Performance Analysis of Image Forgery Detection using Transform Function and Machine Learning Algorithms
Main Article Content
Abstract
The image forgery process deformed the reputation of digital multimedia data in the era of internet technology. The availability of image editing software promotes the activity of image forgery. The action of forgery rise Ransome demands from the legitimate use of social media. The increasing rate of multimedia temptation changes the authenticity of data. Image forgery detection is a vital challenge for research scholars in the current decade. The forgery detection detects the location of forgery in the image and ensures the authentication of the picture. This paper represents the study of image forgery detection based on transform methods and machine learning. The transform methods have been great potential in image processing and pattern recognition. The various derivates of transform methods estimate the image forgery. The variants of transform include discrete wavelet transform, DCT, FFT, SIFT and many more transform. The applied transform methods have certain limitations and the detection of forged image compromised. The machine learning algorithm increases the detection ratio of image forgery. The trends of machine learning algorithms focus on image forgery detection and improve the detection ratio. Machine learning provides various classification and clustering algorithms for image forgery detection. This paper analyzed the experimental performance of image forgery detection based on transform and machine learning algorithms. The analysis process uses MATLAB tools and a standard image forgery dataset for the detection ratio. The analysis of results suggests that the machine learning algorithm is very efficient instead of transform-based methods.
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.