Anselmo Ferreira

Going deeper into copy-move forgery detection

We have developed a new and effective approach to detect copy-move forgeries.Our method is able to deal with rotations, resize and compression simultaneously.Our method report a small false positive rate detection.We have developed a dataset comprising 216 realistic copy-move forgeries.Method tested against 15 state-of-the-art methods and using different datasets. This work presents a new approach toward copy-move forgery detection based on multi-scale analysis and voting processes of a digital image. Given a suspicious image, we extract interest points robust to scale and rotation finding possible correspondences among them. We cluster correspondent points into regions based on geometric constraints. Thereafter, we construct a multi-scale image representation and for each scale, we examine the generated groups using a descriptor strongly robust to rotation, scaling and partially robust to compression, which decreases the search space of duplicated regions and yields a detection map. The final decision is based on a voting process among all detection maps. We validate the method using various datasets comprising original and realistic image clonings. We compare the proposed method to 15 others from the literature and report promising results.

Behavior Knowledge Space-Based Fusion for Copy–Move Forgery Detection

The detection of copy-move image tampering is of paramount importance nowadays, mainly due to its potential use for misleading the opinion forming process of the general public. In this paper, we go beyond traditional forgery detectors and aim at combining different properties of copy-move detection approaches by modeling the problem on a multiscale behavior knowledge space, which encodes the output combinations of different techniques as a priori probabilities considering multiple scales of the training data. Afterward, the conditional probabilities missing entries are properly estimated through generative models applied on the existing training data. Finally, we propose different techniques that exploit the multi-directionality of the data to generate the final outcome detection map in a machine learning decision-making fashion. Experimental results on complex data sets, comparing the proposed techniques with a gamut of copy-move detection approaches and other fusion methodologies in the literature, show the effectiveness of the proposed method and its suitability for real-world applications.

Laser printer attribution: Exploring new features and beyond

With a huge amount of printed documents nowadays, identifying their source is useful for criminal investigations and also to authenticate digital copies of a document. In this paper, we propose novel techniques for laser printer attribution. Our solutions do not need very high resolution scanning of the investigated document and explore the multidirectional, multiscale and low-level gradient texture patterns yielded by printing devices. The main contributions of this work are: (1) the description of printed areas using multidirectional and multiscale co-occurring texture patterns; (2) description of texture on low-level gradient areas by a convolution texture gradient filter that emphasizes textures in specific transition areas and (3) the analysis of printer patterns in segments of interest, which we call frames, instead of whole documents or only printed letters. We show by experiments in a well documented dataset that the proposed methods outperform techniques described in the literature and present near-perfect classification accuracy being very promising for deployment in real-world forensic investigations.

Convolutional Neural Network approaches to granite tiles classification

Abstract The quality control process in stone industry is a challenging problem to deal with nowadays. Due to the similar visual appearance of different rocks with the same mineralogical content, economical losses can happen in industry if clients cannot recognize properly the rocks delivered as the ones initially purchased. In this paper, we go toward the automation of rock-quality assessment in different image resolutions by proposing the first data-driven technique applied to granite tiles classification. Our approach understands intrinsic patterns in small image patches through the use of Convolutional Neural Networks tailored for this problem. Experiments comparing the proposed approach to texture descriptors in a well-known dataset show the effectiveness of the proposed method and its suitability for applications in some uncontrolled conditions, such as classifying granite tiles under different image resolutions.

Automatic Tracking of Indoor Soccer Players Using Videos from Multiple Cameras

Indoor soccer has been of tactical and scientific interest, with applications dedicated to analyze tactical and physiological factors and also physical training. In both cases, the analysis is based on player tracking, done with human supervision. This paper presents an automatic tracking method which shows the trajectories of indoor soccer players during the game and saving skilled labor during the process. For this, we use a predictive filter to model the motion and the observation of multiple stationary cameras, strategically positioned around the court. We associate a particle filter to a robust probabilistic observation model with the measurement in court coordinates. The observation model proposed is based on data fusion across multiple camera coordinates and projected onto the court plane, creating a multimodal and bidirectional probability function, which represents the potential localization of players in the court plane. The probability function uses an appearance model to observe players location, distinguishing very close players and yielding good weights in the observation model. The experimental results show tracking errors below 70 centimeters in most cases and indicate the potential of the method to help sports teams.

Image segmentation using quadtree-based similarity graph and normalized cut

The graph cuts in image segmentation have been widely used in recent years because it regards the problem of image partitioning as a graph partitioning issue, a well-known problem in graph theory. The normalized cut approach uses spectral graph properties of the image representative graph to bipartite it into two or more balanced subgraphs, achieving in some cases good results when applying this approach to image segmentation. In this work, we discuss the normalized cut approach and propose a Quadtree based similarity graph as the input graph in order to segment images. This representation allow us to reduce the cardinality of the similarity graph. Comparisons to the results obtained by other graph similarity representation were also done in sampled images.

Data-Driven Feature Characterization Techniques for Laser Printer Attribution

Laser printer attribution is an increasing problem with several applications, such as pointing out the ownership of crime proofs and authentication of printed documents. However, as commonly proposed methods for this task are based on custom-tailored features, they are limited by modeling assumptions about printing artifacts. In this paper, we explore solutions able to learn discriminant-printing patterns directly from the available data during an investigation, without any further feature engineering, proposing the first approach based on deep learning to laser printer attribution. This allows us to avoid any prior assumption about printing artifacts that characterize each printer, thus highlighting almost invisible and difficult printer footprints generated during the printing process. The proposed approach merges, in a synergistic fashion, convolutional neural networks (CNNs) applied on multiple representations of multiple data. Multiple representations, generated through different pre-processing operations, enable the use of the small and lightweight CNNs whilst the use of multiple data enable the use of aggregation procedures to better determine the provenance of a document. Experimental results show that the proposed method is robust to noisy data and outperforms existing counterparts in the literature for this problem.

A Multiscale and Multi-Perturbation Blind Forensic Technique For Median Detecting

This paper aims at detecting traces of median filtering in digital images, a problem of paramount importance in forensics given that filtering can be used to conceal traces of image tampering such as resampling and light direction in photomontages. To accomplish this objective, we present a novel approach based on multiple and multiscale progressive perturbations on images able to capture different median filtering traces through using image quality metrics. Such measures are then used to build a discriminative feature space suitable for proper classification regarding whether or not a given image contains signs of filtering. Experiments using a real-world scenario with compressed and uncompressed images show the effectiveness of the proposed method.

Multi-directional and multi-scale perturbation approaches for blind forensic median filtering detection

The forensic detection of median filtering has recently attracted the attention of the research community, mainly because of the median filtering potential uses for tampering and concealing image tampering traces in digital images. In this paper, we propose multi-scale and multi-perturbation solutions that build a highly discriminative feature space, which highlights the artifacts of median filtering by means of image quality measures. The proposed methods achieve promising results when validated with a series of real-world test cases, comprising different image compression levels, resolutions, and also a cross-dataset validation protocol.