Application of improved deep forest algorithm in image recognition

Shiyang Shi; Linna Liu; Jianyin Fang; Huaijun Deng

doi:10.1117/12.2652487

20 October 2022 Application of improved deep forest algorithm in image recognition

Shiyang Shi, Linna Liu, Jianyin Fang, Huaijun Deng

Proceedings Volume 12350, 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022); 1235025 (2022) https://doi.org/10.1117/12.2652487
Event: 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 2022, Qingdao, China

Abstract

With the continuous development of artificial intelligence technology, the method based on deep learning has become a research hotspot in the field of engineering. However, the setting of super parameters and the amount of training data are strictly required for the deep neural networks, which is difficult to meet the needs of rapid, accurate and stable diagnosis in practical industry. To solve above problems, a diagnosis method based on improved deep forest was proposed, which is applied to small-scale data sets. The cascade forest stage of traditional deep forest model has problems like high computational cost and redundant data processing, therefore, in the paper a deep forest model based on Linear Discriminant Analysis (LDA) feature extraction is designed. The improved deep forest model improves the data transmission and processing ability in multi-granularity scanning and cascade forest, and enhances the feature representation in the model while ensuring the data diversity, so as to improve the operation efficiency and diagnosis performance of the algorithm. Compared with the traditional machine learning methods, the experimental results show that the improved method has better accuracy.

Citation Download Citation

Shiyang Shi, Linna Liu, Jianyin Fang, and Huaijun Deng "Application of improved deep forest algorithm in image recognition", Proc. SPIE 12350, 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235025 (20 October 2022); https://doi.org/10.1117/12.2652487

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available