Matches in SemOpenAlex for { <https://semopenalex.org/work/W3163158492> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W3163158492 abstract "Deep learning and convolutional neural networks have become the main tools of computer vision. These techniques are good at using supervised learning to learn complex representations from data. In particular, under limited settings, the image recognition model now performs better than the human baseline. However, computer vision science aims to build machines that can see. It requires the model to be able to extract more valuable information from images and videos than recognition. Generally, it is much more challenging to apply these deep learning models from recognition to other problems in computer vision.This thesis presents end-to-end deep learning architectures for a new computer vision field: watermark retrieval from 3D printed objects. As it is a new area, there is no state-of-the-art on many challenging benchmarks. Hence, we first define the problems and introduce the traditional approach, Local Binary Pattern method, to set our baseline for further study. Our neural networks seem useful but straightfor- ward, which outperform traditional approaches. What is more, these networks have good generalization. However, because our research field is new, the problems we face are not only various unpredictable parameters but also limited and low-quality training data.To address this, we make two observations: (i) we do not need to learn everything from scratch, we know a lot about the image segmentation area, and (ii) we cannot know everything from data, our models should be aware what key features theyshould learn. This thesis explores these ideas and even explore more. We show how to use end-to-end deep learning models to learn to retrieve watermark bumps and tackle covariates from a few training images data. Secondly, we introduce ideas from synthetic image data and domain randomization to augment training data and understand various covariates that may affect retrieve real-world 3D watermark bumps. We also show how the illumination in synthetic images data to effect and even improve retrieval accuracy for real-world recognization applications." @default.
- W3163158492 created "2021-05-24" @default.
- W3163158492 creator A5006651636 @default.
- W3163158492 date "2020-01-01" @default.
- W3163158492 modified "2023-09-27" @default.
- W3163158492 title "Information embedding and retrieval in 3D printed objects" @default.
- W3163158492 hasPublicationYear "2020" @default.
- W3163158492 type Work @default.
- W3163158492 sameAs 3163158492 @default.
- W3163158492 citedByCount "0" @default.
- W3163158492 crossrefType "dissertation" @default.
- W3163158492 hasAuthorship W3163158492A5006651636 @default.
- W3163158492 hasConcept C108583219 @default.
- W3163158492 hasConcept C111368507 @default.
- W3163158492 hasConcept C119857082 @default.
- W3163158492 hasConcept C12725497 @default.
- W3163158492 hasConcept C127313418 @default.
- W3163158492 hasConcept C153180895 @default.
- W3163158492 hasConcept C154945302 @default.
- W3163158492 hasConcept C177264268 @default.
- W3163158492 hasConcept C199360897 @default.
- W3163158492 hasConcept C202444582 @default.
- W3163158492 hasConcept C26517878 @default.
- W3163158492 hasConcept C33923547 @default.
- W3163158492 hasConcept C38652104 @default.
- W3163158492 hasConcept C41008148 @default.
- W3163158492 hasConcept C81363708 @default.
- W3163158492 hasConcept C9652623 @default.
- W3163158492 hasConceptScore W3163158492C108583219 @default.
- W3163158492 hasConceptScore W3163158492C111368507 @default.
- W3163158492 hasConceptScore W3163158492C119857082 @default.
- W3163158492 hasConceptScore W3163158492C12725497 @default.
- W3163158492 hasConceptScore W3163158492C127313418 @default.
- W3163158492 hasConceptScore W3163158492C153180895 @default.
- W3163158492 hasConceptScore W3163158492C154945302 @default.
- W3163158492 hasConceptScore W3163158492C177264268 @default.
- W3163158492 hasConceptScore W3163158492C199360897 @default.
- W3163158492 hasConceptScore W3163158492C202444582 @default.
- W3163158492 hasConceptScore W3163158492C26517878 @default.
- W3163158492 hasConceptScore W3163158492C33923547 @default.
- W3163158492 hasConceptScore W3163158492C38652104 @default.
- W3163158492 hasConceptScore W3163158492C41008148 @default.
- W3163158492 hasConceptScore W3163158492C81363708 @default.
- W3163158492 hasConceptScore W3163158492C9652623 @default.
- W3163158492 hasLocation W31631584921 @default.
- W3163158492 hasOpenAccess W3163158492 @default.
- W3163158492 hasPrimaryLocation W31631584921 @default.
- W3163158492 hasRelatedWork W1776042733 @default.
- W3163158492 hasRelatedWork W2143660872 @default.
- W3163158492 hasRelatedWork W2607777488 @default.
- W3163158492 hasRelatedWork W2785105650 @default.
- W3163158492 hasRelatedWork W2891313969 @default.
- W3163158492 hasRelatedWork W2910141298 @default.
- W3163158492 hasRelatedWork W2946453420 @default.
- W3163158492 hasRelatedWork W2952809312 @default.
- W3163158492 hasRelatedWork W2958756501 @default.
- W3163158492 hasRelatedWork W2963492113 @default.
- W3163158492 hasRelatedWork W2981114409 @default.
- W3163158492 hasRelatedWork W2987008042 @default.
- W3163158492 hasRelatedWork W2996647511 @default.
- W3163158492 hasRelatedWork W3002520175 @default.
- W3163158492 hasRelatedWork W3124227290 @default.
- W3163158492 hasRelatedWork W3129279281 @default.
- W3163158492 hasRelatedWork W3169973052 @default.
- W3163158492 hasRelatedWork W3170144722 @default.
- W3163158492 hasRelatedWork W3196096487 @default.
- W3163158492 hasRelatedWork W2137585067 @default.
- W3163158492 isParatext "false" @default.
- W3163158492 isRetracted "false" @default.
- W3163158492 magId "3163158492" @default.
- W3163158492 workType "dissertation" @default.