Jorge D. Mendiola-Santibañez

Morphological Background Detection and Enhancement of Images With Poor Lighting

In this paper, some morphological transformations are used to detect the background in images characterized by poor lighting. Lately, contrast image enhancement has been carried out by the application of two operators based on the Webers law notion. The first operator employs information from block analysis, while the second transformation utilizes the opening by reconstruction, which is employed to define the multibackground notion. The objective of contrast operators consists in normalizing the grey level of the input image with the purpose of avoiding abrupt changes in intensity among the different regions. Finally, the performance of the proposed operators is illustrated through the processing of images with different backgrounds, the majority of them with poor lighting conditions.

Morphological contrast measure and contrast enhancement: One application to the segmentation of brain MRI

In this paper a morphological contrast measure is introduced. The quantification of the contrast is based on the analysis of the edges, which are associated with substantial changes in luminance. Due to this, the contrast measure is used to detect the image that presents a high visual contrast when a set of output images is analyzed. The set of output images is obtained by application of morphological contrast mappings with size criteria. These contrast transformations are defined under the notion of partitions generated by the set of flat zones of the image; therefore, they are connected transformations. In addition, an application to the segmentation of white and grey matter in brain magnetic resonance images (MRI) is provided. The detection of white matter is carried out by means of a contrast mapping with specific control parameters; subsequently, white and grey matter are separated and their ratio is calculated and compared with manual segmentations. Also, an example of segmentation of white and grey matter in MRI corrupted by 5% noise is presented in order to observe the performance of the morphological transformations proposed in this work.

Morphological Connected Filtering on Viscous Lattices

This paper deals with the notion of connectivity in viscous lattices. In particular, a new family of morphological connected filters, called connected viscous filters is proposed. Connected viscous filters are completely determined by two criteria: size parameter and connectivity. The connection of these filters is defined on viscous lattices in such a way that they verify several properties of the traditionally known filters by reconstruction. Moreover, reconstruction algorithms used to implement filters by reconstruction can also be employed to implement these new filters. We also show that connected viscous filters have a behavior similar to filters with reconstruction criteria. The interest of these new connected filters is illustrated with different examples.

Image segmentation and filtering based on transformations with reconstruction criteria

In this paper, a class of transformations with reconstruction criteria, derived from the reconstruction transformations, is investigated. The idea to build these transformations consists in stopping the reconstruction process according to a size criterion. This class of transformations was initially proposed for obtaining intermediate results between the morphological opening and the opening by reconstruction. Here, the transformations are presented in the general case, as in the reconstruction transformations case, by imposing some conditions on the marker. We show that the set of markers for the transformations with reconstruction criteria is given by the set of dilated images. The interest of these transformations in image segmentation is shown, and in particular, the form of selecting the markers for segmenting images is described for binary images. Also, the use of the opening and closing with reconstruction criteria to build other morphological tools is illustrated to show the performance of these transformations. In particular, the notion of granulometry and the alternating sequential filters using openings and closings with reconstruction criteria are investigated.

Filtering of mixed Gaussian and impulsive noise using morphological contrast detectors

Several morphological transformations to detect noise are introduced. The initial method is a modification of a procedure presented previously in the current literature. The proposals given in the study allow to detect noise in two ways: (i) using a contrast measure and (ii) applying different proximity criteria into several proposed toggle mappings. In the end, two of the proposals given in this study yield a better performance with respect to methods in which this research is based. However, although the methodology to identify noise works adequately, the results are limited due to the use of the structuring element. In Section 4, an image with two types of noise is cleaned. Such image is contaminated with zero mean Gaussian noise with 0.01 variance and 5% of salt and pepper noise. From this experiment, the proposal giving the best performance is selected; subsequently, this is compared with other recent operators as PDEs, wavelets, morphological connected rank max opening and amoebas.

A PC-based architecture for parameter analysis of vector-controlled induction motor drive

In this article a methodology for constructing a user interface for system control and data acquisition of a drive which is suitable for three-phase induction motors ([emailxa0protected]) is presented. The entire hardware implementation is shown, including power and digital stages. Communication between the computer and the controller is engaged in order to enhance an analysis of power quality, adjust the controller parameters for tuning the flux and speed loops, and performance of the embedded algorithm. USB and Ethernet protocols have been put into operation in the user front-end because a high speed sample frequency is required in order to guarantee the real-time operation of the whole system. A software interface is developed using LabVIEW environment enabling features not only as filtering signals of phase voltage and current but also power spectrum measurements. Vector-controlled drive is programmed on a digital signal processor (DSP) in order to ensure efficient use of energy in the power stage and proper tracking of the reference at low and high speeds.

Application of morphological connected openings and levelings on magnetic resonance images of the brain

In this article, several advanced connected transformations from mathematical morphology for computational neuroanatomy applications are developed. In particular, brain is separated from the skull in MRI T1 using morphological connected openings. The use of connected transformations allow the preservation of regions, without introduce new information. As a result, the segmented brains preserve by complete information of the original images being more reliable for the specialist who deals with information such as white and gray matter.

Image Segmentation Based on Transformations with Reconstruction Criteria

In this paper, a class of transformations with reconstruction criteria is investigated. This class of transformations was initially proposed for obtaining intermediate results between the morphological opening and the opening by reconstruction. Here, the transformations are presented in the general case, as in the reconstruction transformations case, by imposing some conditions on the marker. The form of selecting the markers to build these transformations is particularly described for binary images. Since the transformations studied in this work use a reconstruction criterion, we illustrate how it can be modified in order to have a better control of the output image. Finally, the interest of these transformations in image segmentation is also shown.

Review: Morphological multiscale fingerprints from connected transformations

In this paper a multiscale study based on the use of morphological connected transformations is presented. In particular, the morphological opening and closing by reconstruction are used as connected transformations. These transformations have the characteristic of preserving contours without introducing new information, in addition to smoothing the processed image as the size of the structuring element increases. Due to this, both connected filters and the identity are used as primitives to introduce two operators that allow a multiscale treatment to the processed image in accordance with the scale parameter. The multiscale morphological operators are called opening-closing by reconstruction and closing-opening by reconstruction, respectively. In the case of the opening-closing by reconstruction transformation, the propagation of extrema when the structuring element enlarges has an interesting behavior. In addition, the fingerprints of the image given as a function of regional maxima, regional minima and scale parameter are defined. Finally, the proposals of this work are illustrated with some examples.

Sequential application of viscous opening and lower leveling for three-dimensional brain extraction on magnetic resonance imaging T1

Abstract. A composition of the viscous opening and the lower leveling is introduced to extract brain in magnetic resonance imaging T1. The innovative transformation disconnects chained components and has better control on the reconstruction process of the marker inside of the original image. However, the sequential operator requires setting several parameters, making its application difficult. Due to this situation, a simplification is carried out on it to obtain a more practical method. The proposed morphological transformations were tested with the Internet Brain Segmentation Repository (IBSR) database, which is used as a benchmark among the community. The results are compared using the Jaccard and Dice indices with respect to (i) manual segmentations obtained from the IBSR, (ii) mean indices reported in the current literature, and (iii) segmentations obtained from the Brain Extraction Tool, since this is one of the most popular algorithms used for brain segmentation. The average indices of Jaccard and Dice indicate that the reduced transformation produces similar results to the other methods reported in the literature while the sequential operator presents a better performance.