Earticle

초록

영어

In image recognition field, the fact is that the trained image classifier can not recognize the images, whose class type is not the same as the training data. To resolve this problem, a new image classifier is proposed, which is based on the class incremental extreme learning machine. The new classifier can recognize the normal images well, label them with new labels, and update itself with the new labeled data. Tested on the real-world daily activity data set, the results show that our algorithm performs well.

목차

Abstract
 1. Problem Description
 2. Relevant Work
 3. Image Classification Technique Based on Class-Incremental Learning
  3.1. Framework of the Algorithm
  3.2. ELM Model with Recognition Capacity for Suspected Abnormal Images
  3.3. Identification and Labeling of Samples of New Image Classes
  3.4. Transfer and Updating of ELM Model
 4. Experiment and Result Analysis
  4.1. Data Preparation
  4.2. Algorithm Performance Evaluation
 5. Summary
 Acknowledgment
 References

키워드

저자

• Wei Tao [ China National Digital Switching System Engineering＆Technological R＆D Center, Zhengzhou City, Henan Province, Computer College, Henan institute of engineering, Zhengzhou City, Henan Province, China ]
• Ji Xin-Sheng [ Computer College, Henan institute of engineering, Zhengzhou City, Henan Province, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Signal Processing, Image Processing and Pattern Recognition

• 간기

  격월간

• pISSN

  2005-4254

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605