Shiu Yin Yuen

A Genetic Algorithm That Adaptively Mutates and Never Revisits

A novel genetic algorithm is reported that is non-revisiting: It remembers every position that it has searched before. An archive is used to store all the solutions that have been explored before. Different from other memory schemes in the literature, a novel binary space partitioning tree archive design is advocated. Not only is the design an efficient method to check for revisits, if any, it in itself constitutes a novel adaptive mutation operator that has no parameter. To demonstrate the power of the method, the algorithm is evaluated using 19 famous benchmark functions. The results are as follows. (1) Though it only uses finite resolution grids, when compared with a canonical genetic algorithm, a generic real-coded genetic algorithm, a canonical genetic algorithm with simple diversity mechanism, and three particle swarm optimization algorithms, it shows a significant improvement. (2) The new algorithm also shows superior performance compared to covariance matrix adaptation evolution strategy (CMA-ES), a state-of-the-art method for adaptive mutation. (3) It can work with problems that have large search spaces with dimensions as high as 40. (4) The corresponding CPU overhead of the binary space partitioning tree design is insignificant for applications with expensive or time-consuming fitness evaluations, and for such applications, the memory usage due to the archive is acceptable. (5) Though the adaptive mutation is parameter-less, it shows and maintains a stable good performance. However, for other algorithms we compare, the performance is highly dependent on suitable parameter settings.

Connective hough transform

A method to extend the Hough transform (HT) to detect connectivity by ordered accumulation is reported. The method is applied to the dynamic combinatorial HT [6]. A focus of attention mechanism is also reported. Our connective HT with focus of attention reduces the computational complexity of the DCHT and increases the S/N ratio of the peak in its accumulator. It may be regarded as a principled method for curve tracing. A general method to improve the computational efficiency of the DCHT by probabilistic selection of interesting fixation points is also introduced. Results using simulated and real data are reported.

An Evolutionary Algorithm That Makes Decision Based on the Entire Previous Search History

In this paper, we report a novel evolutionary algorithm that enhances its performance by utilizing the entire previous search history. The proposed algorithm, namely history driven evolutionary algorithm (HdEA), employs a binary space partitioning tree structure to memorize the positions and the fitness values of the evaluated solutions. Benefiting from the space partitioning scheme, a fast fitness function approximation using the archive is obtained. The approximation is used to improve the mutation strategy in HdEA. The resultant mutation operator is parameter-less, anisotropic, and adaptive. Moreover, the mutation operator naturally avoids the generation of out-of-bound solutions. The performance of HdEA is tested on 34 benchmark functions with dimensions ranging from 2 to 40. We also provide a performance comparison of HdEA with eight benchmark evolutionary algorithms, including a real coded genetic algorithm, differential evolution, two improved differential evolution, covariance matrix adaptation evolution strategy, two improved particle swarm optimization, and an estimation of distribution algorithm. Seen from the experimental results, HdEA outperforms the other algorithms for multimodal function optimization.

A non-revisiting Genetic Algorithm

Genetic Algorithm (GA) is a revisiting stochastic algorithm. In other words, a solution that has been visited before may be revisited. The fitness of the solution has to be evaluated each time. Since fitness evaluation is the most computationally intensive process in the execution of the GA, revisits should be minimized or eliminated. In this paper, a novel dynamic binary partitioning tree archive is proposed to eliminate all revisits. It works as follows: When the GA generates a solution, the tree is accessed. A leaf node is appended to the tree if the solution has not been visited before and so has no record in the tree. Otherwise, a search is initiated from the leaf node that is the duplicate to the solution to find the nearest neighbor solution in the search space that is not visited. During this process, whole sub-trees may be pruned if all the leaf nodes it contains are visited. The search naturally implements a self adaptive mutation mechanism. Hence the GA requires no other mutation parameter or mutation scheme. Experimental results reveal that this new GA is superior in performance compared with the standard GA with revisits, and the tree archive is not memory intensive.

