Exploiting intensity inhomogeneity to extract textured objects from natural scenes

• Main Authors: DING, Jundi, SHEN, Jialie, PANG, Hwee Hwa, CHEN, Songcan, YANG, Jingyu
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2010
• Subjects: Cue integration; Intensity inhomogeneity; Intrinsic randomness; Natural images; Natural scenes; Natural textures; Salient regions; Seeded region; Statistical properties; Textured objects; Textured regions; Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/3866; https://ink.library.smu.edu.sg/context/sis_research/article/4868/viewcontent/ExploitingIntensityInhomogeneity_2009.pdf
• Institution: Singapore Management University

Extracting textured objects from natural scenes is a challenging task in computer vision. The main difficulties arise from the intrinsic randomness of natural textures and the high-semblance between the objects and the background. In this paper, we approach the extraction problem with a seeded regio...