Multiwavelet transform and multi-dimension-two activation function wavelet network using for person identification

Abstract EN

The relatively new field of Multiwavelet shows promise in removing some of the limitations of wavelets.

This paper introduces a new human face recognition using the combination of Multiwavelet transform (MWT) and multidimensional-Two Activation Function Wavelet Network (MD-TAFWN).

After taking the MWT of the image, it is required to divide the approximate quarter into four parts and rearrange them in 3D form.

Next, this 3D data will be fed into a proposed MD-Two Activation Function Wavelet Network.

This is for face image.

For the fingerprint image, it is required to divide the approximate quarter into four parts and rearrange them in 3D form.

Next, this 3D data will be fed into a proposed MD-Two Activation Function Wavelet Network.

The proposed transform is considered as a feature extractor of the decomposed reference images with different frequency sub bands, and amid-range frequency sub band for data image to the representation of the given image.

Evaluations have generally shown that the technique of the combination for Discrete Multi-wavelet Transform (DMWT) and the Two Activation Function Wavelet Network (MD-TAFWN) is interesting and promising.

The results obtained showed that the combination technique outperformed.

Other conventional methods that use a given transform with neural Network (NN).

It results in a perfect recognition of 100 % to a data base which consists of 100 human face images.