Joint object discovery and segmentation with image-wise reconstruction error
| Autor: | Takayuki Kurozumi, Go Irie, Shuhei Tarashima, Tetsuya Kinebuchi, Jingjing Pan |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Noise measurement
Computer science Segmentation-based object categorization business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Scale-space segmentation Pattern recognition 02 engineering and technology Iterative reconstruction Image segmentation 010501 environmental sciences 01 natural sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Computer vision Noise (video) Artificial intelligence business Image restoration 0105 earth and related environmental sciences |
| Zdroj: | ICIP |
| DOI: | 10.1109/icip.2016.7532477 |
| Popis: | We tackle the problem of joint discovery and segmentation of the object of interest from noisy image sets collected via web crawling (e.g., Figure 1). Existing methods [1] [2] [3] employ region-wise comparison in order to separate noise images (images not containing target objects) from the rest, which may be a bottleneck for scaling up to larger datasets. Our idea to avoid such computationally intensive operations is to use image-wise reconstruction errors. Specifically, based on the assumption that images containing target objects are easier to be reconstructed by a pool of target objects than noise images, we first reconstruct each image using a small number of similar target objects. The resulting error is then combined with some other criteria (e.g., saliency) so as to delineate only target object regions. Experimental evaluations on a noisy image dataset [1] demonstrate that our approach achieves state-of-the-art results on every subset of the dataset 5–7 times faster than existing methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|