[vc_empty_space][vc_empty_space]
Multi patch approach in K-means clustering method for color image segmentation in pulmonary tuberculosis identification
Rulaningtyas R.a,b, Suksmono A.B.a, Mengko T.a, Saptawati P.a
a Department of Electrical Engineering, Bandung Institute of Technology, Bandung, Indonesia
b Department of Physics, Airlangga University, Surabaya, 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]© 2015 IEEE.Ziehl-Neelsen staining in sputum smear slides of pulmonary tuberculosis disease causes the sputum images become complex. The clinicians feel hard to examine sputum slide manually because there is no staining standardization. For helping the clinicians, this research developed new algorithm which did segmentation to separate the tuberculosis bacteria images from the background images. So that, the tuberculosis bacteria appear well. Several methods have been performed in this research. There were adaptive color thresholding, K-means clustering and K-nearest neighbors to improve the performance of color segmentation. All processing were done in the Commission Internationale de l’Eclairage Lab (CIELAB) color space. K-nearest neighbors method gave the best accuracy 97.90%, but has not been able to give good result on the whole image and need long computational time in learning process. Therefore, this research modified K-means clustering using patch technique for color image segmentation in the image of pulmonary tuberculosis sputum. The weakness of local optima in the K-means clustering repaired with a patch technique, as well as the learning process to get the patch pattern which is used as a reference to the new data. This method gave good segmentation accuracy 97.68% and fast computational 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=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Adaptive thresholding,Color image segmentation,K-means clustering,K-means clustering method,K-nearest neighbors,K-nearest neighbors method,Modified k-means clustering,patch[/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]adaptive thresholding,K-means clustering,K-nearest neighbors,patch,segmentation[/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/ICICI-BME.2015.7401338[/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]