Chaincode Contour Processing for Handwritten Word Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Role of Holistic Paradigms in Handwritten Word Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Dynamics features Extraction for on-Line Signature verification
CONIELECOMP '04 Proceedings of the 14th International Conference on Electronics, Communications and Computers
Local Slant Estimation for Handwritten English Words
IWFHR '04 Proceedings of the Ninth International Workshop on Frontiers in Handwriting Recognition
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Intelligent water dispersal controller using Mamdani approach
FS'07 Proceedings of the 8th Conference on 8th WSEAS International Conference on Fuzzy Systems - Volume 8
Online slant identification algorithm for curved strokes
SEPADS'08 Proceedings of the 7th WSEAS International Conference on Software Engineering, Parallel and Distributed Systems
Online signature slant feature identification algorithm
WSEAS Transactions on Computer Research
Hi-index | 0.00 |
A vector rule-based approach and analysis to on-line slant signature recognition algorithm is presented. Extracting features in signature is an intense area due to complex human behavior, which is developed through repetition. Features such as direction, slant, baseline, pressure, speed and numbers of pen ups and downs are some of the dynamic information signature that can be extracted from an online method. This paper presents the variables involve in designing the algorithm for extracting the slant feature. Signature Extraction Features System (SEFS) is used to extract the slant features in signature automatically for analysis purposes. The system uses both local and global slant characteristics in extracting the feature. Local slant is the longest slant among the detected slant while the global slant represents the highest quantity of classified slant whether the slant are leftward, upright or rightward. Development and analysis are reported on a database comprises of 20 signatures from 20 subjects. The system is compared to human expert evaluation. The results demonstrate a competitive performance with 85% accuracy.