Advances in photo editing software have made it possible to generate visually convincing photographic forgeries which have been increased tremendously in recent years.In order to alleviate the problem of image forgery,a handful of techniques have been presented in the literature to detect forgery either in shadow or reflection.This paper aims to develop a technique to detect the image forgery either in shadow or reflection using features enabled neural network.The proposed technique of image forgery detection contains three important steps,like segmentation,feature extraction and detection.In segmentation,shadow points and reflection points are identified using map-based segmentation and FCM clustering.Then,feature points from the shadow points and reflective parts are extracted by considering texture consistency and strength consistency using LVP operator.The final step of forgery detection is performed using the feed forward neural network,where a new algorithm called ABCLM is developed for training of neural network weights.The performance is analyzed with four existing algorithms using measures such as accuracy and MSE.From the analysis,we understand that the proposed technique obtained the maximum accuracy of 80.49％.