Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971303460> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2971303460 abstract "Eye pupil localization is one of the indispensable technologies in various computer vision applications such as virtual reality and augmented reality. In general, the algorithm consists of finding the approximate eye region and finding the pupil position by extracting the semantic feature from each eye region. However, the performance is affected not only by illumination and image resolution but also by glasses wear. Therefore, this paper proposes an eye pupil localization algorithm which is robust against the above disturbance conditions and also has high accuracy using heterogeneous CNN models. First, faces in the image and landmarks in the face(s) are detected sequentially, and the eye region is determined based on the landmarks. Especially, if glasses are present, the glasses are removed by GAN to find the correct eye region. Next, the pupil region is segmented using fully convolutional networks. Finally, the position of the segmented pupil is calculated. Experimental results show that the proposed algorithm outperforms the state-of-the-art algorithms for public databases such as BioID and GI4E." @default.
- W2971303460 created "2019-09-05" @default.
- W2971303460 creator A5002584996 @default.
- W2971303460 creator A5045921699 @default.
- W2971303460 creator A5056469803 @default.
- W2971303460 creator A5065677543 @default.
- W2971303460 date "2019-09-01" @default.
- W2971303460 modified "2023-10-16" @default.
- W2971303460 title "Accurate Eye Pupil Localization Using Heterogeneous CNN Models" @default.
- W2971303460 cites W1903029394 @default.
- W2971303460 cites W1964988669 @default.
- W2971303460 cites W1986291329 @default.
- W2971303460 cites W2017617273 @default.
- W2971303460 cites W2040336280 @default.
- W2971303460 cites W2043033468 @default.
- W2971303460 cites W2046399019 @default.
- W2971303460 cites W2078626246 @default.
- W2971303460 cites W2087681821 @default.
- W2971303460 cites W2128625732 @default.
- W2971303460 cites W2583387051 @default.
- W2971303460 cites W2800040407 @default.
- W2971303460 cites W2962793481 @default.
- W2971303460 cites W2963073614 @default.
- W2971303460 cites W3098075019 @default.
- W2971303460 cites W4293154803 @default.
- W2971303460 doi "https://doi.org/10.1109/icip.2019.8803121" @default.
- W2971303460 hasPublicationYear "2019" @default.
- W2971303460 type Work @default.
- W2971303460 sameAs 2971303460 @default.
- W2971303460 citedByCount "8" @default.
- W2971303460 countsByYear W29713034602020 @default.
- W2971303460 countsByYear W29713034602021 @default.
- W2971303460 countsByYear W29713034602022 @default.
- W2971303460 crossrefType "proceedings-article" @default.
- W2971303460 hasAuthorship W2971303460A5002584996 @default.
- W2971303460 hasAuthorship W2971303460A5045921699 @default.
- W2971303460 hasAuthorship W2971303460A5056469803 @default.
- W2971303460 hasAuthorship W2971303460A5065677543 @default.
- W2971303460 hasConcept C154945302 @default.
- W2971303460 hasConcept C15744967 @default.
- W2971303460 hasConcept C169760540 @default.
- W2971303460 hasConcept C2777394604 @default.
- W2971303460 hasConcept C31972630 @default.
- W2971303460 hasConcept C41008148 @default.
- W2971303460 hasConceptScore W2971303460C154945302 @default.
- W2971303460 hasConceptScore W2971303460C15744967 @default.
- W2971303460 hasConceptScore W2971303460C169760540 @default.
- W2971303460 hasConceptScore W2971303460C2777394604 @default.
- W2971303460 hasConceptScore W2971303460C31972630 @default.
- W2971303460 hasConceptScore W2971303460C41008148 @default.
- W2971303460 hasLocation W29713034601 @default.
- W2971303460 hasOpenAccess W2971303460 @default.
- W2971303460 hasPrimaryLocation W29713034601 @default.
- W2971303460 hasRelatedWork W1866425048 @default.
- W2971303460 hasRelatedWork W188136256 @default.
- W2971303460 hasRelatedWork W2067291342 @default.
- W2971303460 hasRelatedWork W2148725491 @default.
- W2971303460 hasRelatedWork W2161834109 @default.
- W2971303460 hasRelatedWork W2320174866 @default.
- W2971303460 hasRelatedWork W2565528002 @default.
- W2971303460 hasRelatedWork W2592357055 @default.
- W2971303460 hasRelatedWork W276445467 @default.
- W2971303460 hasRelatedWork W3119850247 @default.
- W2971303460 isParatext "false" @default.
- W2971303460 isRetracted "false" @default.
- W2971303460 magId "2971303460" @default.
- W2971303460 workType "article" @default.