Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285134509> ?p ?o ?g. }
- W4285134509 endingPage "1075" @default.
- W4285134509 startingPage "1064" @default.
- W4285134509 abstract "Numerous imaging applications are affected by the poor quality of images caused by poor illuminating conditions, contrast degradation, and unwanted noise. These effects create noticeable artifacts in an indeterministic selective manner, where some parts of the image are modified, and some parts of the image are uninfluenced. Thus, classification of an image into various sections and then segment-wise application of imaging algorithms is a preferable solution. The paper focuses on classifying an image into three categories as under-well-over exposed regions. This paper introduces the concept of multilevel superpixel-based classification. Superpixel stores the local integrity and color similarity of an image; hence an image is initially classified into an experimentally pre-determined number of superpixels. Then, a novel algorithm depending upon the superpixel contrast, entropy, and statistical distribution of illumination classifies it into an under-well-over-exposed region. Then with an increased number of superpixels, we reiterate the whole process. The regions classified into the same category in both iterations perform as the training datasets for the support-vector-machine (SVM) classifier. Finally, the trained SVM classifies the ambiguous regions obtained from multilevel superpixel classification. Both qualitative and visual results show the superior performance of the proposed method over state-of-the-art methods." @default.
- W4285134509 created "2022-07-14" @default.
- W4285134509 creator A5051124509 @default.
- W4285134509 creator A5066467382 @default.
- W4285134509 date "2023-10-01" @default.
- W4285134509 modified "2023-09-27" @default.
- W4285134509 title "Novel Unsupervised Learning Architecture for Exposure Based Classification and Enhancement" @default.
- W4285134509 cites W1964797636 @default.
- W4285134509 cites W1966994480 @default.
- W4285134509 cites W1971014006 @default.
- W4285134509 cites W1993150044 @default.
- W4285134509 cites W2002260165 @default.
- W4285134509 cites W2021228735 @default.
- W4285134509 cites W2038905805 @default.
- W4285134509 cites W2054814429 @default.
- W4285134509 cites W2102584639 @default.
- W4285134509 cites W2110158442 @default.
- W4285134509 cites W2112633580 @default.
- W4285134509 cites W2114770744 @default.
- W4285134509 cites W2118246710 @default.
- W4285134509 cites W2121927366 @default.
- W4285134509 cites W2135996040 @default.
- W4285134509 cites W2137304315 @default.
- W4285134509 cites W2139756630 @default.
- W4285134509 cites W2141983208 @default.
- W4285134509 cites W2144628669 @default.
- W4285134509 cites W2159990220 @default.
- W4285134509 cites W2285474868 @default.
- W4285134509 cites W2574210758 @default.
- W4285134509 cites W2587580983 @default.
- W4285134509 cites W2612911136 @default.
- W4285134509 cites W2620950432 @default.
- W4285134509 cites W2799396445 @default.
- W4285134509 cites W2884110313 @default.
- W4285134509 cites W2945180985 @default.
- W4285134509 cites W2963716449 @default.
- W4285134509 cites W2995898670 @default.
- W4285134509 cites W3022873651 @default.
- W4285134509 cites W3037564611 @default.
- W4285134509 cites W3096613845 @default.
- W4285134509 cites W3107034740 @default.
- W4285134509 cites W3128437195 @default.
- W4285134509 cites W3154997553 @default.
- W4285134509 cites W3170968229 @default.
- W4285134509 cites W3175052667 @default.
- W4285134509 cites W3176180772 @default.
- W4285134509 cites W3177177219 @default.
- W4285134509 cites W3195428940 @default.
- W4285134509 cites W3196939630 @default.
- W4285134509 cites W4205340545 @default.
- W4285134509 cites W4206615997 @default.
- W4285134509 doi "https://doi.org/10.1109/tai.2022.3190240" @default.
- W4285134509 hasPublicationYear "2023" @default.
- W4285134509 type Work @default.
- W4285134509 citedByCount "0" @default.
- W4285134509 crossrefType "journal-article" @default.
- W4285134509 hasAuthorship W4285134509A5051124509 @default.
- W4285134509 hasAuthorship W4285134509A5066467382 @default.
- W4285134509 hasConcept C106301342 @default.
- W4285134509 hasConcept C115961682 @default.
- W4285134509 hasConcept C119857082 @default.
- W4285134509 hasConcept C121332964 @default.
- W4285134509 hasConcept C12267149 @default.
- W4285134509 hasConcept C153180895 @default.
- W4285134509 hasConcept C154945302 @default.
- W4285134509 hasConcept C2776502983 @default.
- W4285134509 hasConcept C41008148 @default.
- W4285134509 hasConcept C62520636 @default.
- W4285134509 hasConcept C75294576 @default.
- W4285134509 hasConcept C95623464 @default.
- W4285134509 hasConceptScore W4285134509C106301342 @default.
- W4285134509 hasConceptScore W4285134509C115961682 @default.
- W4285134509 hasConceptScore W4285134509C119857082 @default.
- W4285134509 hasConceptScore W4285134509C121332964 @default.
- W4285134509 hasConceptScore W4285134509C12267149 @default.
- W4285134509 hasConceptScore W4285134509C153180895 @default.
- W4285134509 hasConceptScore W4285134509C154945302 @default.
- W4285134509 hasConceptScore W4285134509C2776502983 @default.
- W4285134509 hasConceptScore W4285134509C41008148 @default.
- W4285134509 hasConceptScore W4285134509C62520636 @default.
- W4285134509 hasConceptScore W4285134509C75294576 @default.
- W4285134509 hasConceptScore W4285134509C95623464 @default.
- W4285134509 hasIssue "5" @default.
- W4285134509 hasLocation W42851345091 @default.
- W4285134509 hasOpenAccess W4285134509 @default.
- W4285134509 hasPrimaryLocation W42851345091 @default.
- W4285134509 hasRelatedWork W2041399278 @default.
- W4285134509 hasRelatedWork W2056016498 @default.
- W4285134509 hasRelatedWork W2136184105 @default.
- W4285134509 hasRelatedWork W2336974148 @default.
- W4285134509 hasRelatedWork W2563096758 @default.
- W4285134509 hasRelatedWork W2742991909 @default.
- W4285134509 hasRelatedWork W2972035100 @default.
- W4285134509 hasRelatedWork W3013515612 @default.
- W4285134509 hasRelatedWork W2187500075 @default.
- W4285134509 hasRelatedWork W2345184372 @default.
- W4285134509 hasVolume "4" @default.
- W4285134509 isParatext "false" @default.