Illumination-based texture descriptor and fruitfly support vector neural network for image forgery detection in face images

• Published in: IET image processing 2018-08, Vol.12 (8), p.1439-1449
• Main Authors: Cristin, Rajan, Ananth, John Patrick, Cyril Raj, Velankanni
• Format: Article
• Language: English
• Subjects: classifier; editing tools; edition; face images; face recognition; feature extraction; forgery detection scheme; fruit fly optimisation algorithm; fruitfly support vector neural network; Gabor filters; image classification; image forgery detection; image texture; learning (artificial intelligence); manipulation; neural nets; object detection; optimisation; pattern classification; remarkable interest; Research Article; supervised learning approach; support vector machines; texture descriptor; Viola–Jones algorithm; wavelet + texture operator
• ISSN: 1751-9659; 1751-9667; 1751-9667
• DOI: 10.1049/iet-ipr.2017.1120

Forgery detection from the images is gaining remarkable interest as there are a lot of editing tools that enable to cause edition with manipulation or removal of the objects from the images. This study proposes a new forgery detection scheme that is based on the supervised learning approach. The supervised learning is brought about by using the support vector neural network and the optimisation is enabled using the fruit fly optimisation algorithm. Initially, the images are fed to the texture descriptor and the face is detected using the Viola–Jones algorithm. The face detected images are subjected to the feature extraction using the Gabor filter + wavelet + texture operator and the features are concatenated to present the input to the classifier. Then, the classifier which is trained using the fruit fly optimisation classifies the features to detect the presence of the manipulation. The performance of the proposed scheme is evaluated with the existing methods for the evaluation metrics accuracy, sensitivity, and specificity using two datasets, namely DSO-1 and DSI-1. The analysis shows that the proposed scheme attained an accuracy of 0.9523, the sensitivity of 0.94, and the specificity of 0.9583, which are greater when compared to the existing methods.