Tampere University of Technology

TUTCRIS Research Portal

Content-Adaptive Superpixel Segmentation Via Image Transformation

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Standard

Content-Adaptive Superpixel Segmentation Via Image Transformation. / Chuchvara, Aleksandra; Gotchev, Atanas.

2019 IEEE International Conference on Image Processing (ICIP). IEEE, 2019. p. 1505-1509 (IEEE International Conference on Image Processing).

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Chuchvara, A & Gotchev, A 2019, Content-Adaptive Superpixel Segmentation Via Image Transformation. in 2019 IEEE International Conference on Image Processing (ICIP). IEEE International Conference on Image Processing, IEEE, pp. 1505-1509, IEEE International Conference on Image Processing, 1/01/00. https://doi.org/10.1109/ICIP.2019.8803058

APA

Chuchvara, A., & Gotchev, A. (2019). Content-Adaptive Superpixel Segmentation Via Image Transformation. In 2019 IEEE International Conference on Image Processing (ICIP) (pp. 1505-1509). (IEEE International Conference on Image Processing). IEEE. https://doi.org/10.1109/ICIP.2019.8803058

Vancouver

Chuchvara A, Gotchev A. Content-Adaptive Superpixel Segmentation Via Image Transformation. In 2019 IEEE International Conference on Image Processing (ICIP). IEEE. 2019. p. 1505-1509. (IEEE International Conference on Image Processing). https://doi.org/10.1109/ICIP.2019.8803058

Author

Chuchvara, Aleksandra ; Gotchev, Atanas. / Content-Adaptive Superpixel Segmentation Via Image Transformation. 2019 IEEE International Conference on Image Processing (ICIP). IEEE, 2019. pp. 1505-1509 (IEEE International Conference on Image Processing).

Bibtex - Download

@inproceedings{a49acf7fc60c4eb0b0d388eb1eb59db5,
title = "Content-Adaptive Superpixel Segmentation Via Image Transformation",
abstract = "We propose simple and efficient method that produces content-adaptive superpixels, i.e. smaller segments in content-dense areas and larger segments in content-sparse areas. Previous adaptive methods distribute superpixels over the image according to image content. In contrast, we transform the image itself to redistribute the content density uniformly across the image area. This transformation is guided by a significance map, which characterizes the ‘importance’ of each pixel. Arbitrary superpixel algorithm can be utilized to segment the transformed image into regular superpixels, providing a suitable representation for subsequent tasks. Regular superpixels in the transformed image induce content-adaptive superpixels in the original image facilitating the improved segmentation accuracy.",
keywords = "Image segmentation, Image edge detection, Optimization, Benchmark testing, Detectors, Measurement, Task analysis, Superpixel, image segmentation",
author = "Aleksandra Chuchvara and Atanas Gotchev",
year = "2019",
month = "9",
doi = "10.1109/ICIP.2019.8803058",
language = "English",
isbn = "978-1-5386-6250-2",
series = "IEEE International Conference on Image Processing",
publisher = "IEEE",
pages = "1505--1509",
booktitle = "2019 IEEE International Conference on Image Processing (ICIP)",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - Content-Adaptive Superpixel Segmentation Via Image Transformation

AU - Chuchvara, Aleksandra

AU - Gotchev, Atanas

PY - 2019/9

Y1 - 2019/9

N2 - We propose simple and efficient method that produces content-adaptive superpixels, i.e. smaller segments in content-dense areas and larger segments in content-sparse areas. Previous adaptive methods distribute superpixels over the image according to image content. In contrast, we transform the image itself to redistribute the content density uniformly across the image area. This transformation is guided by a significance map, which characterizes the ‘importance’ of each pixel. Arbitrary superpixel algorithm can be utilized to segment the transformed image into regular superpixels, providing a suitable representation for subsequent tasks. Regular superpixels in the transformed image induce content-adaptive superpixels in the original image facilitating the improved segmentation accuracy.

AB - We propose simple and efficient method that produces content-adaptive superpixels, i.e. smaller segments in content-dense areas and larger segments in content-sparse areas. Previous adaptive methods distribute superpixels over the image according to image content. In contrast, we transform the image itself to redistribute the content density uniformly across the image area. This transformation is guided by a significance map, which characterizes the ‘importance’ of each pixel. Arbitrary superpixel algorithm can be utilized to segment the transformed image into regular superpixels, providing a suitable representation for subsequent tasks. Regular superpixels in the transformed image induce content-adaptive superpixels in the original image facilitating the improved segmentation accuracy.

KW - Image segmentation

KW - Image edge detection

KW - Optimization

KW - Benchmark testing

KW - Detectors

KW - Measurement

KW - Task analysis

KW - Superpixel

KW - image segmentation

U2 - 10.1109/ICIP.2019.8803058

DO - 10.1109/ICIP.2019.8803058

M3 - Conference contribution

SN - 978-1-5386-6250-2

T3 - IEEE International Conference on Image Processing

SP - 1505

EP - 1509

BT - 2019 IEEE International Conference on Image Processing (ICIP)

PB - IEEE

ER -