Researches Advanced in Image Recognition based on Deep Learning
DOI:
https://doi.org/10.54097/hset.v39i.6760Keywords:
Image Recognition; Deep Learning; Computer Vision.Abstract
In the discipline of computer vision, which tries to create a model to predict the category of objects present in a given image, image recognition has always been a research hotspot. Early image recognition models were mainly based on manual features, and their recognition accuracy and generalization ability often fluctuated greatly with changes in the scene, which could not meet the actual application requirements. Convolutional neural networks have progressed quickly, which has accelerated the development of deep learning-based image recognition. in this paper, we detail the development of image recognition technology. Specifically, we introduce the three approaches of convolutional neural network, recurrent neural network, and graph neural network as the traditional methods of image recognition. including their design ideas, key steps, advantages and disadvantages. We also compare the recognition accuracy of different methods on the ImageNe dataset to try to explore the application boundaries of different methods. Finally, we go over the difficulties in the area of image identification and project its future growth.
Downloads
References
Cheng Qiyun, Sun Caixin, Zhang Xiaoxing, et al. Short-Term load forecasting model and method for power system based on complementation of neural network and fuzzy logic. Transactions of China Electrotechnical Society, 2004, 19(10): 53-58.
Fangfang. Research on power load forecasting based on Improved BP neural network. Harbin Institute of Technology, 2011.
Amjady N. Short-term hourly load forecasting using time series modeling with peak load estimation capability. IEEE Transactions on Power Systems, 2001, 16(4): 798-805.
Ma Kunlong. Short term distributed load forecasting method based on big data. Changsha: Hunan University, 2014.
SHI Biao, LI Yu Xia, YU Xhua, YAN Wang. Short-term load forecasting based on modified particle swarm optimizer and fuzzy neural network model. Systems Engineering-Theory and Practice, 2010, 30(1): 158-160.
Fangfang. Research on power load forecasting based on Improved BP neural network. Harbin Institute of Technology, 2011.
Amjady N. Short-term hourly load forecasting using time series modeling with peak load estimation capability. IEEE Transactions on Power Systems, 2001, 16(4): 798-805.
Ma Kunlong. Short term distributed load forecasting method based on big data. Changsha: Hunan University, 2014.
SHI Biao, LI Yu Xia, YU Xhua, YAN Wang. Short-term load forecasting based on modified particle swarm optimizer and fuzzy neural network model. Systems Engineering-Theory and Practice, 2010, 30(1): 158-160.
Fangfang. Research on power load forecasting based on Improved BP neural network. Harbin Institute of Technology, 2011.
Amjady N. Short-term hourly load forecasting using time series modeling with peak load estimation capability. IEEE Transactions on Power Systems, 2001, 16(4): 798-805.
Ma Kunlong. Short term distributed load forecasting method based on big data. Changsha: Hunan University, 2014.
SHI Biao, LI Yu Xia, YU Xhua, YAN Wang. Short-term load forecasting based on modified particle swarm optimizer and fuzzy neural network model. Systems Engineering-Theory and Practice, 2010, 30(1): 158-160.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
