R. De Alencar Lotufo

Novel automatic PCB inspection technique based on connectivity

This paper presents a novel technique for PCB inspection based on the comparison of the Connected Table of a Reference and a Test Image. The method is based on connected component analysis, which is a natural way to extract the connectivity information of the conductors of a PCB. The registration of the PCB holes, which is a common problem related to referential model techniques, is solved by the concept of zone of influence of each hole. This paper describes the method and its implementation using standard Morphology Image Processing techniques. A result of applying the technique to real images is shown.

Classification of the distance transformation algorithms under the mathematical morphology approach

The distance transform (DT) is a morphological erosion of the binary image by a given structuring function, that dictates the distance metric in the transformation. There are many known algorithms and structuring function decompositions to efficiently implement a morphological erosion. Most of the erosion algorithms are classified as parallel, sequential raster (and anti-raster), and propagation. Based on this classification and decomposition, we review and classify most of the DT algorithms reported in the literature. As a result of this study, we have contributed not only to better classify and understand the diversity of the DT algorithms in the literature, but also to create a collection of efficient erosion algorithms suitable to different computer architectures.The distance transform (DT) is a morphological erosion of the binary image by a given structuring function, that dictates the distance metric in the transformation. There are many known algorithms and structuring function decompositions to efficiently implement a morphological erosion. Most of the erosion algorithms are classified as parallel, sequential raster (and anti-raster), and propagation. Based on this classification and decomposition, we review and classify most of the DT algorithms reported in the literature. As a result of this study, we have contributed not only to better classify and understand the diversity of the DT algorithms in the literature, but also to create a collection of efficient erosion algorithms suitable to different computer architectures.

New Extinction Values from Efficient Construction and Analysis of Extended Attribute Component Tree

A gray-level image can be interpreted as a topographical surface, and represented by a component tree, based on the inclusion relation of connected components obtained by threshold decomposition. Relations between plateaus, valleys or mountains of this relief are useful in computer vision systems. An important definition to characterize the topographical surface is the dynamics, introduced by Grimaud (1992), associated to each regional minimum. This concept has been extended, by Vachier and Meyer (1995), by the definition of extinction values associated to each extremum of the image. This paper proposes four new extinction values -- two based on the topology of the component tree: (i) number of descendants and (ii) sub-tree height; and two geometric: (iii) height and (iv) width of a level component bounding box. This paper describes efficient computation of these extinction values based on the incremental determination of attributes from the component tree construction in quasi-linear time, compares the computation time of the method and illustrates the usefulness of these new extinction values from real examples.

Classification of microstructures by morphological analysis and estimation of the hydration degree of cement paste in concrete

Cement is an essential material for the development of the civil construction. The analysis of cement-based materials is useful in the evaluation of mechanical properties, water absorption, air permeability and evolution of hydration degree. The latter is the motivation of this paper. New advantageous techniques of analysis based on the image information are possible using electronic microscopy. We propose here an alternative procedure to the segmentation of microstructures of cement and aggregates in concrete. The central idea consists of a particular use of the morphological operator watershed. We report the results of the analysis of about 450 scanning electron microscope (SEM) images.

Toolbox of image processing for numerical Python

This work consists of the study, development and implementation of an image processing toolbox for the Python language. This environment will be useful in education, research and the development of final applications. The toolbox will be developed using the facilities of the Adesso project for the development of software for scientific computation.

Object segmentation in image sequences by watershed from markers: a generic approach

We propose a generic method to interactive object segmentation in image sequences. This method consists in the extension of efficient techniques of static image segmentation to image sequences by combining them to fast motion estimation techniques. The proposed method has the following characteristics: interactivity, generality, rapid response and progressive manual edition.

Image segmentation by analysis of scale-space

We present a technique in image segmentation based on a hierarchical analysis of scale-space. The image hierarchy is a tree of critical lakes and provides a set of nested partitions. We analyze the scale-space from fine to coarse levels according to specific attributes.

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.

Morphological operators characterized by neighborhood graphs

Mathematical Morphology is a theory that studies the decomposition of lattice operators in terms of some families of elementary lattice operators. When the lattices considered have a sup-generating family, the elementary operators can be characterized by structuring functions. The representation of structuring functions by neighborhood graphs is a powerful model for the construction of image operators. This model, that is a conceptual improvement of the one proposed by Vincent, permits a natural polymorphic extension of classical softwares for image processing by Mathematical Morphology. These systems constitute a complete framework for implementations of connected filters, that are one of the most modern and powerful approaches for image segmentation, and of operators that extract information from populations of objects in images. In this paper, besides presenting the formulation of the model, we present the polymorphic extension of a system for morphological image processing and some applications of it in image analysis.

Hierarchical regions matching in image sequences through association graph

We present a hierarchical method to match regions in image sequences based in graph theory. First, we build a graph representation for each image, the so-called tree of critical lakes, used in the multiscale watershed. In a second step, assignments between regions in subsequent images are accomplished through maximum clique detection in a association graph.We present a hierarchical method to match regions in image sequences based in graph theory. First, we build a graph representation for each image, the so-called tree of critical lakes, used in the multiscale watershed. In a second step, assignments between regions in subsequent images are accomplished through maximum clique detection in a association graph.