Effective classification of Chinese tea samples in hyperspectral imaging

Abstract

Maximum likelihood and neural classifiers are two typical techniques in image classification. This paper investigates how to adapt these approaches to hyperspectral imaging for the classification of five kinds of Chinese tea samples, using visible light hyperspectral spectroscopy rather than near-infrared. After removal of unnecessary parts from each imaged tea sample using a morphological cropper, principal component analysis is employed for feature extraction. The two classifiers are then respectively applied for pixel-level classification, followed by modal-filter based post-processing for robustness. Although the samples look similar to the naked eye, promising results are reported and analysed in these comprehensive experiments. In addition, it is found that the neural classifier outperforms the maximum likelihood classifier in this context

Fast implementation of two-dimensional singular spectrum analysis for effective data classification in hyperspectral imaging

“…The grouping stage is represented by the equation in (2), and even though in [14] we computed the multiplication T t t U U , actually computing the two multiplications from ) ( 2D T X U U t t keeping the order from brackets is less complex, so the complexity is stated as (…”

“…presenting 2-D scenes in a wide spectral range with contiguous wavelengths. This cube provides 1-D spectral signatures in each pixel, so elements in the 2-D scene can be recognized and labeled with promising accuracy in quite diverse applications such as food quality analysis [1,2], health/medical studies [3], arts [4], or remote sensing [5,6].…”

Hyperspectral Imaging as a Rapid Quality Control Method for Herbal Tea Blends

“…In the past decade, the technique has found applications for quality assessment of raw materials and products in various sectors such as agricultural, food and pharmaceutical industries [23,24]. Hyperspectral imaging is used to acquire a spectrum for each pixel in the imaging scene with the purpose of finding objects or identifying materials.…”

Segmentation of multispectral images and prediction of CHI-A concentration for effective ocean colour remote sensing

“…Multispectral/hyperspectral imaging recently has been applied in a wide range of application areas such as remote sensing [1], forensics [2], pharmaceuticals [3] and food analysis [4]. Hyperspectral imaging collects information from across the electro-magnetic spectrum, and thus produces dense sampling in the spectral domain, and can provide much richer information and better discrimination ability than visible light images.…”