A probabilistic patch based image representation using Conditional Random Field model for image classification
This work addresses texture classification, face recognition, and scene classification problems, but it appears incremental as it builds on existing patch-based and CRF techniques.
The paper tackles image classification by encoding local properties and spatial relationships using a Conditional Random Field model on ordered patches, achieving improved performance over existing methods on standard datasets.
In this paper we proposed an ordered patch based method using Conditional Random Field (CRF) in order to encode local properties and their spatial relationship in images to address texture classification, face recognition, and scene classification problems. Typical image classification approaches work without considering spatial causality among distinctive properties of an image for image representation in feature space. In this method first, each image is encoded as a sequence of ordered patches, including local properties. Second, the sequence of these ordered patches is modeled as a probabilistic feature vector by CRF to model spatial relationship of these local properties. And finally, image classification is performed on such probabilistic image representation. Experimental results on several standard image datasets indicate that proposed method outperforms some of existing image classification methods.