Name
Abstract | ||
|---|---|---|
This paper describes hierarchical OCR, a character recognition methodology that achieves high speed and accuracy by using a multiresolution and hierarchical feature space. Features at different resolutions, from coarse to fine-grained, are implemented by means of a recursive classification scheme. Typically, recognizers have to balance the use of features at many resolutions (which yields a high accuracy), with the burden on computational resources in terms of storage space and processing time. We present in this paper, a method that adaptively determines the degree of resolution necessary in order to classify an input pattern. This leads to optimal use of computational resources. The hierarchical OCR dynamically adapts to factors such as the quality of the input pattern, its intrinsic similarities and differences from patterns of other classes it is being compared against, and the processing time available. Furthermore, the finer resolution is accorded to only certain “zones” of the input pattern which are deemed important given the classes that are being discriminated. Experimental results support the methodology presented. When tested on standard NIST data sets, the hierarchical OCR proves to be 300 times faster than a traditional K-nearest-neighbor classification method, and 10 times taster than a neural network method. The comparison uses the same feature set for all methods. Recognition rate of about 96 percent is achieved by the hierarchical OCR. This is at par with the other two traditional methods |
Year | DOI | Venue |
|---|---|---|
2000 | 10.1109/34.845383 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
optimisation,lower case handprinted characters,computational time,storage space,hierarchical ocr,input pattern,hierarchical feature space,traditional k-nearest-neighbor classification method,ocr,computational resource burden,feature space dimensionality,traditional method,computational complexity,different resolution,character recognition methodology,multiresolution hierarchical feature space,multiresolution feature space,image classification,computational resource,hierarchical ocr dynamically adapts,optical character recognition,low-dimensional feature space,upper case handprinted characters,recursive classification scheme,neural network method,processing time,nist,pattern recognition,testing,feature extraction,feature space,recursion,neural networks | Computer vision,Feature vector,Pattern recognition,Computer science,Optical character recognition,Feature extraction,Feature (machine learning),NIST,Artificial intelligence,Contextual image classification,Artificial neural network,Computational complexity theory | Journal |
Volume | Issue | ISSN |
22 | 4 | 0162-8828 |
ISBN | Citations | PageRank |
0-7803-4778-1 | 35 | 1.90 |
References | Authors | |
13 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jaehwa Park | 1 | 65 | 9.50 |
| Venu Govindaraju | 2 | 3521 | 422.00 |
| Sargur N. Srihari | 3 | 2949 | 685.29 |