Abstract
Image manipulation has no longer been rocket science for non-professionals. Tampering of images has become so popular due to the accessibility of free editing application in smart phone’s store, these applications work without any agreement or license from the user which makes the condition more vulnerable. The image alteration is not limited to the smart phone’s applications, they can be done online without downloading and signing in the application making the scenario even worst. These forged images are so tricky that they are not predictable with bare human eyes. So, in order to tackle with this delinquent act, one must develop such system which can instantly discriminate between the unique and altered image. One of the best technologies that can tackle the problem and helps to develop such a scheme is Machine learning. There are several classification techniques based on the requirement of the system that can be applied to the data set, resulting in the classification of images under the groups forged and unforged images. In this work, we have discussed the images which are being forged using Image splicing Technique, in which the region of an original image is cropped and pasted onto the other original image. In this paper, a machine learning classification technique logistic regression has been used to classify images into two classes, spliced and non-spliced images. For this, a combination of four handcrafted features has been extracted from images for feature vector. Then these feature vectors are trained using logistic regression classification model. 10-fold cross-validation test evaluation procedure has been used to evaluate the result. Finally, the comparative analysis of the proposed method with other state-of-the-art methods on three online available datasets is presented in the paper. It is observed that the obtained results perform better than state-of-the-art methods.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.