Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312341104> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4312341104 abstract "Expression recognition is a challenging task. This paper aims to improve upon the accuracy of an existing Machine Learning classification system, with no-retraining of the existing model, by augmenting the images to improve the classification accuracy. A Mid-Processing Unit is used to manipulate data from the first pass of the classifier, this enhances the original image and improves the overall accuracy result. Three, dimensional reduction algorithms are explored as methods to augment the images; Principal Component Analysis, T-distributed Stochastic Neighbour Embedding, and Non-Negative Matrix Factorisation. Facial Landmarks are also explored as an additional data source. Two phased testing was used; 1. to identify which method combination most improved accuracy, and 2. to fine tune the applied weight to the original images. The final results showed that T-distributed Stochastic Neighbour Embedding in combination with a weight set to 0.024, achieved an almost 1% increase in classifier accuracy." @default.
- W4312341104 created "2023-01-04" @default.
- W4312341104 creator A5013565466 @default.
- W4312341104 creator A5046263889 @default.
- W4312341104 creator A5086652988 @default.
- W4312341104 date "2022-07-20" @default.
- W4312341104 modified "2023-09-27" @default.
- W4312341104 title "Augmenting Images with a Mid-Processing Unit to Enhance Classification Accuracy" @default.
- W4312341104 cites W1981918162 @default.
- W4312341104 cites W2083021723 @default.
- W4312341104 cites W2167686991 @default.
- W4312341104 cites W2295124130 @default.
- W4312341104 cites W2745497104 @default.
- W4312341104 cites W2996209825 @default.
- W4312341104 cites W3018475622 @default.
- W4312341104 cites W3099826992 @default.
- W4312341104 cites W3104792420 @default.
- W4312341104 cites W3119221111 @default.
- W4312341104 cites W3145166545 @default.
- W4312341104 cites W4238539449 @default.
- W4312341104 doi "https://doi.org/10.1109/csndsp54353.2022.9907917" @default.
- W4312341104 hasPublicationYear "2022" @default.
- W4312341104 type Work @default.
- W4312341104 citedByCount "0" @default.
- W4312341104 crossrefType "proceedings-article" @default.
- W4312341104 hasAuthorship W4312341104A5013565466 @default.
- W4312341104 hasAuthorship W4312341104A5046263889 @default.
- W4312341104 hasAuthorship W4312341104A5086652988 @default.
- W4312341104 hasConcept C115961682 @default.
- W4312341104 hasConcept C119857082 @default.
- W4312341104 hasConcept C121332964 @default.
- W4312341104 hasConcept C12267149 @default.
- W4312341104 hasConcept C152671427 @default.
- W4312341104 hasConcept C153180895 @default.
- W4312341104 hasConcept C154945302 @default.
- W4312341104 hasConcept C158693339 @default.
- W4312341104 hasConcept C27438332 @default.
- W4312341104 hasConcept C41008148 @default.
- W4312341104 hasConcept C41608201 @default.
- W4312341104 hasConcept C42355184 @default.
- W4312341104 hasConcept C62520636 @default.
- W4312341104 hasConcept C75294576 @default.
- W4312341104 hasConcept C9417928 @default.
- W4312341104 hasConcept C95623464 @default.
- W4312341104 hasConceptScore W4312341104C115961682 @default.
- W4312341104 hasConceptScore W4312341104C119857082 @default.
- W4312341104 hasConceptScore W4312341104C121332964 @default.
- W4312341104 hasConceptScore W4312341104C12267149 @default.
- W4312341104 hasConceptScore W4312341104C152671427 @default.
- W4312341104 hasConceptScore W4312341104C153180895 @default.
- W4312341104 hasConceptScore W4312341104C154945302 @default.
- W4312341104 hasConceptScore W4312341104C158693339 @default.
- W4312341104 hasConceptScore W4312341104C27438332 @default.
- W4312341104 hasConceptScore W4312341104C41008148 @default.
- W4312341104 hasConceptScore W4312341104C41608201 @default.
- W4312341104 hasConceptScore W4312341104C42355184 @default.
- W4312341104 hasConceptScore W4312341104C62520636 @default.
- W4312341104 hasConceptScore W4312341104C75294576 @default.
- W4312341104 hasConceptScore W4312341104C9417928 @default.
- W4312341104 hasConceptScore W4312341104C95623464 @default.
- W4312341104 hasLocation W43123411041 @default.
- W4312341104 hasOpenAccess W4312341104 @default.
- W4312341104 hasPrimaryLocation W43123411041 @default.
- W4312341104 hasRelatedWork W1598786795 @default.
- W4312341104 hasRelatedWork W1607135434 @default.
- W4312341104 hasRelatedWork W1965642519 @default.
- W4312341104 hasRelatedWork W2041636156 @default.
- W4312341104 hasRelatedWork W2153189372 @default.
- W4312341104 hasRelatedWork W2160451891 @default.
- W4312341104 hasRelatedWork W2358965827 @default.
- W4312341104 hasRelatedWork W2538979170 @default.
- W4312341104 hasRelatedWork W3004377704 @default.
- W4312341104 hasRelatedWork W4225691219 @default.
- W4312341104 isParatext "false" @default.
- W4312341104 isRetracted "false" @default.
- W4312341104 workType "article" @default.