Taxonomy of file fragments using Gray-Level Co-Occurrence Matrices

Researches up to data have focused on using non texture based methods in addressing the problem of classifying the data types of file fragments. In this research we considered a file fragment as a 8 bit grayscale image and the Gray Level Co-Occurrence Matrix (GLCM) based method was used to extract textural features. Texture features for fragment dimensions 8 × 8, 16 × 16, 32 × 32 and 64 × 64 and gray level quantizations from 4 to 64 with step increments of 4 were explored. The K nearest neighbor classifier was used as the classifier and the optimal GLCM features for a particular gray level and fragment dimension were determined using Sequential Forward Selection (SFS) algorithm. On the classification of 7 data types, our novel approach reached a maximum overall accuracy of 86.86% in classifying 64 × 64 sized fragments with 12 gray levels.