• Surinder Pal Kaur

Fraud detection is critical from the facial images. This paper presents a noval approach using presentation attack detection(PAD) mechanism for the detection of frauds from the image dataset. To detect the frauds Yale dataset is used. Pre-processing of the images is done using the linear learning color enhancement mechanism. For the purpose of classification neural network is used. The classification result will either be normal or abnormal images. The cumulative density function is applied to obtain the frauds using the fractions fetched from classification phase. Result in terms of false matching rate and false non matching rate is presented that is 0.489 and 0.455. Hybridized PAD with neural network produces better result as compared to plan PAD approach and factor for improvement is 2%.

PAD, Neural network, linear learning color enhancement, FMR, FNMR

"ENHANCED PAD NEURAL BASED APPROACH FOR FORGERY DETECTION IN IMAGES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.80-84, May-2019, Available :http://www.jetir.org/papers/JETIR1905C13.pdf

"ENHANCED PAD NEURAL BASED APPROACH FOR FORGERY DETECTION IN IMAGES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp80-84, May-2019, Available at : http://www.jetir.org/papers/JETIR1905C13.pdf