Interactive reconstruction of industrial sites using parametric models
Proceedings of the 26th Spring Conference on Computer Graphics
A method for text localization and recognition in real-world images
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part III
Ellipse constraints for improved wide-baseline feature matching and reconstruction
IWCIA'11 Proceedings of the 14th international conference on Combinatorial image analysis
Mutual information refinement for flash-no-flash image alignment
ACIVS'11 Proceedings of the 13th international conference on Advanced concepts for intelligent vision systems
Color-based extensions to MSERs
ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part II
Content based image retrieval with LIRe
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Dynamic hand gesture recognition: An exemplar-based approach from motion divergence fields
Image and Vision Computing
A head-mounted device for recognizing text in natural scenes
CBDAR'11 Proceedings of the 4th international conference on Camera-Based Document Analysis and Recognition
Finger and hand detection for multi-touch interfaces based on maximally stable extremal regions
Proceedings of the 2012 ACM international conference on Interactive tabletops and surfaces
Hierarchical feature grouping for multiple object segmentation and tracking
Proceedings of the 27th Conference on Image and Vision Computing New Zealand
Context-aware features and robust image representations
Journal of Visual Communication and Image Representation
Hi-index | 0.02 |
In this paper we present a new algorithm for computing Maximally Stable Extremal Regions (MSER), as invented by Matas et al. The standard algorithm makes use of a union-find data structure and takes quasi-linear time in the number of pixels. The new algorithm provides exactly identical results in true worst-case linear time. Moreover, the new algorithm uses significantly less memory and has better cache-locality, resulting in faster execution. Our CPU implementation performs twice as fast as a state-of-the-art FPGA implementation based on the standard algorithm.The new algorithm is based on a different computational ordering of the pixels, which is suggested by another immersion analogy than the one corresponding to the standard connected-component algorithm. With the new computational ordering, the pixels considered or visited at any point during computation consist of a single connected component of pixels in the image, resembling a flood-fill that adapts to the grey-level landscape. The computation only needs a priority queue of candidate pixels (the boundary of the single connected component), a single bit image masking visited pixels, and information for as many components as there are grey-levels in the image. This is substantially more compact in practice than the standard algorithm, where a large number of connected components must be considered in parallel. The new algorithm can also generate the component tree of the image in true linear time. The result shows that MSER detection is not tied to the union-find data structure, which may open more possibilities for parallelization.