Research on computer vision technology based on BP-LSTM hybrid network
The computer vision direction in the field of artificial intelligence analyses the latest progress of computer vision technology from visual perception and visual generation, including but not limited to image recognition, target detection and image segmentation. First of all, for computer vision te...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2023-07-01
|
| Series: | Applied Mathematics and Nonlinear Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/amns.2021.2.00270 |
| _version_ | 1797266169332236288 |
|---|---|
| author | Yi Qiaoling Ling Shijia Chen Guoluan Liu Liangfang |
| author_facet | Yi Qiaoling Ling Shijia Chen Guoluan Liu Liangfang |
| author_sort | Yi Qiaoling |
| collection | DOAJ |
| description | The computer vision direction in the field of artificial intelligence analyses the latest progress of computer vision technology from visual perception and visual generation, including but not limited to image recognition, target detection and image segmentation. First of all, for computer vision technology, this paper introduces the detailed application of image recognition technology, object detection technology and image segmentation technology. Then, we build a BP neural network combined with a deep LSTM neural network, use the BP network algorithm to select the input variables to reduce the dimension and complexity of the model, and use the selected variables as the input of the deep LSTM network. At the same time, deep LSTM is used to perform high-dimensional deep memory learning features on the selected variables. Finally, the model is separately experimented in computer vision. The experimental results show that the present model and other single models can be selected by BP neural network variables in computer vision applications, which can effectively reduce the complexity of the model and improve the generalisation ability of the model, so that it can be used in computer vision research. |
| first_indexed | 2024-03-07T16:20:02Z |
| format | Article |
| id | doaj.art-b99b6cde089d4777b90c6cc17975865a |
| institution | Directory Open Access Journal |
| issn | 2444-8656 |
| language | English |
| last_indexed | 2024-04-25T00:56:25Z |
| publishDate | 2023-07-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Applied Mathematics and Nonlinear Sciences |
| spelling | doaj.art-b99b6cde089d4777b90c6cc17975865a2024-03-11T10:05:45ZengSciendoApplied Mathematics and Nonlinear Sciences2444-86562023-07-018297598410.2478/amns.2021.2.00270Research on computer vision technology based on BP-LSTM hybrid networkYi Qiaoling0Ling Shijia1Chen Guoluan2Liu Liangfang31Zhongshan Polytechnic, Zhongshan, Guangdong528400, China1Zhongshan Polytechnic, Zhongshan, Guangdong528400, China1Zhongshan Polytechnic, Zhongshan, Guangdong528400, China1Zhongshan Polytechnic, Zhongshan, Guangdong528400, ChinaThe computer vision direction in the field of artificial intelligence analyses the latest progress of computer vision technology from visual perception and visual generation, including but not limited to image recognition, target detection and image segmentation. First of all, for computer vision technology, this paper introduces the detailed application of image recognition technology, object detection technology and image segmentation technology. Then, we build a BP neural network combined with a deep LSTM neural network, use the BP network algorithm to select the input variables to reduce the dimension and complexity of the model, and use the selected variables as the input of the deep LSTM network. At the same time, deep LSTM is used to perform high-dimensional deep memory learning features on the selected variables. Finally, the model is separately experimented in computer vision. The experimental results show that the present model and other single models can be selected by BP neural network variables in computer vision applications, which can effectively reduce the complexity of the model and improve the generalisation ability of the model, so that it can be used in computer vision research.https://doi.org/10.2478/amns.2021.2.00270deep neural networkbp networklstmcomputer vision |
| spellingShingle | Yi Qiaoling Ling Shijia Chen Guoluan Liu Liangfang Research on computer vision technology based on BP-LSTM hybrid network Applied Mathematics and Nonlinear Sciences deep neural network bp network lstm computer vision |
| title | Research on computer vision technology based on BP-LSTM hybrid network |
| title_full | Research on computer vision technology based on BP-LSTM hybrid network |
| title_fullStr | Research on computer vision technology based on BP-LSTM hybrid network |
| title_full_unstemmed | Research on computer vision technology based on BP-LSTM hybrid network |
| title_short | Research on computer vision technology based on BP-LSTM hybrid network |
| title_sort | research on computer vision technology based on bp lstm hybrid network |
| topic | deep neural network bp network lstm computer vision |
| url | https://doi.org/10.2478/amns.2021.2.00270 |
| work_keys_str_mv | AT yiqiaoling researchoncomputervisiontechnologybasedonbplstmhybridnetwork AT lingshijia researchoncomputervisiontechnologybasedonbplstmhybridnetwork AT chenguoluan researchoncomputervisiontechnologybasedonbplstmhybridnetwork AT liuliangfang researchoncomputervisiontechnologybasedonbplstmhybridnetwork |