Matches in SemOpenAlex for { <https://semopenalex.org/work/W2889279385> ?p ?o ?g. }
- W2889279385 endingPage "2481" @default.
- W2889279385 startingPage "2467" @default.
- W2889279385 abstract "The coarse-to-fine shape searching (CFSS) framework is a recently developed algorithm that achieves relatively high accuracy in face alignment by alleviating the poor initialization problem facing traditional cascaded regression approaches. However, its high computational complexity and memory access demands make it difficult for CFSS to satisfy the requirements of real-time processing. To address this issue, a fast shape searching face alignment (F-SSFA) accelerator is presented based on the optimization of the CFSS algorithm and an efficient hardware implementation. First, the learning-based low-dimensional speeded-up robust features method, based on the correlations between the SURF features and the regression targets, is introduced to distill the feature set down to the only most distinct features to reduce the computing load. Second, the partial keypoints Euclidean distance and shape affine transformation are introduced to replace feature extraction and support vector machine classification, thereby accelerating the shape searching process. Compared with CFSS, F-SSFA achieves a $5.8times $ speedup while achieving similar accuracy. Moreover, a VLSI architecture is proposed to realize the fixed-point F-SSFA algorithm. Multiple descriptors located in adjacent regions are simultaneously generated in a single access to the corresponding image data. Therefore, repeated memory access operations are avoided. The optimal parameter configuration for hardware implementation is also exploited based on a tradeoff between accuracy and hardware performance. Simulated with TSMC 65-nm 1P8M technology within a 3.6 mm <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> area, a post-layout simulation shows that 700 fps can be achieved while consuming 300 mW at 200 MHz." @default.
- W2889279385 created "2018-09-07" @default.
- W2889279385 creator A5000141831 @default.
- W2889279385 creator A5017205152 @default.
- W2889279385 creator A5028066238 @default.
- W2889279385 creator A5030863883 @default.
- W2889279385 creator A5036023084 @default.
- W2889279385 creator A5051391822 @default.
- W2889279385 creator A5054524841 @default.
- W2889279385 creator A5064687523 @default.
- W2889279385 date "2019-08-01" @default.
- W2889279385 modified "2023-10-16" @default.
- W2889279385 title "A Face Alignment Accelerator Based on Optimized Coarse-to-Fine Shape Searching" @default.
- W2889279385 cites W1976948919 @default.
- W2889279385 cites W1977821862 @default.
- W2889279385 cites W1992914425 @default.
- W2889279385 cites W1993977496 @default.
- W2889279385 cites W1998294030 @default.
- W2889279385 cites W2009621568 @default.
- W2889279385 cites W2032558548 @default.
- W2889279385 cites W2032618685 @default.
- W2889279385 cites W2058961190 @default.
- W2889279385 cites W2060458806 @default.
- W2889279385 cites W2090495691 @default.
- W2889279385 cites W2097711399 @default.
- W2889279385 cites W2101866605 @default.
- W2889279385 cites W2111372597 @default.
- W2889279385 cites W2116277445 @default.
- W2889279385 cites W2124750300 @default.
- W2889279385 cites W2130563197 @default.
- W2889279385 cites W2130931342 @default.
- W2889279385 cites W2134667272 @default.
- W2889279385 cites W2136000821 @default.
- W2889279385 cites W2136243427 @default.
- W2889279385 cites W2152826865 @default.
- W2889279385 cites W2157285372 @default.
- W2889279385 cites W2170304073 @default.
- W2889279385 cites W2343528117 @default.
- W2889279385 cites W2462523589 @default.
- W2889279385 cites W2465108587 @default.
- W2889279385 cites W2467255717 @default.
- W2889279385 cites W2740020909 @default.
- W2889279385 cites W2755672797 @default.
- W2889279385 cites W2963993755 @default.
- W2889279385 cites W2964014798 @default.
- W2889279385 cites W3152330821 @default.
- W2889279385 doi "https://doi.org/10.1109/tcsvt.2018.2867499" @default.
- W2889279385 hasPublicationYear "2019" @default.
- W2889279385 type Work @default.
- W2889279385 sameAs 2889279385 @default.
- W2889279385 citedByCount "5" @default.
- W2889279385 countsByYear W28892793852020 @default.
- W2889279385 countsByYear W28892793852022 @default.
- W2889279385 countsByYear W28892793852023 @default.
- W2889279385 crossrefType "journal-article" @default.
- W2889279385 hasAuthorship W2889279385A5000141831 @default.
- W2889279385 hasAuthorship W2889279385A5017205152 @default.
- W2889279385 hasAuthorship W2889279385A5028066238 @default.
- W2889279385 hasAuthorship W2889279385A5030863883 @default.
- W2889279385 hasAuthorship W2889279385A5036023084 @default.
- W2889279385 hasAuthorship W2889279385A5051391822 @default.
- W2889279385 hasAuthorship W2889279385A5054524841 @default.
- W2889279385 hasAuthorship W2889279385A5064687523 @default.
- W2889279385 hasConcept C111919701 @default.
- W2889279385 hasConcept C11413529 @default.
- W2889279385 hasConcept C114466953 @default.
- W2889279385 hasConcept C120174047 @default.
- W2889279385 hasConcept C12267149 @default.
- W2889279385 hasConcept C138885662 @default.
- W2889279385 hasConcept C144024400 @default.
- W2889279385 hasConcept C153180895 @default.
- W2889279385 hasConcept C154945302 @default.
- W2889279385 hasConcept C173608175 @default.
- W2889279385 hasConcept C177264268 @default.
- W2889279385 hasConcept C199360897 @default.
- W2889279385 hasConcept C202444582 @default.
- W2889279385 hasConcept C2776401178 @default.
- W2889279385 hasConcept C2779304628 @default.
- W2889279385 hasConcept C33923547 @default.
- W2889279385 hasConcept C36289849 @default.
- W2889279385 hasConcept C41008148 @default.
- W2889279385 hasConcept C41895202 @default.
- W2889279385 hasConcept C52622490 @default.
- W2889279385 hasConcept C68339613 @default.
- W2889279385 hasConcept C92757383 @default.
- W2889279385 hasConcept C98045186 @default.
- W2889279385 hasConceptScore W2889279385C111919701 @default.
- W2889279385 hasConceptScore W2889279385C11413529 @default.
- W2889279385 hasConceptScore W2889279385C114466953 @default.
- W2889279385 hasConceptScore W2889279385C120174047 @default.
- W2889279385 hasConceptScore W2889279385C12267149 @default.
- W2889279385 hasConceptScore W2889279385C138885662 @default.
- W2889279385 hasConceptScore W2889279385C144024400 @default.
- W2889279385 hasConceptScore W2889279385C153180895 @default.
- W2889279385 hasConceptScore W2889279385C154945302 @default.
- W2889279385 hasConceptScore W2889279385C173608175 @default.
- W2889279385 hasConceptScore W2889279385C177264268 @default.
- W2889279385 hasConceptScore W2889279385C199360897 @default.