TY - GEN
T1 - Color texture histograms for natural images interpretation
AU - Aviña-Cervantes, J. Gabriel
AU - Ledezma-Orozco, Sergio
AU - Torres-Cisneros, Miguel
AU - Hernández-Fusilier, Donato
AU - González-Barbosa, Joel
AU - Salazar-Garibay, Adan
PY - 2007
Y1 - 2007
N2 - This paper presents a recognition method for natural images based on color texture histograms in the context of image interpretation and scene modeling. A color histogram of sums and differences is proposed to obtain texture features which are faster to compute than correlograms ( i.e., colored version of co-occurrence matrices) and improving substantially object recognition. Outdoor natural images are generally affected by color casting artifacts which can affect object recognition. Therefore, an on-line color balancing algorithm based on chromatic adaptation models, eliminates these color deviations. The proposed approach globally involves functions as color segmentation, histogram texture analysis and a region recognition step. Our approach has been extensively tested and validated to obtain an accurate 2D scene interpretation from natural images. This technique may be used in robot navigation by identifying navigable regions ( e.g., roads or fairly flat surfaces) on natural scenes, scene modeling and image categorization.
AB - This paper presents a recognition method for natural images based on color texture histograms in the context of image interpretation and scene modeling. A color histogram of sums and differences is proposed to obtain texture features which are faster to compute than correlograms ( i.e., colored version of co-occurrence matrices) and improving substantially object recognition. Outdoor natural images are generally affected by color casting artifacts which can affect object recognition. Therefore, an on-line color balancing algorithm based on chromatic adaptation models, eliminates these color deviations. The proposed approach globally involves functions as color segmentation, histogram texture analysis and a region recognition step. Our approach has been extensively tested and validated to obtain an accurate 2D scene interpretation from natural images. This technique may be used in robot navigation by identifying navigable regions ( e.g., roads or fairly flat surfaces) on natural scenes, scene modeling and image categorization.
UR - http://www.scopus.com/inward/record.url?scp=57749195529&partnerID=8YFLogxK
U2 - 10.1109/MICAI.2007.19
DO - 10.1109/MICAI.2007.19
M3 - Contribución a la conferencia
AN - SCOPUS:57749195529
SN - 9780769531243
T3 - Proceedings - 2007 6th Mexican International Conference on Artificial Intelligence, Special Session, MICAI 2007
SP - 131
EP - 140
BT - Proceedings - 2007 6th Mexican International Conference on Artificial Intelligence, Special Session, MICAI 2007
PB - IEEE Computer Society
T2 - 2007 6th Mexican International Conference on Artificial Intelligence, Special Session, MICAI 2007
Y2 - 4 November 2007 through 10 November 2007
ER -