Signature Recognition and Verification Using Multiple Classifiers Combination of Hu’s and HOG Features | IEEE Conference Publication | IEEE Xplore

Signature Recognition and Verification Using Multiple Classifiers Combination of Hu’s and HOG Features


Abstract:

In this paper, an offline HSR and verification work has been carried out using Hu's invariant moment and HOG feature descriptor. In the HOG feature descriptor, the distri...Show More

Abstract:

In this paper, an offline HSR and verification work has been carried out using Hu's invariant moment and HOG feature descriptor. In the HOG feature descriptor, the distribution (histograms) of directions of gradients (oriented gradients) are used as features. Gradients (x and y derivatives) of an image are useful because the magnitude of gradients is large around edges and corners (regions of abrupt intensity changes).The Hu moments was used to characterize and quantify the shape of the HSR. This moment was used to calucate the centriod and orientation of the HSR. By using this local histogram features, the signature was divided into zones both the Cartesian and polar coordinate systems and two different histogram features are calculated for each zone. The fusion of all MC (global and user-dependent classifiers trained with each feature type), achieves a 15% equal error rate in skilled forgery test. As a result, a 98.33% percent test accuracy is obtained by using the proposed method.
Date of Conference: 26-28 August 2019
Date Added to IEEE Xplore: 11 October 2019
ISBN Information:

ISSN Information:

Conference Location: Kusatsu, Japan

References

References is not available for this document.