Abstract
Research on textural segmentation is reviewed and a model is presented. The model assumes that textural segmentation occurs as a result of differences in the first-order statistics of local features of textural elements rather than as a result of differences in the global second-order statistics of image points. Experiments are reported which conflict with the original Julesz conjecture that textural segmentation is a function of differences in global second-order statistics. The results support the hypothesis that textural segmentation depends on differences in the local features of textural elements. The results also support the hypothesis that the grouping of features into textural elements can affect textural segmentation by modifying the salience of existing feature differences and by introducing new feature differences.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.