How Do Superpixels Affect Image Segmentation?
نویسنده
چکیده
Computationally intensive segmentation algorithms often operate on an image pre-segmented into small regions referred to as “superpixels”. We investigate the effect of the choice of the pre-segmentation algorithm and its parameters on the outcome of the final segmentation. Three pre-segmentation algorithms are compared. To avoid the particularities of sophisticated segmentation algorithms, the final segmentations are built using agglomerative hierarchical clustering. These segmentations are evaluated using 300 images from the Berkeley Segmentation Dataset. This leads to useful insights about the variations in the final segmentation caused by the choice of the pre-segmentation algorithm.
منابع مشابه
Adaptive strategy for superpixel-based region-growing image segmentation
This work presents a region-growing image segmentation approach based on superpixel decomposition. From an initial contour-constrained over-segmentation of the input image, the image segmentation is achieved by iteratively merging similar superpixels into regions. This approach raises two key issues: (1) how to compute the similarity between superpixels in order to perform accurate merging and ...
متن کاملMulti-layer graph constraints for interactive image segmentation via game theory
The combination of pixels and superpixels has been widely used for image segmentation, where the pixels and superpixels are segmented together. These combination methods can obtain more robust results by using more informative superpixel features. However, since the superpixel may not accurately capture the details for the small and slender regions, the results of these combination methods are ...
متن کاملSegmentation Improvement of High Resolution Remote Sensing Images based on superpixels using Edge-based SLIC algorithm (E-SLIC)
The segmentation of high resolution remote sensing images is one of the most important analyses that play a significant role in the maximal and exact extraction of information. There are different types of segmentation methods among which using superpixels is one of the most important ones. Several methods have been proposed for extracting superpixels. Among the most successful ones, we can r...
متن کاملImage Segmentation as a Classification task
We implement two-class classification model for image segmentation. This project draws loosely on [1]. In a preprocessing stage an image is oversegmented into superpixels by normalized cut algorithm. For a segment as a mergence of superpixels, we define two features based on similarity in brightness. We train a logistic regression classifier to combine these features. As a ground truth segmenta...
متن کاملImproved Image Boundaries for Better Video Segmentation
Graph-based video segmentation methods rely on superpixels as starting point. While most previous work has focused on the construction of the graph edges and weights as well as solving the graph partitioning problem, this paper focuses on better superpixels for video segmentation. We demonstrate by a comparative analysis that superpixels extracted from boundaries perform best, and show that bou...
متن کامل