{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/superpixel-segmentation-using-gaussian","title":"Superpixel Segmentation Using Gaussian Mixture Model","arxiv_id":"1612.08792","date":"2016-12-28","proceeding":null,"authors":["Zhihua Ban","Jian-Guo Liu","Li Cao"],"abstract":"Superpixel segmentation algorithms are to partition an image into\nperceptually coherence atomic regions by assigning every pixel a superpixel\nlabel. Those algorithms have been wildly used as a preprocessing step in\ncomputer vision works, as they can enormously reduce the number of entries of\nsubsequent algorithms. In this work, we propose an alternative superpixel\nsegmentation method based on Gaussian mixture model (GMM) by assuming that each\nsuperpixel corresponds to a Gaussian distribution, and assuming that each pixel\nis generated by first randomly choosing one distribution from several Gaussian\ndistributions which are defined to be related to that pixel, and then the pixel\nis drawn from the selected distribution. Based on this assumption, each pixel\nis supposed to be drawn from a mixture of Gaussian distributions with unknown\nparameters (GMM). An algorithm based on expectation-maximization method is\napplied to estimate the unknown parameters. Once the unknown parameters are\nobtained, the superpixel label of a pixel is determined by a posterior\nprobability. The success of applying GMM to superpixel segmentation depends on\nthe two major differences between the traditional GMM-based clustering and the\nproposed one: data points in our model may be non-identically distributed, and\nwe present an approach to control the shape of the estimated Gaussian functions\nby adjusting their covariance matrices. Our method is of linear complexity with\nrespect to the number of pixels. The proposed algorithm is inherently parallel\nand can get faster speed by adding simple OpenMP directives to our\nimplementation. According to our experiments, our algorithm outperforms the\nstate-of-the-art superpixel algorithms in accuracy and presents a competitive\nperformance in computational efficiency.","url_abs":"http://arxiv.org/abs/1612.08792v2","url_pdf":"http://arxiv.org/pdf/1612.08792v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"superpixel-segmentation-using-gaussian","repo_url":"https://github.com/ahban/GMMSP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"ahban/GMMSP","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"8b6d9cef32fc5ee1e19f0b2770f258940f10f647d91bb39259ebaef107fb3dc5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}