This research aimed for development multi-spectral imaging technique for green tea categories discrimination based on texture analysis. Three key wavelengths of 550, 650 and 800 nm were implemented in a common-aperture multi-spectral charged coupled device camera, and images were acquired for 190 unique images in a four different kinds of green tea data set. An image data set consisting of 15 texture features for each image was generated based on texture analysis techniques including grey level co-occurrence method (GLCM) and texture filtering. For optimization the texture features, 5 features that weren't correlated with the category of tea were eliminated. Unsupervised cluster analysis was conducted using the optimized texture features based on principal component analysis. The cluster analysis showed that the four kinds of green tea could be separated in the first two principal components space, however there was overlapping phenomenon among the different kinds of green tea. To enhance the performance of discrimination, least squares support vector machine (LSSVM) classifier was developed based on the optimized texture features. The excellent discrimination performance for sample in prediction set was obtained with 100%, 100%, 75% and 100% for four kinds of green tea respectively. It can be concluded that texture discrimination of green tea categories based on multi-spectral image technology is feasible.
In this research, the potential ofusing the Visible/Near Infrared Spectroscopy (VisINIRS) was investigated for measuring
the reducing sugar of Fuji apple (from Shanxi of China), and the relationship was established between nondestructive
Vis/NIR spectral measurement and the reducing sugar of apple. Intact apple fruit were measured by reflectance Vis/NIR
in 325-1075 nm range. The data set as the logarithms of the reflectance reciprocal (absorbance (logl/R)) was analyzed in
order to build the best calibration model for this characteristic, using some spectral pretreatments and multivariate
calibration techniques such as partial least square regression (PLS). The models for the reducing sugar (r=0.915),
standard error of prediction (SEP) 0.562 with a bias of 0.054; shown the excellent prediction performance. The Vis/NIR
spectroscopy technique had significantly greater accuracy for determining the reducing sugar. It was concluded that by
using the Vis/NIRS measurement technique, in the spectral range (325-1075 nm), it is possible to assess the reducing
sugar content of apple.
KEYWORDS: Principal component analysis, Near infrared spectroscopy, Reflectivity, Statistical modeling, Near infrared, Reliability, Neurons, Neural networks, Spectroscopy, Data modeling
A new method for discrimination of apple varieties by means of infrared spectroscopy (NIRS) was developed. First, the
characteristic spectra of apple were got through principal component analysis (PCA), the analysis suggested that the
cumulative reliabilities of PC (principal component)1 and PC2 was more than 98%. The 2-dimensions plot was drawn
with the scores of the first and the second principal components; it appeared to provide the best clustering of the vaneties
of apple. PCA compressed thousands of spectral data into several variables that described the body of spectra; the
several variables were applied as inputs to a back propagation neural network with one hidden layer. 75 samples with
three varieties were selected randomly, then they were used to build BP-ANN model. This model had been used to predict
the varieties of 15 unknown samples; the recognition rate of 100% was achieved. This model is reliable and practicable.
So this paper could offer a new approach to the fast discrimination of apple varieties methods.
Visible/Near Infrared Speciroscopy (Vis/NIR) appears as a prominent technique for nondestructive fruit quality
assessment. This research work was focused in to evaluate the use of Vis/NIRS in measuring the quality characteristics
of intact Fuji apple (from Shanxi of China), and the relationship was established between nondestructive Vis/NIR
spectral measurement and the soluble solids content of apple. Intact apple fruit were measured by reflectance Vis/NIR in
325-1075 nm range. The data set as the logarithms of the reflectance reciprocal (absorbance (logl/R)) was analyzed in
order to build the best calibration model for this characteristic, using some spectral pretreatments and multivariate
calibration techniques such as partial least square regression (PLS). The models for the SSC (r =0.862), standard error of
prediction (SEP) 0.907 with a bias of 0.599; shown the reasonable prediction performance. The Vis/NIR spectroscopy
technique had significantly accuracy for detennining the SSC. It was concluded that the Vis/NIRS measurement
technique seems reliable to assess the soluble solids content of apple non-destructively.
