- We will send in 10–14 business days.
/images/books/13399039/9783844314038.jpg)
- Author: Kaushik Roy
- Publisher: LAP Lambert Academic Publishing
- ISBN-10: 3844314032
- ISBN-13: 9783844314038
- Format: 15.2 x 22.9 x 0.9 cm, minkšti viršeliai
- Language: English
- SAVE -10% with code: EXTRA
On the Development of an OCR System for Indian Postal Automation (e-book) (used book) | bookbook.eu
Reviews
Description
Various problems towards the development of Indian Postal Automation (IPA) system is discussed here. More specifically, in this endeavor, some of the tasks such as, statistical analysis of Indian postal documents, bi-lingual pin code digit recognition, script identification prior to city name recognition, and Dynamic Programming (DP) based city name recognition of Bangla script are the major contributions of this work. The feature sets considered for the work consists of Structural and Statistical features, Normalized binary pixel images, Direction code based features, Gradient based features etc. For recognition, two categories of classifiers, viz., Multi Layer Perceptron (MLP) and Modified Quadratic Discriminant Function (MQDF) based classifiers have been selectively tested here and detailed results are presented.
EXTRA 10 % discount with code: EXTRA
The promotion ends in 22d.00:22:11
The discount code is valid when purchasing from 10 €. Discounts do not stack.
- Author: Kaushik Roy
- Publisher: LAP Lambert Academic Publishing
- ISBN-10: 3844314032
- ISBN-13: 9783844314038
- Format: 15.2 x 22.9 x 0.9 cm, minkšti viršeliai
- Language: English English
Various problems towards the development of Indian Postal Automation (IPA) system is discussed here. More specifically, in this endeavor, some of the tasks such as, statistical analysis of Indian postal documents, bi-lingual pin code digit recognition, script identification prior to city name recognition, and Dynamic Programming (DP) based city name recognition of Bangla script are the major contributions of this work. The feature sets considered for the work consists of Structural and Statistical features, Normalized binary pixel images, Direction code based features, Gradient based features etc. For recognition, two categories of classifiers, viz., Multi Layer Perceptron (MLP) and Modified Quadratic Discriminant Function (MQDF) based classifiers have been selectively tested here and detailed results are presented.
Reviews