Evaluation of wavelet transform preprocessing with deep learning aimed at palm vein recognition application

There are many medical equipments being used by human as assistance to check some organs inside the body. The medical modalities are developed to obtain the most effective and efficient in terms of quality and cost. Research about infrared spectrum as the medical equipment is a highlight among scientists since it can be captured the blood vessel of humans. Infrared penetrates the human skin and be captured by camera. Vein has a pattern and it can be used as human identification system. However, the images need enhancement because of low contrast. Wavelet transforms such as Haar and Daubechies can enhance the quality of vein images. Hence the identification process can be conducted by using deep learning method. In this paper, we use one of convolutional neural networks (CNN) method called AlexNet structure as the deep learning method due to its high performance. As for the wavelet transforms, the Haar wavelet, Daubechies 2, Daubechies 4, and Daubechies 10 are selected for evaluation on palm vein images in the image preprocessing step. As a result, we found that the accuracy of the wavelet transforms and enhanced palm vein images are more than 92%. The highest accuracy can be achieved by applying Daubechies 10 wavelet transform with an accuracy of 93.92%±0.98334.