Image interpretation using contextual feedback

Author

Lai, George C. ; de Figueiredo, Rui J.P.

Author_Institution

Lab. for Machine Intelligence, Vision, & Neural Comput., California Univ., Irvine, CA, USA

Volume

2

fYear

1995

fDate

23-26 Oct 1995

Firstpage

623

Abstract

We present a methodology for scene analysis using contextual feedback and demonstrate the approach in a simple example. In our approach, we combine bottom-up and top-down decision making into a systematic mechanism. From feedback of high-level descriptions, the system iteratively arrives at improved identification. The implementation uses OINNs (optimal interpolative neural networks) to determine plausibility and enforce constraints in label assignments. The proposed method can be extended for the analysis of more complex scenes

Keywords

decision theory; feedback; image segmentation; interpolation; iterative methods; neural nets; OINN; bottom-up decision making; contextual feedback; feedback; high-level description; identification; image interpretation; label assignments; optimal interpolative neural networks; plausibility; scene analysis; top-down decision making; Feedback; Image analysis; Image segmentation; Labeling; Laboratories; Layout; Machine intelligence; Neural networks; Neurofeedback; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1995. Proceedings., International Conference on

Conference_Location

Washington, DC

Print_ISBN

0-8186-7310-9

Type

conf

DOI

10.1109/ICIP.1995.537556

Filename

537556