Abstract | ||
---|---|---|
This paper considers the problem of automatically segmenting an image into a small number of regions that correspond to objects conveying semantics or high-level structure. Although such object-level segmentation usually requires additional high-level knowledge or learning process, we explore what low level cues can produce for this purpose. Our idea is to construct a feature vector for each pixel, which elaborately integrates spectral attributes, color Gaussian mixture models, and geodesic distance, such that it encodes global color and spatial cues as well as global structure information. Then, we formulate the Potts variational model in terms of the feature vectors to provide a variational image segmentation algorithm that is performed in the feature space. We also propose a heuristic approach to automatically select the number of segments. The use of feature attributes enables the Potts model to produce regions that are coherent in color and position, comply with global structures corresponding to objects or parts of objects and meanwhile maintain a smooth and accurate boundary. We demonstrate the effectiveness of our algorithm against the state-of-the-art with the data set from the famous Berkeley benchmark. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/TIP.2013.2268973 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
gaussian processes,feature vector,global structures,global structure information,high-level structure,objects conveying semantics,berkeley benchmark,geodesic distance,image segmentation,high-level knowledge,heuristic approach,low level cue,object segmentation,low level cues,image reconstruction,object recognition,color gaussian mixture model,variational model,learning process,object-level image segmentation,potts model,potts variational model,image colour analysis | Computer vision,Feature vector,Scale-space segmentation,Feature detection (computer vision),Pattern recognition,Image texture,Segmentation,Range segmentation,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Mathematics | Journal |
Volume | Issue | ISSN |
22 | 10 | 1941-0042 |
Citations | PageRank | References |
2 | 0.35 | 21 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hongyuan Zhu | 1 | 109 | 16.59 |
jianmin zheng | 2 | 1024 | 99.03 |
jianfei cai | 3 | 1804 | 147.18 |
Nadia Magnenat-Thalmann | 4 | 5119 | 659.15 |