Tea categories classification is an importance task for quality inspection. And traditional way for doing this by human is time-consuming, requirement of too much manual labor. This study proposed a method for discriminating green tea categories based on multi-spectral images technique. Four tea categories were selected for this study, and total of 243 multi-spectral images were collected using a common-aperture multi-spectral charged coupled device camera with three channels (550, 660 and 800 nm). A compound image which has the clearest outline of samples was process by combination of the three monochrome images (550, 660 and 800 nm). After image preprocessing, 18 morphometry parameters were obtained for each samples. The 18 parameters used including area, perimeter, centroid and eccentricity et al. To better understanding these parameters, principal component analysis was conducted on them, and score plot of the first three independent components was obtained. The first three components accounted for 99.02% of the variation of original 18 parameters. It can be found that the four tea categories were distributed in dense clusters respectively in score plot. But the boundaries among them were not clear, so a further discrimination must be developed. Three algorithms including support vector machines, artificial neural network and linear discriminant analysis were adopted for developed classification models based on the optimized 9 features. Wonderful result was obtained by support vector machines model with accuracy of 93.75% for prediction unknown samples in testing set. It can be concluded that it is an effective method to classification tea categories based on computer vision, and support vector machines is very specialized for development of classification model.
The sugar content of watermelon is important to its taste thus influences the market. It's difficult to know whether the melon
is sweet or not for consumers. We tried to develop a convenient meter to determine the sugar of watermelon. The first
objective of this paper was to demonstrate the feasibility of using a near-infrared reflectance spectrometer (NIRS) to
investigate the relationship between sugar content of watermelon and absorption spectra. The NIRS reflectance of
nondestructive watermelon was measured with a Visible/NIR spectrophotometer in 325-1075nm range. The sugar content
of watermelon was obtained with a handhold sugar content meter. The second objective was to measure the watermelon's
dielectric property, such as dielectric resistance, capacitance, quality factor and dielectric loss. A digital electric bridge
instrument was used to get the dielectric property. The experimental results show that they were related to watermelon's
sugar content. A comparison between the two methods was made in the paper. The model derived from NIRS reflection is
useful for class identification of Zaochun Hongyu watermelon though it's not quite accurate in sweetness prediction (the max.
deviation is 0.7). Electric property bears little relation to sugar content of watermelon at this experiment and it couldn't be
used as non-destructive inspection method.
KEYWORDS: Calibration, Statistical modeling, Near infrared, Animal model studies, Spectroscopy, Chemical analysis, Near infrared spectroscopy, Agriculture, Reflectivity, Ecosystems
This paper introduced the processing of the domestic and international livestock wastewater. The actuality of
environmental problems caused by livestock husbandry was discussed and the relationship between husbandry and
sustainable development was remarked on. From the point of ecosystem, dealing with livestock wastewater harmlessly
with bio-filtration system is advised. A bio-filtration system is set up based on the analysis of a typical and simple water
treatment system. The system mainly consists of a solid removal basin and a planting filter. We elect ryegrass as the
planting-filter, because it gets best sod, mechanic filtration and bio-filtration. Effects of static bio-filtration were studied
in ryegrass. Under this system, to achieve preferable purification efficiency, the wastewater concentration and the area of
planting which suited for pasture growth will be provided. Near infrared spectra was used to analyze the water quality,
about chemical oxygen demand (CODcr). A set of 20 samples of livestock wastewater with different concentrations was
taken from the Animal Institution of Zhejiang Agricultural Science Organization, and the partial least square (PLS) was
used to develop predictive models. To validate these models, some samples were used. SEP were 22, 32 and r2 values
using the validation set of data were 0.9895, 0.9985 for COD of wastewater.
The objective of this research was to analyze NIR spectroscopy potential to estimate COD in livestock wastewater. A
total of 20 wastewater samples were taken from the Animal Institution of Zhejiang Agricultural Science Organization.
We selected two kinds of containers with the sizes of l000mL and 2000mL for samples, because of the high absorption
peaks in the near-infrared region (350-11OOnm) around 635nm. 14 samples spectra were used during the calibration and
cross-validation stage. Five samples spectra were used to predict COD concentration in wastewater. NW spectra and
constituents were related using partial least square (PLS) technique. The r2 between measured and predicted values of
COD of wastewater with l000mL and 2000mL, 0.9895 and 0.9985, as well as SEP showed table l, 22 and 32,
respectively, demonstrated that NIR method have potential to predict COD in wastewater. While SEP and SEC is high,
because the magnitude of COD value in livestock wastewater is high. In other words, higher magnitudes will result in
high standard error values. However, the result also shows that NIR could be a good tool to be combined with
environmental monitoring of water quality.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.