Identification of Impurities in Fresh Shrimp Using Improved Majority Scheme-Based Classifier
| Autor: | Zihao Liu, Fang Cheng, Hanmei Hong |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Majority rule
business.industry Comparison results Pattern recognition 02 engineering and technology 01 natural sciences Applied Microbiology and Biotechnology Analytical Chemistry Shrimp 010309 optics Classification rate 0103 physical sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Safety Risk Reliability and Quality business Safety Research Classifier (UML) Food Science Mathematics |
| Zdroj: | Food Analytical Methods. 9:3133-3142 |
| ISSN: | 1936-976X 1936-9751 |
| DOI: | 10.1007/s12161-016-0497-3 |
| Popis: | The efficient removal of impurities from post-harvest raw shrimp is beneficial to improve the quality of shrimp products. Single feature combined with single classifier results in poor classification rate. Moreover, accuracy of combined classifiers remains unsatisfactory, especially when sound shrimp is mixed with various defective shrimp and impurities. In this study, an improved majority rule (IMAJ) classifier combination scheme was proposed to address this problem. The accuracy of IMAJ (91.53 %) was compared with six other kinds of classifier combination schemes proposed by Kittler. The schemes include Sum (89.93 %), Product (65.99 %), Max (89.76 %), Min (80 %), Median (88.18 %), and Majority (89.2 %). Comparison results indicate that the combination classifier based on IMAJ rule is superior. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink