Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949837029> ?p ?o ?g. }
- W2949837029 abstract "Superpixel segmentation algorithms are to partition an image into perceptually coherence atomic regions by assigning every pixel a superpixel label. Those algorithms have been wildly used as a preprocessing step in computer vision works, as they can enormously reduce the number of entries of subsequent algorithms. In this work, we propose an alternative superpixel segmentation method based on Gaussian mixture model (GMM) by assuming that each superpixel corresponds to a Gaussian distribution, and assuming that each pixel is generated by first randomly choosing one distribution from several Gaussian distributions which are defined to be related to that pixel, and then the pixel is drawn from the selected distribution. Based on this assumption, each pixel is supposed to be drawn from a mixture of Gaussian distributions with unknown parameters (GMM). An algorithm based on expectation-maximization method is applied to estimate the unknown parameters. Once the unknown parameters are obtained, the superpixel label of a pixel is determined by a posterior probability. The success of applying GMM to superpixel segmentation depends on the two major differences between the traditional GMM-based clustering and the proposed one: data points in our model may be non-identically distributed, and we present an approach to control the shape of the estimated Gaussian functions by adjusting their covariance matrices. Our method is of linear complexity with respect to the number of pixels. The proposed algorithm is inherently parallel and can get faster speed by adding simple OpenMP directives to our implementation. According to our experiments, our algorithm outperforms the state-of-the-art superpixel algorithms in accuracy and presents a competitive performance in computational efficiency." @default.
- W2949837029 created "2019-06-27" @default.
- W2949837029 creator A5014627584 @default.
- W2949837029 creator A5049225898 @default.
- W2949837029 creator A5060859362 @default.
- W2949837029 date "2016-12-27" @default.
- W2949837029 modified "2023-09-25" @default.
- W2949837029 title "Superpixel Segmentation Using Gaussian Mixture Model" @default.
- W2949837029 cites W1548953334 @default.
- W2949837029 cites W1561797649 @default.
- W2949837029 cites W1658330868 @default.
- W2949837029 cites W1791783407 @default.
- W2949837029 cites W1839843765 @default.
- W2949837029 cites W1938929646 @default.
- W2949837029 cites W1944585701 @default.
- W2949837029 cites W1950112384 @default.
- W2949837029 cites W1992779583 @default.
- W2949837029 cites W1994938019 @default.
- W2949837029 cites W1997942003 @default.
- W2949837029 cites W1999478155 @default.
- W2949837029 cites W2003060733 @default.
- W2949837029 cites W2003088946 @default.
- W2949837029 cites W2010975286 @default.
- W2949837029 cites W2016872984 @default.
- W2949837029 cites W2018377917 @default.
- W2949837029 cites W2039684198 @default.
- W2949837029 cites W2049633694 @default.
- W2949837029 cites W2067191022 @default.
- W2949837029 cites W2104125540 @default.
- W2949837029 cites W2108424265 @default.
- W2949837029 cites W2110158442 @default.
- W2949837029 cites W2110248298 @default.
- W2949837029 cites W2114808114 @default.
- W2949837029 cites W2118246710 @default.
- W2949837029 cites W2119531662 @default.
- W2949837029 cites W2119823327 @default.
- W2949837029 cites W2121947440 @default.
- W2949837029 cites W2124260943 @default.
- W2949837029 cites W2135431554 @default.
- W2949837029 cites W2143516773 @default.
- W2949837029 cites W2149233894 @default.
- W2949837029 cites W2156406314 @default.
- W2949837029 cites W2167094141 @default.
- W2949837029 cites W2293105860 @default.
- W2949837029 cites W2295342296 @default.
- W2949837029 cites W2312198368 @default.
- W2949837029 cites W2471353525 @default.
- W2949837029 doi "https://doi.org/10.48550/arxiv.1612.08792" @default.
- W2949837029 hasPublicationYear "2016" @default.
- W2949837029 type Work @default.
- W2949837029 sameAs 2949837029 @default.
- W2949837029 citedByCount "0" @default.
- W2949837029 crossrefType "posted-content" @default.
- W2949837029 hasAuthorship W2949837029A5014627584 @default.
- W2949837029 hasAuthorship W2949837029A5049225898 @default.
- W2949837029 hasAuthorship W2949837029A5060859362 @default.
- W2949837029 hasBestOaLocation W29498370291 @default.
- W2949837029 hasConcept C105795698 @default.
- W2949837029 hasConcept C107673813 @default.
- W2949837029 hasConcept C11413529 @default.
- W2949837029 hasConcept C121332964 @default.
- W2949837029 hasConcept C124504099 @default.
- W2949837029 hasConcept C153180895 @default.
- W2949837029 hasConcept C154945302 @default.
- W2949837029 hasConcept C160633673 @default.
- W2949837029 hasConcept C163716315 @default.
- W2949837029 hasConcept C178650346 @default.
- W2949837029 hasConcept C182081679 @default.
- W2949837029 hasConcept C33923547 @default.
- W2949837029 hasConcept C41008148 @default.
- W2949837029 hasConcept C49781872 @default.
- W2949837029 hasConcept C57830394 @default.
- W2949837029 hasConcept C61224824 @default.
- W2949837029 hasConcept C62520636 @default.
- W2949837029 hasConcept C73555534 @default.
- W2949837029 hasConcept C89600930 @default.
- W2949837029 hasConceptScore W2949837029C105795698 @default.
- W2949837029 hasConceptScore W2949837029C107673813 @default.
- W2949837029 hasConceptScore W2949837029C11413529 @default.
- W2949837029 hasConceptScore W2949837029C121332964 @default.
- W2949837029 hasConceptScore W2949837029C124504099 @default.
- W2949837029 hasConceptScore W2949837029C153180895 @default.
- W2949837029 hasConceptScore W2949837029C154945302 @default.
- W2949837029 hasConceptScore W2949837029C160633673 @default.
- W2949837029 hasConceptScore W2949837029C163716315 @default.
- W2949837029 hasConceptScore W2949837029C178650346 @default.
- W2949837029 hasConceptScore W2949837029C182081679 @default.
- W2949837029 hasConceptScore W2949837029C33923547 @default.
- W2949837029 hasConceptScore W2949837029C41008148 @default.
- W2949837029 hasConceptScore W2949837029C49781872 @default.
- W2949837029 hasConceptScore W2949837029C57830394 @default.
- W2949837029 hasConceptScore W2949837029C61224824 @default.
- W2949837029 hasConceptScore W2949837029C62520636 @default.
- W2949837029 hasConceptScore W2949837029C73555534 @default.
- W2949837029 hasConceptScore W2949837029C89600930 @default.
- W2949837029 hasLocation W29498370291 @default.
- W2949837029 hasOpenAccess W2949837029 @default.
- W2949837029 hasPrimaryLocation W29498370291 @default.
- W2949837029 hasRelatedWork W2136485282 @default.
- W2949837029 hasRelatedWork W2139982152 @default.