Multi-ellipses detection on images inspired by collective animal behavior

Abstract

This paper presents a novel and effective technique for extracting multiple ellipses from an image. The approach employs an evolutionary algorithm to mimic the way animals behave collectively assuming the overall detection process as a multi-modal optimization problem. In the algorithm, searcher agents emulate a group of animals that interact to each other using simple biological rules which are modeled as evolutionary operators. In turn, such operators are applied to each agent considering that the complete group has a memory to store optimal solutions (ellipses) seen so-far by applying a competition principle. The detector uses a combination of five edge points as parameters to determine ellipse candidates (possible solutions) while a matching function determines if such ellipse candidates are actually present in the image. Guided by the values of such matching functions, the set of encoded candidate ellipses are evolved through the evolutionary algorithm so that the best candidates can be fitted into the actual ellipses within the image. Just after the optimization process ends, an analysis over the embedded memory is executed in order to find the best obtained solution (the best ellipse) and significant local minima (remaining ellipses). Experimental results over several complex synthetic and natural images have validated the efficiency of the proposed technique regarding accuracy, speed and robustness.

Comparison of Recent Metaheuristic Algorithms for Shape Detection in Images

“…where A 1 , A 2 , A 3 , C 1 , C 2 and C 3 are fixed coefficients computed by using Eqs. (12) and (13). Once computed these elements, the position in the next iteration (k + 1) of each candidate solution p is adapted as follows:…”

“…Therefore, conducted by the values of the matching function, the set of encoded points are operated through a particular metaheuristic approach so that the best solutions represent the original shapes inside the image. Different pioneer metaheuristic algorithms have been used to produce several interesting shape detectors such as Genetic algorithms (GAs) [5,6] and Particle Swarm Optimization (PSO) [7], Differential Evolution (DE) [8], Cloning Selection method (CSM) [9], Harmony Search (HS) [10], Artificial Bee Colony (ABC) [11] and Animal Behavior (AB) [12,13].…”

Cellular edge detection: Combining cellular automata and cellular learning automata

“…In [5] edge detection performed by using Particle Swarm Optimization (PSO). Moreover, in [6] ellipsoid shapes are detected by an edge detection approach.…”

“…Otherwise, if the pixel value of I is zero (I = 0), it will evaluate through (6). Based on (6), if the central cell equals to zero, the corresponding pixel of output image J will set to zero (J = 0).…”

Utilization of the Discrete Differential Evolution for Optimization in Multidimensional Point Clouds

“…The article [38] summarizes different applications of evolutionary algorithms in the pattern recognition and machine learning including the Differential Evolution. The DE has been utilized for human body pose estimation from the point clouds [6, 36, 40], circles detection [7], ellipses detection [41], recognition of leukocytes in images, or 3D face model reconstruction utilizing multiview 2D images [42]. Most of the referenced algorithms optimize analytically a temporary pattern shape, deformable or active shape models.…”