Matches in SemOpenAlex for { <https://semopenalex.org/work/W2000436291> ?p ?o ?g. }
Showing items 1 to 54 of
54
with 100 items per page.
- W2000436291 abstract "We present a fast new algorithm for grayscale character recognition. By operating on grayscale images directly, we attempt to maximize the information that can be extracted. Traditional recognition based on binarization of images is also avoided. Previous work using gradient-based contour encoding was used in a restricted domain where objects were size- invariant and fewer patterns had to be distinguished; a simpler feature set sufficed, in this domain. In character recognition, a feature-extractor has to handle character images of arbitrary size. Our algorithm extracts local contour features based on the pixel gradients present in an image. A gradient map, i.e., gradient magnitude and direction at every pixel, is computed; this map is thresholded to avoid responses to noise and spurious artifacts, the map is then partitioned coarsely. Character contours are encoded by quantizing gradient directions into a few representative direction bins. This method does not require that images be normalized to a fixed grid-size before feature extraction. Features extracted by this method have been used to train a 2-layer neural network classifier. Experiments with machine-printed numeric (10-class), and alphanumeric & punctuation (77-class) character images, captured at 300 ppi from mailpiece images, have been conducted. Currently, 99.4% numerals and 93.4% from 77-class images were recognized correctly from a testing set of 5420 numeric and 24,988 character images. When shape and case confusions are allowed, the recognition performance improves to 97.5%. A similar experiment with binarized 77-class images resulted in 92.1% correctly recognized test images. This method is being extended to handwritten characters recognition." @default.
- W2000436291 created "2016-06-24" @default.
- W2000436291 creator A5001005511 @default.
- W2000436291 creator A5026156265 @default.
- W2000436291 creator A5078431770 @default.
- W2000436291 date "1993-04-14" @default.
- W2000436291 modified "2023-10-03" @default.
- W2000436291 title "<title>Gradient-based contour encoding for gray-scale character recognition</title>" @default.
- W2000436291 doi "https://doi.org/10.1117/12.143609" @default.
- W2000436291 hasPublicationYear "1993" @default.
- W2000436291 type Work @default.
- W2000436291 sameAs 2000436291 @default.
- W2000436291 citedByCount "3" @default.
- W2000436291 crossrefType "proceedings-article" @default.
- W2000436291 hasAuthorship W2000436291A5001005511 @default.
- W2000436291 hasAuthorship W2000436291A5026156265 @default.
- W2000436291 hasAuthorship W2000436291A5078431770 @default.
- W2000436291 hasConcept C115961682 @default.
- W2000436291 hasConcept C153180895 @default.
- W2000436291 hasConcept C154945302 @default.
- W2000436291 hasConcept C160633673 @default.
- W2000436291 hasConcept C191178318 @default.
- W2000436291 hasConcept C31972630 @default.
- W2000436291 hasConcept C33923547 @default.
- W2000436291 hasConcept C41008148 @default.
- W2000436291 hasConcept C52622490 @default.
- W2000436291 hasConcept C78201319 @default.
- W2000436291 hasConceptScore W2000436291C115961682 @default.
- W2000436291 hasConceptScore W2000436291C153180895 @default.
- W2000436291 hasConceptScore W2000436291C154945302 @default.
- W2000436291 hasConceptScore W2000436291C160633673 @default.
- W2000436291 hasConceptScore W2000436291C191178318 @default.
- W2000436291 hasConceptScore W2000436291C31972630 @default.
- W2000436291 hasConceptScore W2000436291C33923547 @default.
- W2000436291 hasConceptScore W2000436291C41008148 @default.
- W2000436291 hasConceptScore W2000436291C52622490 @default.
- W2000436291 hasConceptScore W2000436291C78201319 @default.
- W2000436291 hasLocation W20004362911 @default.
- W2000436291 hasOpenAccess W2000436291 @default.
- W2000436291 hasPrimaryLocation W20004362911 @default.
- W2000436291 hasRelatedWork W1580518810 @default.
- W2000436291 hasRelatedWork W2039904248 @default.
- W2000436291 hasRelatedWork W2060518359 @default.
- W2000436291 hasRelatedWork W2105354826 @default.
- W2000436291 hasRelatedWork W2157071234 @default.
- W2000436291 hasRelatedWork W2160069326 @default.
- W2000436291 hasRelatedWork W2184652563 @default.
- W2000436291 hasRelatedWork W2346354572 @default.
- W2000436291 hasRelatedWork W2533404752 @default.
- W2000436291 hasRelatedWork W2542932817 @default.
- W2000436291 isParatext "false" @default.
- W2000436291 isRetracted "false" @default.
- W2000436291 magId "2000436291" @default.
- W2000436291 workType "article" @default.