TY - GEN
T1 - A comparative study of the use of a robust color image segmentation method
AU - Alvarado-Cervantes, Rodolfo
AU - Felipe-Riverón, Edgardo M.
AU - Khartchenko, Vladislav
AU - Pogrebnyak, Oleksiy
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016
Y1 - 2016
N2 - In this paper, a comparative study of some basic close related color image segmentation methods is presented. It is focused in the evaluation of two segmentation methods based on a recently published adaptive color similarity function making use of: 1) pixel samples of both figure and background and classifying by maximum similarity, and 2) pixel samples of only figure and classifying by automatic thresholding thus employing only half of input information. It is also presented for comparison, the results of classification using the Euclidean metric of a* and b* channels rejecting L* in the L*a*b* color space and with the Euclidian metric of the R, G, and B channels in the RGB color space. From the results it was obtained that the segmentation technique using the adaptive color similarity function and classifying by automatic thresholding (employing only half of the information supplied to the other methods) had better performance than those implemented in the L*a*b* and RGB color spaces in all cases of study. The performance is equivalent to that using pixel sample of both figure and background and classifying by maximum similarity. The improvement in quality of the segmentation techniques using the color similarity function is substantially significant.
AB - In this paper, a comparative study of some basic close related color image segmentation methods is presented. It is focused in the evaluation of two segmentation methods based on a recently published adaptive color similarity function making use of: 1) pixel samples of both figure and background and classifying by maximum similarity, and 2) pixel samples of only figure and classifying by automatic thresholding thus employing only half of input information. It is also presented for comparison, the results of classification using the Euclidean metric of a* and b* channels rejecting L* in the L*a*b* color space and with the Euclidian metric of the R, G, and B channels in the RGB color space. From the results it was obtained that the segmentation technique using the adaptive color similarity function and classifying by automatic thresholding (employing only half of the information supplied to the other methods) had better performance than those implemented in the L*a*b* and RGB color spaces in all cases of study. The performance is equivalent to that using pixel sample of both figure and background and classifying by maximum similarity. The improvement in quality of the segmentation techniques using the color similarity function is substantially significant.
KW - CIELAB Lab color space
KW - Color image segmentation
KW - Color metrics
KW - Color segmentation evaluation
KW - Synthetic color image generation
UR - http://www.scopus.com/inward/record.url?scp=85117856692&partnerID=8YFLogxK
U2 - 10.1109/MICAI-2016.2016.00015
DO - 10.1109/MICAI-2016.2016.00015
M3 - Contribución a la conferencia
AN - SCOPUS:85117856692
T3 - Proceedings of a Special Session - 15th Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence, MICAI 2016
SP - 41
EP - 48
BT - Proceedings of a Special Session - 15th Mexican International Conference on Artificial Intelligence
A2 - Sidorov, Grigori
A2 - Alcantara, Oscar Herrera
A2 - Jimenez, Sabino Miranda
A2 - Lagunas, Obdulia Pichardo
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th Mexican International Conference on Artificial Intelligence, MICAI 2016
Y2 - 23 October 2016 through 29 October 2016
ER -