Rubens Campos Machado

Morphological Image Processing

Morphological processing (MP) has applications in diverse areas of image processing as filtering, segmentation, and pattern recognition, to both binary and grayscale images. One of the most important operations in morphological image processing is reconstruction from markers. The basic idea is to mark certain image components and then to reconstruct that portion of the image that contains the marked components. The basic fitting operation of morphology is the erosion of an image by a structuring element. Erosion is done by scanning the image with the structuring element. When the structuring element fits completely inside the object, the probe position is marked. The erosion result consists of all scanning locations, where the structuring element fits inside the object. The eroded image is usually a shrunken version of the image, and the shrinking effect is controlled by the structuring element size and shape. As an extension of the binary case, grayscale opening (closing) can be achieved simply by threshold decomposition, followed by binary opening (closing) and stack reconstruction. Grayscale opening and closing have the same properties as their binary equivalents.

Fingerprint Liveness Detection Using Convolutional Neural Networks

With the growing use of biometric authentication systems in the recent years, spoof fingerprint detection has become increasingly important. In this paper, we use convolutional neural networks (CNNs) for fingerprint liveness detection. Our system is evaluated on the data sets used in the liveness detection competition of the years 2009, 2011, and 2013, which comprises almost 50 000 real and fake fingerprints images. We compare four different models: two CNNs pretrained on natural images and fine-tuned with the fingerprint images, CNN with random weights, and a classical local binary pattern approach. We show that pretrained CNNs can yield the state-of-the-art results with no need for architecture or hyperparameter selection. Data set augmentation is used to increase the classifiers performance, not only for deep architectures but also for shallow ones. We also report good accuracy on very small training sets (400 samples) using these large pretrained networks. Our best model achieves an overall rate of 97.1% of correctly classified samples-a relative improvement of 16% in test error when compared with the best previously published results. This model won the first prize in the fingerprint liveness detection competition 2015 with an overall accuracy of 95.5%.

Adessowiki on-line collaborative scientific programming platform

Adessowiki (http://www.adessowiki.org) is a collaborative environment for development, documentation, teaching and knowledge repository of scientific computing algorithms. The system is composed of a collection of collaborative web pages in the form of a wiki. The articles of this wiki can embed programming code that will be executed on the server when the page is rendered, incorporating the results as figures, texts and tables on the document. The execution of code at the server allows hardware and software centralization and access through a web browser. This combination of a collaborative wiki environment, central server and execution of code at rendering time enables a host of possible applications like, for example: a teaching environment, where students submit their reports and exercises on Adessowiki without needing to install special software; authoring of texts, papers and scientific computing books, where figures are generated in a reproducible way by programs written by the authors; comparison of solutions and benchmarking of algorithms given that all the programs are executed under the same configuration; creation of an encyclopedia of algorithms and executable source code. Adessowiki is an environment that carries simultaneously documentation, programming code and results of its execution without any software configuration such as compilers, libraries and special tools at the client side.

A Comparison Between Extinction Filters and Attribute Filters

Attribute filters and extinction filters are connected filters used to simplify greyscale images. The first kind is widely explored in the image processing literature, while the second is not much explored yet. Both kind of filters can be efficiently implemented on the max-tree. In this work, we compare these filters in terms of processing time, simplification of flat zones and reduction of max-tree nodes. We also compare their influence as a pre-processing step before extracting affine regions used in matching and pattern recognition. We perform repeatability tests using extinction filters and attribute filters, set to preserve the same number of extrema, as a pre-processing step before detecting Hessian-Affine and Maximally Stable Extremal Regions (MSER) affine regions. The results indicate that using extinction filters as pre-processing obtain a significantly higher (more than 5% on average) number of correspondences on the repeatability tests than the attribute filters. The results in processing natural images show that preserving 5% of images extrema using extinction filters achieve on average 95% of the number of correspondences compared to applying the affine region detectors directly to the unfiltered images, and the average number of max-tree nodes is reduced by a factor greater than 3. Therefore, we can conclude that extinction filters are better than attribute filters with respect to preserving the number of correspondences found by affine detectors, while simplifying the max-tree structure. The use of extinction filters as a pre-processing step is recommended to accelerate image recognition tasks.

