Identification of Impurities in Fresh Shrimp Using Improved Majority Scheme-Based Classifier
- PDF / 961,724 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 6 Downloads / 162 Views
Identification of Impurities in Fresh Shrimp Using Improved Majority Scheme-Based Classifier Zihao Liu 1 & Fang Cheng 1 & Hanmei Hong 1
Received: 2 November 2015 / Accepted: 23 March 2016 # Springer Science+Business Media New York 2016
Abstract The efficient removal of impurities from postharvest 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. Keywords Impurity identification . Combination classifiers . IMAJ
Introduction Increasing emphasis on shrimp quality and safety is a major driving force to establish automatic shrimp classification systems. China’s Ministry of Agriculture stipulates explicitly that no defective shrimp and impurities should be included in cir* Fang Cheng [email protected]
1
College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, People’s Republic of China
culated shrimp products in supermarkets (Wang et al. 2013). This trend is likely to continue in Asia-Pacific Economic Cooperation (APEC) countries, the European Union, the USA, and even worldwide. Defective harvested shrimp are mostly infected with viruses, such as Taura syndrome virus (TSV) (Koh et al. 2014), white spot syndrome virus (WSSV) (Jariyapong et al. 2015), infectious hypodermal and hematopoietic necrosis virus (IHHNV) (Galvan-Alvarez et al. 2012), and hepatopancreatic parvovirus (HPV) (Madan et al. 2014). Shrimp infected with TSV, WSSV, IHHNV, and HPV are more likely to suffer with surface damage and defects, such as shuck adherence and soft shuck, white spot areas in the body, body paleness, thin body, and deep body color. In addition, the most common foreign impurity is the little white fish. Defective shrimp and fish are collectively called impurities. Traditional processes to remove impurities are accomplished manually, thus presenting shortcomings of being strongly subjective, time-consuming, and unable to provide data record. Tail-less and soft shuck shrimp often show large similarities with sound shrimp in appearance. Thus, discerning the difference with human eyes becomes difficult. An automatic shrimp classification system with high accuracy and high efficiency is expected. In our previous studies of identifying impurity (Liu Zihao 2015), three difficulties are hindering our progresses, which are listed as follows: 1. Generally, to enhance the processing speed and yield of products, most ima
Data Loading...