KEYWORDS: Mathematical modeling, Spectroscopy, Near infrared, Statistical modeling, Calibration, Data modeling, Chemical analysis, Principal component analysis, Statistical analysis, Reflectivity
In order to measuring the sugar content of yogurt rapidly, a fast measurement of sugar content of yogurt using
Vis/NIR-spectroscopy techniques was established. 25 samples selected separately from five different brands of yogurt
were measured by Vis/NIR-spectroscopy. The sugar content of yogurt on positions scanned by spectrum were measured
by a sugar content meter. The mathematical model between sugar content and Vis/NIR spectral measurements was
established and developed based on partial least squares (PLS). The correlation coefficient of sugar content based on
PLS model is more than 0.894, and standard error of calibration (SEC) is 0.356, standard error of prediction (SEP) is
0.389. Through predicting the sugar content quantitatively of 35 samples of yogurt from 5 different brands, the
correlation coefficient between predictive value and measured value of those samples is more than 0.934. The results
show the good to excellent prediction performance. The Vis/NIR spectroscopy technique had significantly greater
accuracy for determining the sugar content. It was concluded that the Vis/NIRS measurement technique seems reliable to
assess the fast measurement of sugar content of yogurt, and a new method for the measurement of sugar content of
yogurt was established.
This work is aim to present a new approach for discrimination of varieties of tea by means of infrared spectroscopy
(NIRS) (325-1075nm). The relationship has been established between the reflectance spectra and tea varieties. The data
set consists of a total of 150 samples of tea. First, the spectra data was analyzed with principal component analysis. It
appeared to provide the reasonable clustering of the varieties of tea. PCA compressed thousands of spectral data into a
small quantity of principal components and described the body of spectra the scores of the first 6 principal components
computed by PCA had been applied as inputs to a back propagation neural network with one hidden layer. 125 samples
of five varieties were selected randomly, which were used to build BP-ANN model. This model had been used to predict
the varieties of 25 unknown samples; the residual error for the calibration samples is 1.267 x 10-4. The recognition rate of
100% was achieved. This model is reliable and practicable. So this paper put forward a new method to the fast
discrimination of varieties of tea.
In this research, the potential of using the Visible/Near Infrared Spectroscopy (Vis/NIRS) was investigated for measuring
the acidity of Chinese bayberry (Myrica rubra Sieb.et Zucc. ), and the relationship is established between nondestructive
Vis/NIR spectral measurement and the major physiological property of Chinese bayberry. Intact Chinese bayberry fruit
were measured by reflectance Vis/NIR in 325-1075 nm range. The data set as the logarithms of the reflectance
reciprocal (absorbance (loglIR)) was analyzed in order to build the best calibration model for this characteristic, using
some spectral pretreatments and multivariate calibration techniques such as partial least square regression (PLS). The
models for the pH (r=0.963), standard error ofprediction (SEP) 0.21 with a bias of 0.138; shown the excellent prediction
performance. The Vis/NIR spectroscopy technique had significantly greater accuracy for determining the pH. It was
concluded that the Vis/NIRS measurement technique seems reliable to assess the quality attribute of Chinese bayberry
nondestructively.
A fast measurement of pH of yogurt using Vis/NIR-spectroscopy techniques was established in order to measuring the
acidity of yogurt rapidly. 27 samples selected separately from five different brands of yogurt were measured by
Vis/NIR-spectroscopy. The pH of yogurt on positions scanned by spectrum was measured by a pH meter. The
mathematical model between pH and Vis/NIR spectral measurements was established and developed based on partial
least squares (PLS) by using Unscramble V9.2. Then 25 unknown samples from 5 different brands were predicted based
on the mathematical model. The result shows that The correlation coefficient of pH based on PLS model is more than
0.890, and standard error of calibration (SEC) is 0.037, standard error of prediction (SEP) is 0.043. Through predicting
the pH of 25 samples of yogurt from 5 different brands, the correlation coefficient between predictive value and
measured value of those samples is more than 0918. The results show the good to excellent prediction performances.
