location:Home > 2018 Vol.1 Jun No.3 > Deep learning annotation method based on multi-features

2018 Vol.1 Jun No.3

  • Title: Deep learning annotation method based on multi-features
  • Name: Cleveland Damona
  • Company: Transylvania University,America
  • Abstract:

    The traditional deep learning annotation method has a long working time and the positioning accuracy is very poor. A new learning annotation method is studied for the above problems. The method structure and workflow are designed. The annotation method structure consists of two parts: regular RBM and deep neuron network. In order to test the working effect of the method, compared with the traditional method, it can be seen from the results that the designed standard method is short in time, high in precision, and has a good development space. This study has certain guiding significance for academic analysis.

  • Keyword: Multi-Feature; Fusion Feature; Deep Learning; Image Semantic Annotation
  • DOI: 10.12250/jpciams2018030112
  • Citation form: Cleveland Damona.Deep learning annotation method based on multi-features[J]. Computer Informatization and Mechanical System, 2018, vol. 1, pp. 42-46.
Reference:

[1] Hu Junping, Deng Peng, Li Yongcheng. Research on vehicle detection based on multi feature fusion and PSVM, [J]. Computer Simulation, 2017, 15 (12): 326-330.
[2] Huang Dongmei, Xu Qiongqiong, He Qi, and so on. Integrated multi feature depth learning annotation methods [J]. Computer Engineering And Applications, 2018, 54 (1): 224-228.
[3] Liu Weibin, Zou Zhiyuan, Zou Zhiyuan. Feature fusion method in pattern classification [J]. Journal of Beijing University of Posts and Telecommunications, 2017, 40 (4): 1-8.
[4] Beam Rui, Zhu Qingxin, Liao Shujiao, and so on. [J]. computer application based on multi feature fusion, [J]. Computer Application, 2017, 37 (4): 1179-1184.
[5] Song Pei Yu and Xing Yan. The multi feature fusion of Chinese micro-blog emotion analysis Methods to study the [J]. Electronic World, 2018, 25 (2): 20-21.
[6] Pei Xiaomin, Fan Huijie, Tang Yan Dong. Time space feature fusion depth learning network human behavior identification method [J]. Infrared And Laser Engineering, 2018, 47 (2): 55-60.
[7] Wang Jun, Charlie min. Detection of abnormal behavior based on deep learning characteristics [J]. Journal of Hunan University (NATURAL SCIENCE) 2017, 44 (10): 130-138.
[8] Gong An, Ding Mingbo, Dou Fei. DBN based multi feature fusion music emotion classification method [J]. Computer System Application, 2017, 26 (9): 158-164.

Tsuruta Institute of Medical Information Technology
Address:[502,5-47-6], Tsuyama, Tsukuba, Saitama, Japan TEL:008148-28809 fax:008148-28808 Japan,Email:jpciams@hotmail.com,2019-09-16