Improving Accuracy for Image Parsing Using Spatial Context and Mutual Information
| Autor: | Sun-Wook Choi, Thi Ly Vu, Chong Ho Lee |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
Spatial contextual awareness
Markov random field Computer science business.industry Nonparametric statistics Inference Pattern recognition Mutual information Object (computer science) computer.software_genre k-nearest neighbors algorithm Computer Science::Computer Vision and Pattern Recognition Image parsing Artificial intelligence Data mining business computer |
| Zdroj: | Neural Information Processing ISBN: 9783642420504 ICONIP (3) |
| DOI: | 10.1007/978-3-642-42051-1_23 |
| Popis: | This paper presents a novel approach for image parsing based on nonparametric model in superpixel level. Spatial context and mutual information between object co-occurrence are introduced and applied for improving the accuracy of image parsing. These methods make the probability of object co-occurrence more reliable, and thus the inference of object label from K nearest neighbors is more accurate. Our system integrates the probability of object co-occurrence with the spatial context and mutual information into a Markov Random Field(MRF) framework. Experimental results on SIFTFlow and Barcelona dataset shows that the spatial context and the mutual information are promising methods to improve the accuracy of nonparametric image parsing models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|