Matches in SemOpenAlex for { <https://semopenalex.org/work/W2885459080> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2885459080 abstract "Image segmentation is an important part of many computer vision tasks such as image recognition and image understanding. Traditional image segmentation algorithms are susceptible to the influence of complex backgrounds such as illumination, shading and occlusion, thus the application of convolution neural network to image segmentation becomes a hot spot of current research. But in the process of image convolution, as the convolution goes further, the image will lose some edge information, resulting in the blurring of the final partition edge. To overcome this problem, we propose an image segmentation algorithm combining the fully convolution neural network and K-means clustering algorithm. By conducting pixel matching between the coarse segmentation result obtained by using the convolution neural network and the segmentation results obtained by using K-means, the algorithm enhances the classification of pixels on the edge to improve segmentation accuracy. The proposed algorithm adopts two-stage training method to train and optimize the model. The experimental results on VOC2012 set validate the effectiveness of the proposed method." @default.
- W2885459080 created "2018-08-22" @default.
- W2885459080 creator A5036563779 @default.
- W2885459080 creator A5074065765 @default.
- W2885459080 creator A5076097741 @default.
- W2885459080 creator A5082932847 @default.
- W2885459080 date "2018-08-09" @default.
- W2885459080 modified "2023-09-23" @default.
- W2885459080 title "Fully convolution neural network combined with K-means clustering algorithm for image segmentation" @default.
- W2885459080 cites W1903029394 @default.
- W2885459080 cites W1983364832 @default.
- W2885459080 cites W2031489346 @default.
- W2885459080 cites W2102605133 @default.
- W2885459080 doi "https://doi.org/10.1117/12.2502814" @default.
- W2885459080 hasPublicationYear "2018" @default.
- W2885459080 type Work @default.
- W2885459080 sameAs 2885459080 @default.
- W2885459080 citedByCount "2" @default.
- W2885459080 countsByYear W28854590802021 @default.
- W2885459080 countsByYear W28854590802022 @default.
- W2885459080 crossrefType "proceedings-article" @default.
- W2885459080 hasAuthorship W2885459080A5036563779 @default.
- W2885459080 hasAuthorship W2885459080A5074065765 @default.
- W2885459080 hasAuthorship W2885459080A5076097741 @default.
- W2885459080 hasAuthorship W2885459080A5082932847 @default.
- W2885459080 hasConcept C11413529 @default.
- W2885459080 hasConcept C124504099 @default.
- W2885459080 hasConcept C153180895 @default.
- W2885459080 hasConcept C154945302 @default.
- W2885459080 hasConcept C160633673 @default.
- W2885459080 hasConcept C25694479 @default.
- W2885459080 hasConcept C31972630 @default.
- W2885459080 hasConcept C41008148 @default.
- W2885459080 hasConcept C42314347 @default.
- W2885459080 hasConcept C45347329 @default.
- W2885459080 hasConcept C50644808 @default.
- W2885459080 hasConcept C65885262 @default.
- W2885459080 hasConcept C67561299 @default.
- W2885459080 hasConcept C73555534 @default.
- W2885459080 hasConcept C81363708 @default.
- W2885459080 hasConcept C89600930 @default.
- W2885459080 hasConceptScore W2885459080C11413529 @default.
- W2885459080 hasConceptScore W2885459080C124504099 @default.
- W2885459080 hasConceptScore W2885459080C153180895 @default.
- W2885459080 hasConceptScore W2885459080C154945302 @default.
- W2885459080 hasConceptScore W2885459080C160633673 @default.
- W2885459080 hasConceptScore W2885459080C25694479 @default.
- W2885459080 hasConceptScore W2885459080C31972630 @default.
- W2885459080 hasConceptScore W2885459080C41008148 @default.
- W2885459080 hasConceptScore W2885459080C42314347 @default.
- W2885459080 hasConceptScore W2885459080C45347329 @default.
- W2885459080 hasConceptScore W2885459080C50644808 @default.
- W2885459080 hasConceptScore W2885459080C65885262 @default.
- W2885459080 hasConceptScore W2885459080C67561299 @default.
- W2885459080 hasConceptScore W2885459080C73555534 @default.
- W2885459080 hasConceptScore W2885459080C81363708 @default.
- W2885459080 hasConceptScore W2885459080C89600930 @default.
- W2885459080 hasLocation W28854590801 @default.
- W2885459080 hasOpenAccess W2885459080 @default.
- W2885459080 hasPrimaryLocation W28854590801 @default.
- W2885459080 hasRelatedWork W11130107 @default.
- W2885459080 hasRelatedWork W1514982293 @default.
- W2885459080 hasRelatedWork W1544749586 @default.
- W2885459080 hasRelatedWork W2047690042 @default.
- W2885459080 hasRelatedWork W2108989806 @default.
- W2885459080 hasRelatedWork W2165254497 @default.
- W2885459080 hasRelatedWork W2212329603 @default.
- W2885459080 hasRelatedWork W2312957464 @default.
- W2885459080 hasRelatedWork W2382738934 @default.
- W2885459080 hasRelatedWork W3201304295 @default.
- W2885459080 isParatext "false" @default.
- W2885459080 isRetracted "false" @default.
- W2885459080 magId "2885459080" @default.
- W2885459080 workType "article" @default.