Identification of Tea Varieties Using Computer Vision

Chen, Q.; Zhao, Junxuan; Cai, Jun

doi:10.13031/2013.24363

Cited by 43 publications

(30 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For humans, caffeine has many important physiological effects, such as stimulation of the central nervous system, diuresis and gastric acid secretion (Rostagno et al, 2011). However, high amounts of caffeine can cause trembling, nausea, nervousness and seizures and mutation effects such as inhibition of DNA (Chen et al, 2008). A fatal dose of caffeine has been evaluated to be more than 10 g (about 170 mg kg -1 of body weight).…”

Section: Introductionmentioning

confidence: 99%

Utilization of electrochemical methods in determination of trace elements in beverages

Svítková¹,

Machková²,

Šatkovská³

et al. 2012

Acta Chimica Slovaca

View full text Add to dashboard Cite

Electrochemical methods have many inherent advantages such as simplicity, low cost and amenability to miniaturization. A new, sensitive and selective electrochemical method for the caffeine determination using boron doped diamond electrode was developed. It was found by cyclic voltammetry that caffeine provided highly reproducible and well-defi ned irreversible oxidation peak, at very positive potential of +1.55 V vs. Ag/AgCl electrode. The effect of pH and scan rate on the voltammetric response of caffeine oxidation were studied to select the optimum experimental conditions. Linear response of peak current on the concentration in the range from 4 × 10 -7 to 2.5 × 10 -5 mol L -1, good repeatability (RSD of 2.1 %) and the detection limit of 1.5 × 10 -7 mol L -1 without any chemical modifi cations and electrochemical surface pretreatment were observed by differential pulse voltammetry in 0.4 mol L -1 perchloric acid. The effect of possible interfering compounds appeared to be negligible which evidently proved very good selectivity. The proposed method was successfully applied for the caffeine determination in commercially available beverage samples, with results in a close statistical agreement to these declared by manufacturer.

show abstract

Section: Introductionmentioning

confidence: 99%

Utilization of electrochemical methods in determination of trace elements in beverages

Svítková¹,

Machková²,

Šatkovská³

et al. 2012

Acta Chimica Slovaca

View full text Add to dashboard Cite

show abstract

“…LDA is focused on finding optimal boundaries between classes. Here, a brief introduction of LDA is presented in this paper, and readers can refer to other literature (Yang et al 2005;Chen et al 2008). The number of principal component factors (PCs) is crucial for the performance of the LDA identification model, and identification rates in training and prediction sets were used as criteria to optimise the number of PCs.…”

Section: Identification Results Of Lda Modelmentioning

confidence: 99%

Nondestructive identification of tea (Camellia sinensis L.) varieties using FT-NIR spectroscopy and pattern recognition

Chen¹,

Zhao²,

MuHua³

et al. 2008

Czech J. Food Sci.

View full text Add to dashboard Cite

Chen Q., Zhao J., Liu M., Cai J. (2008): Nondestructive identification of tea (Camellia sinensis L.) varieties using FT-NIR spectroscopy and pattern recognition. Czech J. Food Sci., 26: 360-367.Due to more and more tea varieties in the current tea market, rapid and accurate identification of tea (Camellia sinensis L.) varieties is crucial to the tea quality control. Fourier Transform Near-Infrared (FT-NIR) spectroscopy coupled with the pattern recognition was used to identify individual tea varieties as a rapid and non-invasive analytical tool in this work. Seven varieties of Chinese tea were studied in the experiment. Linear Discriminant Analysis (LDA) and Artificial Neural Network (ANN) were compared to construct the identification models based on Principal Component Analysis (PCA). The number of principal components factors (PCs) was optimised in the constructing model. The experimental results showed that the performance of ANN model was better than LDA models. The optimal ANN model was achieved when four PCs were used, identification rates being all 100% in the training and prediction sets. The overall results demonstrated that FT-NIR spectroscopy technology with ANN pattern recognition method can be successfully applied as a rapid method to identify tea varieties.

show abstract

“…We compared the best feature (64 CH and 25 FRFE, then reduced to four PCs) and the best classifier (Jaya-FNN), with seven state-of-the-art approaches (SVM [15], BPNN [16], LDA [21], GNN [22], FSCABC-FNN [25], SVM + WTA [28], and FSVM + WTA [28]), on the basis of ASR of 10ˆ10-fold SCV, which were used in reference [25,28]. Table 7 shows the comparison results.…”

Section: Comparison To State-of-the-art Approachesmentioning

confidence: 99%

“…The issues in modeling TCI systems require the development of novel computational tools. For instance, Chen et al [21] employed 12 color features and 12 texture features. Then, they employed principal component analysis (PCA) and linear discriminant analysis (LDA) to generate the classification system.…”

Section: Introductionmentioning

confidence: 99%

Tea Category Identification Using a Novel Fractional Fourier Entropy and Jaya Algorithm

Zhang

Yang

Cattani

et al. 2016

Entropy

View full text Add to dashboard Cite

This work proposes a tea-category identification (TCI) system, which can automatically determine tea category from images captured by a 3 charge-coupled device (CCD) digital camera. Three-hundred tea images were acquired as the dataset. Apart from the 64 traditional color histogram features that were extracted, we also introduced a relatively new feature as fractional Fourier entropy (FRFE) and extracted 25 FRFE features from each tea image. Furthermore, the kernel principal component analysis (KPCA) was harnessed to reduce 64 + 25 = 89 features. The four reduced features were fed into a feedforward neural network (FNN). Its optimal weights were obtained by Jaya algorithm. The 10ˆ10-fold stratified cross-validation (SCV) showed that our TCI system obtains an overall average sensitivity rate of 97.9%, which was higher than seven existing approaches. In addition, we used only four features less than or equal to state-of-the-art approaches. Our proposed system is efficient in terms of tea-category identification.

show abstract

Identification of Tea Varieties Using Computer Vision

Cited by 43 publications

References 0 publications

Utilization of electrochemical methods in determination of trace elements in beverages

Utilization of electrochemical methods in determination of trace elements in beverages

Nondestructive identification of tea (Camellia sinensis L.) varieties using FT-NIR spectroscopy and pattern recognition

Tea Category Identification Using a Novel Fractional Fourier Entropy and Jaya Algorithm

Contact Info

Product

Resources

About