep Network Methods for 3D Robot Vision
B. Burchfiel (2018)
Deep Learning: A Critical Appraisal
G. Marcus (2018)
Learning Priors for Invariance
Eric T. Nalisnick (2018)
10.1038/s41529-018-0058-x
A review of deep learning in the study of materials degradation
Will Nash (2018)
10.1109/LRA.2018.2850532
Layouts From Panoramic Images With Geometry and Deep Learning
Clara Fernandez-Labrador (2018)
10.1109/TPAMI.2017.2709749
SIFT Meets CNN: A Decade Survey of Instance Retrieval
L. Zheng (2018)
10.1109/ISSC.2018.8585381
Deep Learning for Visual Navigation of Unmanned Ground Vehicles : A review
Niall O’Mahony (2018)
10.1155/2018/1639561
Real-Time Human Detection for Aerial Captured Video Sequences via Deep Models
Nouar AlDahoul (2018)
10.1007/11744023_32
SURF: Speeded Up Robust Features
H. Bay (2006)
10.1109/ICSENST.2017.8304431
Real-time monitoring of powder blend composition using near infrared spectroscopy
Niall O' Mahony (2017)
10.1016/j.patcog.2018.06.017
Learning spatial relations and shapes for structural object description and scene recognition
M. Clément (2018)
Dataset Augmentation in Feature Space
Terrance Devries (2017)
10.1109/CVPR.2012.6248075
Teaching 3D geometry to deformable part models
Bojan Pepik (2012)
Comparative Study of Deep Learning Software Frameworks
S. Bahrampour (2016)
10.1145/3041957
Business Process Variability Modeling
M. Rosa (2017)
10.1155/2018/7068349
Deep Learning for Computer Vision: A Brief Review
A. Voulodimos (2018)
10.1016/J.JMSY.2018.01.003
Deep learning for smart manufacturing: Methods and applications
J. Wang (2018)
10.1007/978-3-030-01258-8_23
Modeling Visual Context is Key to Augmenting Object Detection Datasets
Nikita Dvornik (2018)
10.1007/978-3-319-10602-1_48
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin (2014)
10.5244/C.29.160
Very Efficient Training of Convolutional Neural Networks using Fast Fourier Transform and Overlap-and-Add
Tyler Highlander (2015)
10.3390/s17061341
Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images †
L. Ran (2017)
10.1145/3042064
Deep Learning Advances in Computer Vision with 3D Data: A Survey
Anastasia Ioannidou (2017)
10.1109/ICIP.2018.8451487
Curvature Augmented Deep Learning for 3D Object Recognition
Sarah Braeger (2018)
On the Selection of Initialization and Activation Function for Deep Neural Networks
Soufiane Hayou (2018)
10.1007/s11704-016-5520-8
The role of prior in image based 3D modeling: a survey
H. Zhu (2016)
10.1109/TPAMI.2019.2911075
Significance of Softmax-Based Features in Comparison to Distance Metric Learning-Based Features
Shota Horiguchi (2020)
10.1109/ICPR.2016.7899697
3D point cloud object detection with multi-view convolutional neural network
Guan Pang (2016)
10.1109/CVPR.2018.00470
PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition
Mikaela Angelina Uy (2018)
10.1111/cgf.13276
Photometric Stabilization for Fast‐forward Videos
X. Zhang (2017)
10.1109/CVPR.2018.00472
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
Yin Zhou (2018)
10.1155/2018/4149103
A Composite Model of Wound Segmentation Based on Traditional Methods and Deep Neural Networks
Fangzhao Li (2018)
10.1155/2017/1827016
A Novel Ensemble Method for Imbalanced Data Learning: Bagging of Extrapolation-SMOTE SVM
Qi Wang (2017)
10.1145/3065386
ImageNet classification with deep convolutional neural networks
A. Krizhevsky (2017)
10.1016/0031-3203(94)90115-5
Geometric hashing with line features
Frank C. D. Tsai (1994)
10.1080/01431161.2018.1519277
A hybrid of deep learning and hand-crafted features based approach for snow cover mapping
Rahul Nijhawan (2019)
10.1109/ICCV.2015.510
Learning Spatiotemporal Features with 3D Convolutional Networks
Du Tran (2015)
Image Identification Using SIFT Algorithm: Performance Analysis against Different Image Deformations
