원문정보
보안공학연구지원센터(IJSIP)
International Journal of Signal Processing, Image Processing and Pattern Recognition
Vol.9 No.9
2016.09
pp.279-290
피인용수 : 0건 (자료제공 : 네이버학술정보)
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
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
저자정보
참고문헌
자료제공 : 네이버학술정보