Application of Hyperspectral Imaging to Discriminate the Variety of Maize Seeds
- PDF / 1,762,396 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 85 Downloads / 163 Views
Application of Hyperspectral Imaging to Discriminate the Variety of Maize Seeds Lu Wang 1 & Da-Wen Sun 1,2 & Hongbin Pu 1 & Zhiwei Zhu 1
Received: 13 December 2014 / Accepted: 18 March 2015 # Springer Science+Business Media New York 2015
Abstract Hyperspectral imaging technique was utilized as a rapid and nondestructive tool to classify different varieties of maize seeds in the current study. The feasibility of combining spectral data with texture features to improve the classification accuracy for maize seeds was analyzed. Average and pretreated spectra with detrending were extracted from the region of interest of hyperspectral images over the wavelength region of 400–1000 nm, and six optimal spectral wavelengths were selected by successive projection algorithm. Meanwhile, five textural feature variables were extracted by gray-level run-length matrix analysis. Least-square support vector machine was developed to classify different varieties of maize seeds based on spectral, textural, or fusion data. The leastsquare support vector machine model based on full pretreated spectral data (91.667 %) achieved better results than those based on full spectral data (90.741 %) and optimal spectral data (87.037 %). On the other hand, an accuracy of 88.889 % based on data fusion was achieved, which was superior to the results based on spectra (87.037 %) or texture (85.185 %) alone. At last, the resulting classification maps were developed to visualize different varieties of maize seeds. The current study indicated that combining spectral data with textural features was an effective method to improve the classification accuracy for maize varieties.
* Da-Wen Sun [email protected]; http://www.ucd.ie/refrig; http://www.ucd.ie/sun 1
College of Light Industry and Food Sciences, South China University of Technology, Guangzhou 510641, People’s Republic of China
2
Food Refrigeration and Computerised Food Technology (FRCFT), Agriculture and Food Science Centre, University College Dublin, National University of Ireland, Belfield, Dublin 4, Ireland
Keywords Maize . Corn . Classification . Spectra . Texture . Data fusion
Introduction Quality assurance is very important for the healthy development of the agricultural industry. Therefore on one hand, techniques such as drying (Sun and Woods 1997; Sun and Byrne 1998; Delgado and Sun 2002a, b), refrigeration (Sun et al. 1996; Sun 1997a, b; McDonald and Sun 2001; McDonald et al. 2001; Kiani and Sun 2011) and edible coating (Xu et al. 2001) should be employed to keep the quality of agricultural products, on the other hand, effective and efficient methods should be developed to evaluate and classify their qualities. Maize is one of the most popular staple food in many countries due to its flavor and nutrition. There are numerous maize varieties available including sweet maize, waxy maize, and dent maize (Anthony 2014). The price, use, nutrition, and quality of maize are all related to the varieties. Waxy maize contains a large amount of amylopectin and is widely used for direct consumption
Data Loading...
