Open Access

ARTICLE

A Review on Deep Learning Approaches to Image Classification and Object Segmentation

by Hao Wu, Qi Liu, Xiaodong Liu

1 Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), School of Computer and Software, Nanjing University of Information Science & Technology, No. 219, Ningliu Road, Nanjing, 210044, China.
2 Shandong BetR Medical Technology Co., Ltd.
3 School of Computer and Software, Nanjing University of Information Science & Technology, No. 219, Ningliu Road, Nanjing, 210044, China.
4 School of Computing, Edinburgh Napier University, 10 Colinton Road, Edinburgh, EH10 5DT, UK.

* Corresponding Author: Qi Liu. Email: .

Computers, Materials & Continua 2019, 60(2), 575-597. https://doi.org/10.32604/cmc.2019.03595

Abstract

Deep learning technology has brought great impetus to artificial intelligence, especially in the fields of image processing, pattern and object recognition in recent years. Present proposed artificial neural networks and optimization skills have effectively achieved large-scale deep learnt neural networks showing better performance with deeper depth and wider width of networks. With the efforts in the present deep learning approaches, factors, e.g., network structures, training methods and training data sets are playing critical roles in improving the performance of networks. In this paper, deep learning models in recent years are summarized and compared with detailed discussion of several typical networks in the field of image classification, object detection and its segmentation. Most of the algorithms cited in this paper have been effectively recognized and utilized in the academia and industry. In addition to the innovation of deep learning algorithms and mechanisms, the construction of large-scale datasets and the development of corresponding tools in recent years have also been analyzed and depicted.

---

Keywords

---

Citations