Recognition of sloppy, hand-printed characters

Doyle, W.F.

doi:10.1145/1460361.1460380

Cited by 35 publications

(19 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, in some characterrecognizing machines the stimulus is normalized, or subjected to filtering operations such as "thinning" and "smoothing," before being tested (Doyle, 1960;Minsky, 1963;Selfridge & Neisser, 1963;Stevens, 1961;Unger, 1959). Other artificial recognizers carry the preprocessing further, incorporating a stage in which features are extracted from the stimulus; these features are tested in the subsequent decision process (Bomba, 1959;Fischler et al , 1962;Stevens, 1961).…”

mentioning

confidence: 99%

Two operations in character recognition: Some evidence from reaction-time measurements

Sternberg¹

1967

Perception & Psychophysics

406

309

View full text Add to dashboard Cite

mentioning

confidence: 99%

Two operations in character recognition: Some evidence from reaction-time measurements

Sternberg¹

1967

Perception & Psychophysics

406

309

View full text Add to dashboard Cite

“…Image-based feature extraction was introduced in the early 60s' for character recognition. 3,4 In the late 1980s, feature extraction techniques were used for the first time in spatial sciences with digital images as the data source. 5 During the last two decades, this technique has been used in different fields related to spatial sciences.…”

Section: Introductionmentioning

confidence: 99%

Hybrid method for building extraction in vegetation-rich urban areas from very high-resolution satellite imagery

Jayasekare

Wickramasuriya

Namazi-Rad

et al. 2017

J. Appl. Remote Sens

View full text Add to dashboard Cite

A continuous update of building information is necessary in today's urban planning. Digital images acquired by remote sensing platforms at appropriate spatial and temporal resolutions provide an excellent data source to achieve this. In particular, high-resolution satellite images are often used to retrieve objects such as rooftops using feature extraction. However, high-resolution images acquired over built-up areas are associated with noises such as shadows that reduce the accuracy of feature extraction. Feature extraction heavily relies on the reflectance purity of objects, which is difficult to perfect in complex urban landscapes. An attempt was made to increase the reflectance purity of building rooftops affected by shadows. In addition to the multispectral (MS) image, derivatives thereof namely, normalized difference vegetation index and principle component (PC) images were incorporated in generating the probability image. This hybrid probability image generation ensured that the effect of shadows on rooftop extraction, particularly on light-colored roofs, is largely eliminated. The PC image was also used for image segmentation, which further increased the accuracy compared to segmentation performed on an MS image. Results show that the presented method can achieve higher rooftop extraction accuracy (70.4%) in vegetation-rich urban areas compared to traditional methods. Disciplines Engineering | Physical Sciences and Mathematics Publication DetailsJayasekare, A. S., Wickramasuriya, R., Namazi-Rad, M., Perez, P. & Singh, G. (2017). Hybrid method for building extraction in vegetation-rich urban areas from very high-resolution satellite imagery. Journal of Applied Remote Sensing, 11 (3), 036017-1-036017-12. Abstract. A continuous update of building information is necessary in today's urban planning. Digital images acquired by remote sensing platforms at appropriate spatial and temporal resolutions provide an excellent data source to achieve this. In particular, high-resolution satellite images are often used to retrieve objects such as rooftops using feature extraction. However, high-resolution images acquired over built-up areas are associated with noises such as shadows that reduce the accuracy of feature extraction. Feature extraction heavily relies on the reflectance purity of objects, which is difficult to perfect in complex urban landscapes. An attempt was made to increase the reflectance purity of building rooftops affected by shadows. In addition to the multispectral (MS) image, derivatives thereof namely, normalized difference vegetation index and principle component (PC) images were incorporated in generating the probability image. This hybrid probability image generation ensured that the effect of shadows on rooftop extraction, particularly on light-colored roofs, is largely eliminated. The PC image was also used for image segmentation, which further increased the accuracy compared to segmentation performed on an MS image. Results show that the presented method can achieve higher rooftop ex...

show abstract

“…Recent work by Chow utilises 4 the conditional probability of occurrence of near neighbours of a point in a pattern, in addition to the conditional probability of occurrence of the point itself. Curve-tracing or feature-detection methods, as exemplified by the work of Spilerman 5 or Doyle, 6 represent alternative approaches which, in effect, employ measurements on the interrelation between points of the pattern to attain a classification of the pattern. The performance of feature-detection methods compared with statistical-weighting methods generally exhibits a reduced dependence on the a priori data and an increase in sensitivity Paper IEE, Vol.…”

Section: Introductionmentioning

confidence: 99%

Character recognition by context-dependent transformations

Stern¹,

Shen

1964

Proc. Inst. Electr. Eng. UK

View full text Add to dashboard Cite

SynopsisThis paper records an investigation of a character-recognition method applicable to hand-printed numerals. The technique employed may be characterised as a feature-detection method which utilises a decision tree to reduce the data to a decodable form. The data, consisting of lines and enclosures, are classified into labelled categories by a process which results in the formation of a one-dimensional symbol string. This string is then reduced to a decodable form by sets of context-dependent transformations. Data obtained by computer simulation are presented, indicating the ability of the method to recognise machine-and handprinted numerals.

show abstract

Recognition of sloppy, hand-printed characters

Cited by 35 publications

References 3 publications

Two operations in character recognition: Some evidence from reaction-time measurements

Two operations in character recognition: Some evidence from reaction-time measurements

Hybrid method for building extraction in vegetation-rich urban areas from very high-resolution satellite imagery

Character recognition by context-dependent transformations

Contact Info

Product

Resources

About