Nondestructive Freshness Discriminating of Shrimp Using Visible/Near-Infrared Hyperspectral Imaging Technique and Deep L
- PDF / 1,801,488 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 100 Downloads / 169 Views
Nondestructive Freshness Discriminating of Shrimp Using Visible/Near-Infrared Hyperspectral Imaging Technique and Deep Learning Algorithm Xinjie Yu 1,2
&
Lie Tang 2 & Xiongfei Wu 3 & Huanda Lu 1
Received: 18 June 2017 / Accepted: 28 September 2017 # Springer Science+Business Media, LLC 2017
Abstract In this study, visible and near-infrared hyperspectral imaging (HSI) technique combined with deep learning algorithm was investigated for discriminating the freshness of shrimp during cold storage. Shrimps were labeled into two freshness grades (fresh and stale) according to their total volatile basic nitrogen contents. Spectral features were extracted from the HSI data by stacked auto-encoders (SAEs)based deep learning algorithm and then used to classify the freshness grade of shrimp by a logistic regression (LR)-based deep learning algorithm. The results demonstrated that the SAEs–LR achieved satisfactory total classification accuracy of 96.55 and 93.97% for freshness grade of shrimp in calibration (116 samples) and prediction (116 samples) sets, respectively. An image processing algorithm was also developed for visualizing the classification map of freshness grade. Results confirmed the possibility of rapid and nondestructive detecting freshness grade of shrimp by the combination of hyperspectral imaging technique and deep learning algorithm. The SAEs–LR method adds a new tool for the multivariate analysis of hyperspectral image for shrimp quality inspections.
* Xinjie Yu [email protected] * Lie Tang [email protected]
1
Ningbo Institute of Technology, Zhejiang University, Ningbo 315100, China
2
Department of Agricultural and Biosystems Engineering, Iowa State University, Ames, IA 50011, USA
3
Ningbo Marine and Fishery Research Institute, Ningbo 315100, China
Keywords Detection . Cold storage . Freshness . Stacked auto-encoders . Logistic regression . Hyperspectral imaging
Introduction Shrimp is one of the most delicious seafood, with a high nutritional value and many health benefits (Mohebbi et al. 2009). However, the shrimp is hard to preserve and its freshness usually degrades rapidly in a few days due to its high content in protein and moisture (Liu et al. 2015). Consumption of deteriorated shrimp could cause serious health hazards (Tsironi et al. 2009; Mastromatteo et al. 2010). Therefore, in order to guarantee the quality and safety of this highly perishable seafood, the rapid and nondestructive detection of freshness in shrimp is a necessary task. Volatile compounds such as ammonia, dimethylamine, and trimethylamine, which are known as total volatile basic nitrogen (TVB-N), are products of microbial degradation and are considered as important indicators to evaluate the freshness of shrimp. If the TVB-N content in shrimp is detected, its freshness grade could be assessed under the TVB-N content (Okpala et al. 2014). Recently, hyperspectral imaging (HSI) technology has been used to quantitatively detect TVB-N content in shrimp for the purpose of freshness assessment (Cheng and Sun 2014; Dai e
Data Loading...
