[vc_empty_space][vc_empty_space]
Compact computer vision for black tea quality evaluation based on the black tea particles
Suprijantoa, Rakhmawati A.b, Yuliastuti E.a
a Intrumentation and Control Research Group, Faculty of Industrial Technology, Bandung Institute of Technology, Indonesia
b Organoleptic and Microbiology Laboratory, Centre for Quality Control of Goods, Ministry of Trade, Indonesia
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]The quality of tea determines its market value. In Indonesia, the black tea standard quality evaluation refers to Indonesian National Standard (SNI) of black tea 01-1902-1995. At present, organoleptic evaluation as visual and aroma inspection by trained evaluator, chemical instrument as gas chromatography and colorimetric evaluation, are being used as the tea quality evaluation. However, this method relatively takes more time and energy, more expensive and sometimes inaccurate. This research was intended to develop compact computer vision prototype for CTC grade BP1 black tea quality. In image acquisition process, standard box with illuminator and digital microscope with 5x magnification were used to capture the detail of tea particles. Which in each sequence of evaluation, 2,84 gram particles approximately consists of 1000 granular particles was used. Morphology operation was applied to label each particle in which the parameter of area(A), perimeter(T) and bending energy(E) were determined. Furthermore, the particles’ color information was extracted by use of image color histogram on red(R) and blue(B) channels. Feature sets are consist of T/A, E, R and B parameter values, each parameter value was represented in a certain interval of histogram and uniformly applied in all feature set. These feature sets were used as an input of artificial neural network(ANN) with architecture of multilayer perceptron and 226 input elements within. 30 data sets of tea particles with A, B and C qualities were used as training data with algorithm of backpropagation. The ANN was validated by use of 30 datasets (A, B, C qualities) apart from the training data. The validation process yielded 100% result in recognizing the tea particles qualities which matched the organoleptic method. © 2011 IEEE.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Acquisition process,Artificial Neural Network,B-parameter,Bending energies,Black tea,Chemical instruments,Color information,Data sets,Digital microscopes,Feature sets,geometry feature,Granular particles,Image color,Indonesia,Market values,Morphology operations,multilayer perceptron,National standard,Organoleptic evaluation,Parameter values,Quality evaluation,Training data,Validation process[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]artificial neural networks,Black tea,color,component; backpropagation,computer vision,geometry feature,morphology,multilayer perceptron[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1109/ICA.2011.6130135[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]