The Vis/NIR spectroscopy technique had a significant greater accuracy for determining the value of pH. It was
concluded that the VisINIRS measurement technique can be used to measure pH of yogurt fast and accurately, and a new
method for the measurement of pH of yogurt was established.
A new approach for discrimination of varieties of yogurt by means of VisINTR-spectroscopy was present in this paper.
Firstly, through the principal component analysis (PCA) of spectroscopy curves of 5 typical kinds of yogurt, the
clustering of yogurt varieties was processed. The analysis results showed that the cumulate reliabilities of PC1 and PC2
(the first two principle components) were more than 98.956%, and the cumulate reliabilities from PC1 to PC7 (the first
seven principle components) was 99.97%. Secondly, a discrimination model of Artificial Neural Network (ANN-BP) was
set up. The first seven principles components of the samples were applied as ANN-BP inputs, and the value of type of
yogurt were applied as outputs, then the three-layer ANN-BP model was build. In this model, every variety yogurt
includes 27 samples, the total number of sample is 135, and the rest 25 samples were used as prediction set. The results
showed the distinguishing rate of the five yogurt varieties was 100%. It presented that this model was reliable and
practicable. So a new approach for the rapid and lossless discrimination of varieties of yogurt was put forward.
This research is to use spectroscopy data to determine the producing area of sampled waxberries. which are very similar
in sizes and textures and color. and also very similar in taste. So, it is hard to tell where is the producing area of the given
waxberry. In this research, 30 samples were chosen from each of the 4 kinds of waxberries. The producing areas are
XianJu CiXi Nmghai and Lishui all in Zhejiang province. Firstly, spectroscopy were taken down by ASD FieldSpec
(Handheld type, its spectrum is between 325-1075nm resolution is 3.5nm), and then its acidity measured by PH meter
and sugar content by saccharin-meter. The following data process shows that the spectroscopy can record the whole
information of one sample. By using wavelet transform and PCA analysis. the sampled waxberry producing area were
recognized with higher correction than using the two chemical indices. acidity and sugar content index. In the 30
samples. 100 were used to build model, and let other 20 to forecast. less than 3 samples were forecasted wrongly. The
PCA statistics told us that the relativity between the acidity and sugar index vector to the PCA vector extracted from the
spectroscopy is greater than 0.84. Due to the large standard variance in one sampled set. the using of chemical indices to
classify is not satisfying. This research demonstrates that the different producing areas of waxberry have evident differences in spectroscopy, though it is hard to tell them out by using hand or mouth.
KEYWORDS: Principal component analysis, Near infrared spectroscopy, Reflectivity, Statistical modeling, Data modeling, Near infrared, Analytical research, Spectroscopy, Neurons, Neural networks
A new method for discrimination of varieties of Chinese bayberry by means of infrared spectroscopy (NIRS) (325-1075nm) was developed. A relation has been established between the reflectance spectra and Chinese bayberry varieties.
The dataset consist of a total of 69 samples of Chinese bayberry. First, the data was analyzed with principal component
analysis. It appeared to provide the best clustering of the varieties of Chinese bayberry. PCA compressed thousands of
spectral data into a small quantity of principal components and described the body of spectra; the scores of the first 20
principal components computed by PCA had been applied as inputs to a back propagation neural network with one hidden
layer. 69 samples contained three varieties were selected randomly, then they were used to build BP-ANN model.
This model had been used to predict the varieties of 15 unknown samples; the residual error for the calibration samples
is 1.508458 x 10-6. The recognition rate of 100% was achieved. The result achieved by using PCA-BP method is much
better than the results achieved by only using the PCA method. This model is reliable and practicable. So this paper
could offer a new approach to the fast discrimination ofvarieties of Chinese bayberry.
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.