Image Segmentation Using Deep Learning: A Survey

Image segmentation is a key task in computer vision and image processing with important applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among others, and numerous segmentation algorithms are found in...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 7; pp. 3523 - 3542
Main Authors: Minaee, Shervin, Boykov, Yuri, Porikli, Fatih, Plaza, Antonio, Kehtarnavaz, Nasser, Terzopoulos, Demetri
Format: Journal Article
Language:English
Published: United States IEEE 01.07.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Augmented reality
Coders
Computational modeling
Computer architecture
Computer vision
convolutional neural networks
Deep Learning
encoder-decoder models
Encoders-Decoders
Generative adversarial networks
generative models
Image analysis
Image compression
Image processing
Image Processing, Computer-Assisted - methods
Image segmentation
instance segmentation
Literature reviews
Logic gates
Machine learning
medical image segmentation
Medical imaging
Neural Networks, Computer
panoptic segmentation
recurrent models
Robotics
Scene analysis
semantic segmentation
Semantics
Video compression
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Image segmentation is a key task in computer vision and image processing with important applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among others, and numerous segmentation algorithms are found in the literature. Against this backdrop, the broad success of deep learning (DL) has prompted the development of new image segmentation approaches leveraging DL models. We provide a comprehensive review of this recent literature, covering the spectrum of pioneering efforts in semantic and instance segmentation, including convolutional pixel-labeling networks, encoder-decoder architectures, multiscale and pyramid-based approaches, recurrent networks, visual attention models, and generative models in adversarial settings. We investigate the relationships, strengths, and challenges of these DL-based segmentation models, examine the widely used datasets, compare performances, and discuss promising research directions.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Review-3
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2021.3059968