Image enhancement is a fundamental preprocessing step for many automated systems and vision systems. Many enhancement algorithms have been anticipated based on different sets of criteria. One of the most widely used algorithms is the direct multi-scale image enhancement algorithm. The specialty of this algorithm is, it provides contrast enhancement, tonal rendition, dynamic range compression and accurate edge preservation of the images. It also provides these features to the individual images and/or simultaneously to the images. In this proposed method, a multi-scale image enhancement algorithm is established by using parametric contrast measure with the transform techniques such as Laplacian pyramid, discrete wavelet transform, Stationary wavelet transform and Dual-tree complex wavelet transform. The new contrast measure provides both the luminance and contrast masking characteristics of the human visual system. The proposed method is used to attain simultaneous local and global enhancements. The enhancement measures such as Entropy, Mean opinion score and Measure of enhancement gives better results than the existing methods.

Facial recognition is an important human ability; an infant innately responds to face shapes at birth and can discriminate his or her mother's face from strangers at the tender age of 45hours. Recognizing and identifying people is a vital survival skill, as is reading faces for evidence of ill health or deception. Improving significantly in the last several years ,technologies that can mimic or improve human abilities to recognize and read faces are now maturing for use in medical and security applications, and also face recognition is a billion dollar industry companies like Google photos(Google), Facebook, Flickr, Instagram, Photo bucket, iCloud photo library(Apple) are extensively using face recognition for identifying particular person, for grouping pictures of same person, and also for facial expression analysis. However, face recognition is a complex process, it includes challenges like illumination, pose, angle, noise, and even expressions, which make face recognition tedious process.