Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963741128> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2963741128 abstract "A Content-Based Image Retrieval (CBIR) system which identifies similar medical images based on a query image can assist clinicians for more accurate diagnosis. The recent CBIR research trend favors the construction and use of binary codes to represent images. Deep architectures could learn the non-linear relationship among image pixels adaptively, allowing the automatic learning of high-level features from raw pixels. However, most of them require class labels, which are expensive to obtain, particularly for medical images. The methods which do not need class labels utilize a deep autoencoder for binary hashing, but the code construction involves a specific training algorithm and an ad-hoc regularization technique. In this study, we explored using a deep de-noising autoencoder (DDA), with a new unsupervised training scheme using only backpropagation and dropout, to hash images into binary codes. We conducted experiments on more than 14,000 x-ray images. By using class labels only for evaluating the retrieval results, we constructed a 16-bit DDA and a 512-bit DDA independently. Comparing to other unsupervised methods, we succeeded to obtain the lowest total error by using the 512-bit codes for retrieval via exhaustive search, and speed up 9.27 times with the use of the 16-bit codes while keeping a comparable total error. We found that our new training scheme could reduce the total retrieval error significantly by 21.9%. To further boost the image retrieval performance, we developed Radon Autoencoder Barcode (RABC) which are learned from the Radon projections of images using a de-noising autoencoder. Experimental results demonstrated its superior performance in retrieval when it was combined with DDA binary codes." @default.
- W2963741128 created "2019-07-30" @default.
- W2963741128 creator A5038566332 @default.
- W2963741128 creator A5049126089 @default.
- W2963741128 creator A5051841038 @default.
- W2963741128 date "2016-07-01" @default.
- W2963741128 modified "2023-09-25" @default.
- W2963741128 title "Binary codes for tagging x-ray images via deep de-noising autoencoders" @default.
- W2963741128 cites W1468978781 @default.
- W2963741128 cites W1913628733 @default.
- W2963741128 cites W1956333070 @default.
- W2963741128 cites W1983003547 @default.
- W2963741128 cites W1985473611 @default.
- W2963741128 cites W1992371516 @default.
- W2963741128 cites W2005107501 @default.
- W2963741128 cites W2036109700 @default.
- W2963741128 cites W2036924016 @default.
- W2963741128 cites W2049352011 @default.
- W2963741128 cites W2074668987 @default.
- W2963741128 cites W2089575713 @default.
- W2963741128 cites W2096171208 @default.
- W2963741128 cites W2100495367 @default.
- W2963741128 cites W2131748184 @default.
- W2963741128 cites W2156111011 @default.
- W2963741128 cites W2171790913 @default.
- W2963741128 cites W2172177969 @default.
- W2963741128 cites W2202393049 @default.
- W2963741128 cites W2259336176 @default.
- W2963741128 cites W2268345094 @default.
- W2963741128 cites W2913932916 @default.
- W2963741128 cites W2964155457 @default.
- W2963741128 cites W3103722964 @default.
- W2963741128 doi "https://doi.org/10.1109/ijcnn.2016.7727561" @default.
- W2963741128 hasPublicationYear "2016" @default.
- W2963741128 type Work @default.
- W2963741128 sameAs 2963741128 @default.
- W2963741128 citedByCount "8" @default.
- W2963741128 countsByYear W29637411282017 @default.
- W2963741128 countsByYear W29637411282018 @default.
- W2963741128 countsByYear W29637411282020 @default.
- W2963741128 crossrefType "proceedings-article" @default.
- W2963741128 hasAuthorship W2963741128A5038566332 @default.
- W2963741128 hasAuthorship W2963741128A5049126089 @default.
- W2963741128 hasAuthorship W2963741128A5051841038 @default.
- W2963741128 hasBestOaLocation W29637411282 @default.
- W2963741128 hasConcept C108583219 @default.
- W2963741128 hasConcept C153180895 @default.
- W2963741128 hasConcept C154945302 @default.
- W2963741128 hasConcept C33923547 @default.
- W2963741128 hasConcept C41008148 @default.
- W2963741128 hasConcept C48372109 @default.
- W2963741128 hasConcept C94375191 @default.
- W2963741128 hasConceptScore W2963741128C108583219 @default.
- W2963741128 hasConceptScore W2963741128C153180895 @default.
- W2963741128 hasConceptScore W2963741128C154945302 @default.
- W2963741128 hasConceptScore W2963741128C33923547 @default.
- W2963741128 hasConceptScore W2963741128C41008148 @default.
- W2963741128 hasConceptScore W2963741128C48372109 @default.
- W2963741128 hasConceptScore W2963741128C94375191 @default.
- W2963741128 hasLocation W29637411281 @default.
- W2963741128 hasLocation W29637411282 @default.
- W2963741128 hasOpenAccess W2963741128 @default.
- W2963741128 hasPrimaryLocation W29637411281 @default.
- W2963741128 hasRelatedWork W2005051400 @default.
- W2963741128 hasRelatedWork W2738221750 @default.
- W2963741128 hasRelatedWork W2752730668 @default.
- W2963741128 hasRelatedWork W2773120646 @default.
- W2963741128 hasRelatedWork W2965045533 @default.
- W2963741128 hasRelatedWork W3156786002 @default.
- W2963741128 hasRelatedWork W3208028783 @default.
- W2963741128 hasRelatedWork W4211209597 @default.
- W2963741128 hasRelatedWork W4245792239 @default.
- W2963741128 hasRelatedWork W3108696707 @default.
- W2963741128 isParatext "false" @default.
- W2963741128 isRetracted "false" @default.
- W2963741128 magId "2963741128" @default.
- W2963741128 workType "article" @default.