Image interpretation using contextual feedback
ICIP（1995）
摘要
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.
更多查看译文
关键词
optimal interpolative neural network,high-level description,image interpretation,complex scene,contextual feedback,system iteratively,simple example,improved identification,label assignment,scene analysis,decision theory,top down,iterative methods,neural networks,identification,layout,machine intelligence,bottom up,image analysis,labeling,neural network,feedback,interpolation,shape,neurofeedback,image segmentation,neural nets
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要