The widespread use of digital images has led to a new challenge in digital image forensics. These images can be\nused in court as evidence of criminal cases. However, digital images are easily manipulated which brings up the\nneed of a method to verify the authenticity of the image. One of the methods is by identifying the source camera.\nIn spite of that, it takes a large amount of time to be completed by using traditional desktop computers. To tackle\nthe problem, we aim to increase the performance of the process by implementing it in a distributed computing\nenvironment. We evaluate the camera identification process using conditional probability features and Apache\nHadoop. The evaluation process used 6000 images from six different mobile phones of the different models and\nclassified them using Apache Mahout, a scalable machine learning tool which runs on Hadoop. We ran the source\ncamera identification process in a cluster of up to 19 computing nodes. The experimental results demonstrate\nexponential decrease in processing times and slight decrease in accuracies as the processes are distributed across\nthe cluster. Our prediction accuracies are recorded between 85 to 95% across varying number of mappers.
Loading....