Valentín Osuna

White Blood Cells Detection in Images

As a research area, there are several problems in medical imaging that continue unresolved; one of those is the automatic detection of white blood cells (WBC) in smear images. The study of this kind of images has engaged researchers from fields of medicine and computer vision alike. Several studies have been done to try to approximate this cells with circular or ellipsoid forms; once detected, those cells can be further processed by computer vision systems. In this chapter, detection of WBC in smear digitalized images is achieved by using evolutionary algorithms, with an objective function that considers that since WBC can be approximated by an ellipsoid form, an ellipse detector algorithm may be successfully applied in order to recognize them. In that sense, the optimization problem also consider that a candidate solution is a probable ellipse that could adjust a WBC in the image.

Parameter Identification of Induction Motors

The efficient use of electrical energy is a topic that has attracted attention for its environmental consequences. On the other hand, induction motors represent the main component in most of the industries. They consume the highest energy percentages in industrial facilities. This energy consumption depends on the operation conditions of the induction motor imposed by its internal parameters. Since the internal parameters of an induction motor are not directly measurable, an identification process must be conducted to obtain them. In the identification process, the parameter estimation is transformed into a multidimensional optimization problem where the internal parameters of the induction motor are considered as decision variables. Under this approach, the complexity of the optimization problem tends to produce multimodal error surfaces for which their cost functions are significantly difficult to minimize. Several algorithms based on evolutionary computation principles have been successfully applied to identify the optimal parameters of induction motors. However, most of them maintain an important limitation, they frequently obtain sub-optimal solutions as a result of an improper equilibrium between exploitation and exploration in their search strategies. This chapter presents an algorithm for the optimal parameter identification of induction motors. To determine the parameters, the presented method uses a recent evolutionary method called the Gravitational Search Algorithm (GSA). Different to the most of existent evolutionary algorithms, GSA presents a better performance in multimodal problems, avoiding critical flaws such as the premature convergence to sub-optimal solutions. Numerical simulations have been conducted on several models to show the effectiveness of the presented scheme.

Multilevel Segmentation in Digital Images

Segmentation is used to divide an image into separate regions, which in fact correspond to different real-world objects. One interesting functional criterion for segmentation is the Tsallis entropy (TE), which gives excellent results in bi-level thresholding. However, when it is applied to multilevel thresholding (MT), its evaluation becomes computationally expensive, since each threshold point adds restrictions, multimodality and complexity to its functional formulation. In this chapter, a new algorithm for multilevel segmentation based on the Electromagnetism-Like algorithm (EMO) is presented. In the approach, the EMO algorithm is used to find the optimal threshold values by maximizing the Tsallis entropy. Experimental results over several images demonstrate that the proposed approach is able to improve the convergence velocity, compared with similar methods such as Cuckoo search, and Particle Swarm Optimization.

Photovoltaic Cell Design

In order to improve the performance of solar energy systems, accurate modeling of current versus voltage (I–V) characteristics of solar cells has attracted the attention of various researches. The main drawback in accurate modeling is the lack of information about the precise parameter values which indeed characterize the solar cell. Since such parameters cannot be extracted from the datasheet specifications, an optimization technique is necessary to adjust experimental data to the solar cell model. Considering the I–V characteristics of solar cells, the optimization task involves the solution of complex non-linear and multi-modal objective functions. Several optimization approaches have been presented to identify the parameters of solar cells. However, most of them obtain sub-optimal solutions due to their premature convergence and their difficulty to overcome local minima in multi-modal problems. This chapter describes the use of the Artificial Bee Colony (ABC) algorithm to accurately identify the solar cells’ parameters. The ABC algorithm is an evolutionary method inspired by the intelligent foraging behavior of honeybees. In comparison with other evolutionary algorithms, ABC exhibits a better search capacity to face multi-modal objective functions. In order to illustrate the proficiency of the presented approach, it is compared to other well-known optimization methods. Experimental results demonstrate the high performance of the presented method in terms of robustness and accuracy.

Multi-circle Detection on Images

Hough transform (HT) represents the most common method for circle detection, exhibiting robustness and parallel processing. However, HT adversely demands a considerable computational load and large storage. Alternative approaches may include heuristic methods with iterative optimization procedures for detecting multiple circles. In this chapter a new circle detector for image processing is presented. In the approach, the detection process is therefore assumed as a multi-modal problem which allows multiple circle detection through only one optimization procedure. The algorithm uses a combination of three non-collinear edge points as parameters to determine circles candidates. A matching function (nectar amount) determines if such circle candidates (bee-food-sources) are actually present in the image. Guided by the values of such matching function, the set of encoded candidate circles are evolved through the Artificial Bee Colony (ABC) algorithm so the best candidate (global optimum) can be fitted into an actual circle within the edge-only image. An analysis of the incorporated exhausted-sources memory is executed in order to identify potential local optima i.e. other circles. The overall approach yields a fast multiple-circle detector that locates circular shapes delivering sub-pixel accuracy despite complicated conditions such as partial occluded circles, arc segments or noisy images.

Estimation of View Transformations in Images

Computer vision process frequently include an modeling step whose parameters, obtained from a data set, are not easy to calculate due mainly to the presence of a high proportion of outliers. The most known method to overcome this problem is the random sampling consensus (RANSAC). Such technique, in combination with Harmony Search (HS), are used in this chapter for a robust estimation of multiple view relations from point correspondences in digital images. By using this evolutionary technique, the estimation method endorse a different sampling strategy to generate putative solutions: on one hand, RANSAC generate new candidate solutions in a random fashion; on the other hand, by using HS in combination with RANSAC, each new candidate solution is generated by considering the quality of previous candidate solutions. In other words, the solutions space is searched in an intelligent manner. The HS algorithm is inspired by the improvisation process of an orchestra that takes place when musicians search for a better state of harmony; as a result, the HS-RANSAC can substantially reduce the number of iterations still preserving the robust capabilities of RANSAC. The method is used in this chapter to solve the estimation of homographies, with an engineering application to solve the problem of position estimation in a humanoid robot. In this chapter, seven techniques are compared for the problem of robust homography estimation.

Fast Circle Detection Using Harmony Search Optimization

Automatic circle detection in digital images has received considerable attention over the last years. Recently, several robust circle detectors, based on evolutionary algorithms (EA), have been proposed. They have demonstrated to provide better results than those based on the Hough Transform. However, since EA-detectors usually need a large number of computationally expensive fitness evaluations before a satisfying result can be obtained; their use for real time has been questioned. In this work, a new algorithm based on the Harmony Search Optimization (HSO) is proposed to reduce the number of function evaluation in the circle detection process. In order to avoid the computation of the fitness value of several circle candidates, the algorithm estimates their values by considering the fitness values from previously calculated neighboring positions. As a result, the approach can substantially reduce the number of function evaluations preserving the good search capabilities of HSO. Experimental results from several tests on synthetic and natural images with a varying complexity range have been included to validate the efficiency of the proposed technique regarding accuracy, speed and robustness.