Theoretical and Natural Science
- The Open Access Proceedings Series for Conferences
Series Vol. 5 , 25 May 2023
* Author to whom correspondence should be addressed.
Deep learning is a key technological tool in the field of image identification with wide application prospects because of its significant benefits in feature extraction and model fitting. Deep learning entails numerous stages of non-linear transformations. The primary implementation of the current deep learning technique is the deep neural network, the connection pattern of which takes its reference from the way that the visual cortex of animals is organized. Among all the deep learning methods, Convolutional Neural Network (CNN) is one of the most renowned means to process image. It has excellent performance in terms of large-scale image processing. A convolutional neural network consists of convolutional layers, a fully connected layer, a pooling layer, and associated weights. Convolutional neural networks have fewer parameters to consider than other deep, feed forward neural networks, making them an attractive deep learning architecture. There are several traits in CNN, including pooling, shared weights, and local connections. With the help of these features, the network's complexity and the quantity of training parameters can be decreased, and the model's level of invariance to scale, shift, and distortion can be increased, along with its robustness and fault tolerance. This paper firstly summarized the history of convolutional neural network, then briefly discussed the components like the neuron and multilayer perception. The main structure of the CNN is showed afterwards. The paper also mentioned the features and the applications of CNN, mainly in the field of Computer Vision (CV).
Convolutional neural network, Deep learning, Machine learning, Image processing.
1. Hubel D et al. 1968 Receptive fields and functional architecture of monkey striate cortex. The Journal of Physiology 215-243.
2. Fukushima K et al. 1982 Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition In Competition and cooperation in neural nets (pp. 267-285) Springer Berlin Heidelberg.
3. LeCun Y et al. 1989 Handwritten digit recognition with a back-propagation network Advances in neural information processing systems 2.
4. LeCun Y et al. 1998 Gradient-based learning applied to document recognition Proceedings of the IEEE 86(11) 2278-2324.
5. Nair V et al. 2010 Rectified linear units improve restricted boltzmann machines. In Icml.
6. Gu J et al. 2018 Recent advances in convolutional neural networks Pattern recognition 77 354-377
7. Daidaidemao 2022 A detailed introduction to CNN [Online] CSDN.
8. Krizhevsky A et al. 2017 Imagenet classification with deep convolutional neural networks Communications of the ACM 60(6) 84-90.
9. Taigman Y et al. 2014 Deepface: Closing the gap to human-level performance in face verification In Proceedings of the IEEE conference on computer vision and pattern recognition pp. 1701-1708.
10. Schroff F et al. 2015 Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition pp. 815-823.
11. Yu Q 2019 Semantic segmentation of intracranial hemorrhages in head CT scans In 2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS) pp. 112-115.
12. Sarvamangala D R 2021 Convolutional neural networks in medical image understanding: a survey Evolutionary intelligence 1-22.
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open Access Instruction).