TY - JOUR
T1 - Linear criterion to sort color components in images
AU - Barriga-Rodríguez, Leonardo
AU - Jiménez-Hernández, Hugo
AU - Soto-Cajiga, Alberto
AU - Nava-Balanzar, Luciano
AU - González-Barbosa, José Joel
AU - Gómez-Espinosa, Alfonso
AU - Pedraza-Ortega, Carlos
N1 - Publisher Copyright:
© 2017, Revista Ingenieria e Investigacion - Editorial Board. All rights reserved.
PY - 2017
Y1 - 2017
N2 - The color and its representation play a basic role in Image Analysis process. Several methods can be beneficial whenever they have a correct representation of wave-length variations used to represent scenes with a camera. A wide variety of spaces and color representations is founded in specialized literature. Each one is useful in concrete circumstances and others may offer redundant color information (for instance, all RGB components are high correlated). This work deals with the task of identifying and sorting which component from several color representations offers the majority of information about the scene. This approach is based on analyzing linear dependences among each color component, by the implementation of a new sorting algorithm based on entropy. The proposal is tested in several outdoor/indoor scenes with different light conditions. Repeatability and stability are tested in order to guarantee its use in several image analysis applications. Finally, the results of this work have been used to enhance an external algorithm to compensate the camera random vibrations.
AB - The color and its representation play a basic role in Image Analysis process. Several methods can be beneficial whenever they have a correct representation of wave-length variations used to represent scenes with a camera. A wide variety of spaces and color representations is founded in specialized literature. Each one is useful in concrete circumstances and others may offer redundant color information (for instance, all RGB components are high correlated). This work deals with the task of identifying and sorting which component from several color representations offers the majority of information about the scene. This approach is based on analyzing linear dependences among each color component, by the implementation of a new sorting algorithm based on entropy. The proposal is tested in several outdoor/indoor scenes with different light conditions. Repeatability and stability are tested in order to guarantee its use in several image analysis applications. Finally, the results of this work have been used to enhance an external algorithm to compensate the camera random vibrations.
KW - Camera vibrations
KW - Color analysis
KW - Color sorting
KW - Linear sorting criterion
UR - http://www.scopus.com/inward/record.url?scp=85018671628&partnerID=8YFLogxK
U2 - 10.15446/ing.investig.v37n1.55444
DO - 10.15446/ing.investig.v37n1.55444
M3 - Artículo
SN - 0120-5609
VL - 37
SP - 91
EP - 98
JO - Ingenieria e Investigacion
JF - Ingenieria e Investigacion
IS - 1
ER -