An array-based node-oriented max-tree representation

This paper presents an array-based node-oriented structure for the max-tree representation, which allows direct access and flexible manipulation of its nodes, and is more suitable for OpenMP parallel processing. The proposed structure is based on two arrays called node array (NA), which stores attributes of the nodes, and node index (NI), which indicates the node that each pixel belongs to. We compare it with the pixel-oriented max-tree representation based on a parent array (parent) and an ordering array (S) that allows tree traversals. We show that our max-tree representation requires less memory when the ratio between the number of image pixels and max-tree nodes is greater than 1.6, which is often the case. It is more flexible, and can compute some attributes, such as height and dynamics, with a complexity linear on the number of max-tree nodes instead of the number of image pixels. In our experiments our structure computed the height attribute on average 11.4 faster than the parent/S representation. Also, for a single area-open filter, the sequential implementation of our structure is on average 1.14 times slower and the parallel implementation in a 4-core CPU is 1.2 times faster than the parent/S structure. For an area-open filter followed by the hmax filter, our sequential implementation is 1.34 times faster and our parallel implementation is 2.32 times faster than the parent/S structure.

Interactive max-tree visualization tool for image processing and analysis

The max-tree is a data structure that represents all possible upper thresholds of an image, it has been successfully used in many image processing and analysis applications. The max-tree corresponding to a natural image usually has thousands of nodes, which makes unpractical to build a comprehensive graphical representation of its complete structure. In this paper, we propose a methodology that allows to build an interactive max-tree graphical representation that permits the user to navigate through the max-tree nodes, to visualize its connected components and to create node subsets. Our representation displays a simplified max-tree, but it allows the user to access all max-tree nodes using the interactive features. To the best of our knowledge, this is the first work that proposes an interactive graphical representation of the max-tree. We depict the potential of our max-tree visualization tool for interactive segmentation, connected filtering, and collection of training samples.

Maximal Max-Tree Simplification

The Max-Tree is an efficient data structure that represents all connected components resulting from all possible image upper threshold values. Usually, most of its nodes represent irrelevant extrema, i.e. noise, or small variations of a connected component. This paper proposes the Maximal Max-Tree Simplification (MMS) filter with a normalized threshold criterion (MMS-T) and a Maximally Stable Extremal Regions (MSER) criterion (MMS-MSER) and a methodology to apply them using the Extinction filter We show that after applying our simplification methodology which sets the number of maxima in the image, the number of Max-Tree nodes is at most twice this number. Two applications of the proposed methodology are illustrated.

Prontovideo: an image sequence segmentation tool applied to video edition

This work proposes an image sequence segmentation tool for video masking. It consist of a semi-automatic delineation tool of the object of interest, its segmentation, through the video sequence. The tool is based on the watershed by markers technique, where the markers are propagated from frame to frame using a normalized correlation pattern matching algorithm.

Adessowiki - Collaborative platform for writing executable papers

Abstract Adessowiki is a collaborative platform for scientific programming and document writing. It is a wiki environment that carries simultaneously documentation, programming code and results of its execution without any software con- figuration such as compilers, libraries and special tools at the client side. This combination of a collaborative wiki environment, central server and execution of code at rendering time enables the use of Adessowiki as an executable paper platform, since it fulfills the need to disseminate, validate, and archive research data.

A Max-Tree Simplification Proposal and Applications for the Interactive Max-Tree Visualization Tool

The max-tree is a data structure that represents hierarchically all connected components of an image. It is a powerful structure to perform image processing and analysis tasks. The interactive max-tree visualization tool was the first proposal of an interactive graphical representation for the max-tree, a tool that can be used to navigate, visualize and manipulate the max-tree nodes. In this paper, we propose a more meaningful simplification procedure for the max-tree, we extend the interactive max-tree visualization tool to work with 3D images and we propose the visualization of attributes, a new feature using the interactive max-tree that provides insight for the development of automatic methods.