E. Karami (2017)
10.1109/CVPR.2019.00784
Hybrid Scene Compression for Visual Localization
Federico Camposeco (2019)
10.1007/978-3-319-19665-7_36
Image Alignment for Panorama Stitching in Sparsely Structured Environments
G. Meneghetti (2015)
10.1109/ICMLA.2017.00-37
Integrating Prior Knowledge into Deep Learning
M. Diligenti (2017)
10.1109/FG.2018.00068
Hand-Crafted Feature Guided Deep Learning for Facial Expression Recognition
Guohang Zeng (2018)
The Effectiveness of Data Augmentation in Image Classification using Deep Learning
L. Perez (2017)
10.1109/LRA.2019.2921506
Recurrent Convolutional Fusion for RGB-D Object Recognition
Mohammad Reza Loghmani (2019)
10.1145/2818346.2830593
Deep Learning for Emotion Recognition on Small Datasets using Transfer Learning
Hongwei Ng (2015)



This paper is referenced by
10.3390/s20102799
Shoreline Detection and Land Segmentation for Autonomous Surface Vehicle Navigation with the Use of an Optical System
S. Hożyń (2020)
10.23919/ICACT48636.2020.9061472
EyeNet: An Improved Eye States Classification System using Convolutional Neural Network
Md. Ekhlasur Rahman (2020)
10.3389/fmed.2020.00318
Artificial Intelligence in Cutaneous Oncology
Yu Seong Chu (2020)
10.1016/j.promfg.2020.05.134
Digital image processing with deep learning for automated cutting tool wear detection
Thomas Bergs (2020)
10.1101/2020.07.02.185454
An open-source experimental framework for automation of cell biology experiments
Pavel Katunin (2020)
EXPO-HD: Exact Object Perception using High Distraction Synthetic Data
Roey Ron (2020)
Emotion Recognition on large video dataset based on Convolutional Feature Extractor and Recurrent Neural Network
Denis Rangulov (2020)
10.1038/s41524-020-00380-w
Quantifying defects in thin films using machine vision
Nina Taherimakhsousi (2020)
10.1016/j.jfoodeng.2020.110036
An automatic sorting system for unwashed eggs using deep learning
Amin Nasiri (2020)
10.1007/s11042-020-08767-z
Semi-supervised learning with deep convolutional generative adversarial networks for canine red blood cells morphology classification
Kitsuchart Pasupa (2020)
10.1109/ACCESS.2020.2993289
Dynamic Collaborative Filtering Based on User Preference Drift and Topic Evolution
Charinya Wangwatcharakul (2020)
10.23919/ICCAS47443.2019.8971680
Comparison of Object Recognition Approaches using Traditional Machine Vision and Modern Deep Learning Techniques for Mobile Robot
Sumaira Manzoor (2019)
10.3390/app10061900
Identification of Breast Malignancy by Marker-Controlled Watershed Transformation and Hybrid Feature Set for Healthcare
Tariq Sadad (2020)
10.3390/s20061708
Jellytoring: Real-Time Jellyfish Monitoring Based on Deep Learning Object Detection
Miguel Martin-Abadal (2020)
10.1109/ICAICTA.2019.8904400
Improving Performance of YOLOv3 for Vehicle Detection
Pratamamia A. Prihatmaja (2019)
Instance Segmentation of Buildings in Satellite Images
Karin Fritz (2020)
10.1002/eng2.12141
Data‐driven nonrigid object feature analysis: Subspace application of incidence structure
Nicholas Dominic Wells (2020)
10.1016/j.ifacol.2019.12.555
3D Vision for Precision Dairy Farming
Niall O' Mahony (2019)
10.1109/ISSC49989.2020.9180175
Audio Pre-Processing and Neural Network Models for Identification of Orthopedic Reamers in Use
Michelle Hanlon (2020)
10.1109/ACCESS.2020.3007528
Classification of Financial Tickets Using Weakly Supervised Fine-Grained Networks
Hanning Zhang (2020)
10.1111/tgis.12610
Cartographic reconstruction of building footprints from historical maps: A study on the Swiss Siegfried map
Magnus Heitzler (2020)
10.1109/ACCESS.2020.3018666
A Comprehensive Review of Computer-Aided Diagnosis of Pulmonary Nodules Based on Computed Tomography Scans
Wenming Cao (2020)
Semantic Scholar Logo Some data provided by SemanticScholar