Efficient Graph-Based Image Segmentation
Citations
7,849 citations
Cites background or methods from "Efficient Graph-Based Image Segment..."
...Felzenszwalb and Huttenlocher [8] propose an alter- native graph-based approach that has been applied to generate superpixels....
[...]
...We therefore performed an empirical comparison of five stateof-the-art superpixel methods [8], [23], [26], [25], [15], evaluating their speed, ability to adhere to image boundaries, and impact on segmentation performance....
[...]
...Felzenszwalb and Huttenlocher [8] propose an alter-...
[...]
...Like some other superpixel algorithms [8], SLIC does not explicitly...
[...]
...For example, if adherence to image boundaries is of paramount importance, the graph-based method of [8] may be an ideal choice....
[...]
5,843 citations
5,742 citations
Cites methods from "Efficient Graph-Based Image Segment..."
...We also experimented with the Felzenszwalb and Huttenlocher [24] algorithm but found that Mori’s method, while more computationally expensive, did a much better job at preserving the face-background boundary, a crucial property for superpixel-based segmentation....
[...]
5,068 citations
3,653 citations
Cites methods from "Efficient Graph-Based Image Segment..."
...We first segment the input image into regions using a graphbased image segmentation method [11]....
[...]
...Image regions generated by Felzenszwalb and Huttenlocher’s segmentation method [11] (left), region contrast based segmentation with (left-middle) and without (right-middle) distance weighting....
[...]
...In contrast, our RC variant is slower as it requires image segmentation [11], but produces superior quality saliency maps....
[...]
References
21,651 citations
11,827 citations
"Efficient Graph-Based Image Segment..." refers background or methods in this paper
...The work reported here and the normalized cuts approach (Shi and Malik, 1997) are just a few illustrations of these recent advances....
[...]
...This bias was addressed with the normalized cut criterion developed by Shi and Malik (1997), which takes into account self-similarity of regions....
[...]
...…techniques (e.g., Cooper, 1998; Pavlidas, 1977), techniques based on mapping image pixels to some feature space (e.g., Comaniciu and Meer, 1997, 1999) and more recent formulations in terms of graph cuts (e.g., Shi and Malik, 1997; Wu and Leahy, 1993) and spectral methods (e.g., Weiss, 1999)....
[...]
...3 shows two baseball players (from Shi and Malik, 1997)....
[...]
...While the past few years have seen considerable progress in eigenvector-based methods of image segmentation (e.g., Shi and Malik, 1997; Weiss, 1999), these methods are too slow to be practical for many applications....
[...]
9,439 citations
"Efficient Graph-Based Image Segment..." refers background in this paper
...There is a large literature on segmentation and clustering, dating back over 30 years, with applications in many areas other than computer vision (cf. Jain and Dubes, 1988)....
[...]
...One common approach to image segmentation is based on mapping each pixel to a point in some feature space, and then finding clusters of similar points (e.g., Comaniciu and Meer, 1997, 1999; Jain and Dubes, 1988)....
[...]
...A number of approaches to segmentation are based on finding compact clusters in some feature space (cf. Comaniciu and Meer, 1997; Jain and Dubes, 1988)....
[...]
1,832 citations
"Efficient Graph-Based Image Segment..." refers methods in this paper
...In this section we briefly consider some of the related work that is most relevant to our approach: early graph-based methods (e.g., Urquhart, 1982; Zahn, 1971), region merging techniques (e.g., Cooper, 1998; Pavlidas, 1977), techniques based on mapping image pixels to some feature space (e.g.,…...
[...]
...The work of Zahn (1971) presents a segmentation method based on the minimum spanning tree (MST) of the graph....
[...]
...In this section we briefly consider some of the related work that is most relevant to our approach: early graph-based methods (e.g., Urquhart, 1982; Zahn, 1971), region merging techniques (e....
[...]
...As with certain classical clustering methods (Urquhart, 1982; Zahn, 1971), our method is based on selecting edges from a graph, where each pixel corresponds to a node in the graph, and certain neighboring pixels are connected by undirected edges....
[...]
...As in other graph-based approaches to image segmentation (e.g., Shi and Malik, 1997; Wu and Leahy, 1993; Zahn, 1971) we define an undirected graph G = (V, E), where each image pixel pi has a corresponding vertex vi ∈ V ....
[...]