Morphological Filter Detector for Image Forensics Applications

Abstract

Mathematical morphology provides a large set of powerful non-linear image operators, widely used for feature extraction, noise removal or image enhancement. Although morphological filters might be used to remove artifacts produced by image manipulations, both on binary and graylevel documents, little effort has been spent towards their forensic identification. In this paper we propose a non-trivial extension of a deterministic approach originally detecting erosion and dilation of binary images. The proposed approach operates on grayscale images and is robust to image compression and other typical attacks. When the image is attacked the method looses its deterministic nature and uses a properly trained SVM classifier, using the original detector as a feature extractor. Extensive tests demonstrate that the proposed method guarantees very high accuracy in filtering detection, providing 100% accuracy in discriminating the presence and the type of morphological filter in raw images of three different datasets. The achieved accuracy is also good after JPEG compression, equal or above 76.8% on all datasets for quality factors above 80. The proposed approach is also able to determine the adopted structuring element for moderate compression factors. Finally, it is robust against noise addition and it can distinguish morphological filter from other filters. INDEX TERMS Digital Image Forensics, media authentication, morphological filter detection.

Real-time Vehicle Surveillance System Based on Image Processing and Short Message Service

“…At this stage, the system will perform blob analysis on the residual image. Residual image will go through blob filtering, morphological operations [13], blob monitoring and draw boundaries around the blobs. Those steps are necessary for the system in order generate output that will be used in the warning generation stage.…”

Brain MR Image Enhancement using Average Intensity Replacement Based on GWOHE Algorithm

“…Therefore Skull-stripping is the most essential pre-processing stage [15] Meanwhile, skull stripping is performed in pre-processing stage to remove noise and to retain essential parts of brain such as GM (gray matter), CSF (cerebrospinal fluid) and WM (white matter). The entire process involves morphological operations such as binarization, erosion followed by dilation and filling [18] [19]. Binarization and erosion are used to isolate attached regions of the outer skull.…”

“…Determine the fitness value of each search agents α, β and δ, is estimating approximate possible position of prey. α , β and are three coefficents of optimization and given in form of equations as below, (18) (19) Where, and are prey and wolf position vectors, respectivily. iv.…”

Morphological Texture Description For Hyperspectral Images: Pattern Spectrum

“…It has been widely known mostly for its elementary operators, e.g., erosion-dilation and opening-closing pairs, or segmentation tools, e.g., watershed and skeletonization. While they are useful and can be found at the core of many image processing and analysis solutions [1,2,3], MM also provides a set of tools capable of dealing with textures such as granulometry or, its derivative form, pattern spectrum [4].…”