An Improved Artificial Bee Colony Algorithm for Optimal Design of Electromagnetic Devices

Optimal design problems of electromagnetic devices are generally multimodal, nondifferentiable, and constrained. This makes metaheuristic algorithm a good choice for solving such problems. In this paper, a newly developed metaheuristic algorithm is presented to address the aforementioned issues. The proposed algorithm is based on the paradigm of artificial bee colony (ABC). A drawback of the original ABC algorithm is because its solution variation is only 1-D, as this decreases its convergence speed. In this paper, a one-position inheritance scheme is proposed to alleviate this drawback. An opposite directional (OD) search is also proposed to accelerate the convergence of the ABC algorithm. The novel algorithm is applied to both TEAM Workshop problem 22 and a loudspeaker design problem. Both discrete and continuous cases of problem 22 are tested. The effectiveness and efficiency of the proposed algorithm are demonstrated by comparing its performance with those of the original ABC, an improved ABC known as Gaussian ABC, and differential evolution algorithms.

An unbiased active contour algorithm for object tracking

Active contour models for object tracking are investigated. The unbiased active contour algorithm, a model using edge feature based tracking, modifies the energy functions to correct the bias towards equal-distanced snaxels and small curvature, and eliminates the need to treat corners specially. Comparison with the William and Shah (1992) model shows substantial improvements.

A Multiobjective Evolutionary Algorithm That Diversifies Population by Its Density

Most existing multiobjective evolutionary algorithms (MOEAs) assume the existence of Pareto-optimal solutions/Pareto-optimal objective vectors in a neighborhood of an obtained Pareto-optimal set (PS)/Pareto-optimal front (PF). Obviously, this assumption does not work well on the multiobjective problem (MOP) whose true PF and true PS are in the form of multiple segments-truly disconnected MOP (TYD-MOP). Moreover, these MOEAs commonly involve more than three control parameters; and some of them even involve nine control parameters. The stabilities of their performance against parameter settings are generally unknown. In this paper, we propose a MOEA, namely multiobjective density driven evolutionary algorithm (MODdEA), which can handle TYD-MOP. MODdEA stores all evaluated solutions by a binary space partitioning (BSP) tree. Benefiting from the BSP scheme, a fast solution density estimation by the archive is naturally obtained. MODdEA uses this estimated density together with the nondominated rank to probabilistically select mating individuals, which relaxes the neighborhood assumption on PF in a parameter-less manner. Moreover, two genetic operators, extended arithmetic crossover and diversified mutation, are proposed to enhance the explorative search ability of the algorithm. MODdEA is examined on two test problem sets. The first test set consists of six TYD-MOPs; the second test set consists of 17 benchmark MOPs which are commonly examined by the existing MOEAs. Comparing to 14 test MOEAs, MODdEA has superior performance on TYD-MOP and is competitive on MOP whose true PF and PS are one single connected segment.

A fast marching formulation of perspective shape from shading under frontal illumination

An adaptation of the fast marching method to the perspective Shape from Shading under frontal illumination is proposed. A heuristic is proposed to handle occlusion. The method outperforms Tankus et al. [Tankus, A., Sochen, N., Yeshurun, Y., 2005. Shape-from-shading under perspective projection. Internat. J. Comput. Vision 63(1), 21-43] in both time and accuracy. Accurate methods for generating testing images are also reported.

An investigation of the nature of parameterization for the Hough transform

A novel parameterization method for the Hough transform is reported. Instead of the conventional non-parametric form, the parametric form is used and copies of the transformed shape are plotted on two-dimensional slices of the Hough space. It is shown that the corresponding parameterization has uniform precision with respect to translation, and cancels out the quantization uncertainty due to image digitization. A problem of the Hough transform is discovered which is due to non-uniform discretized voting. It is shown that the above class of parameterizations avoids the problem. Finally, a particular solution of the parameterization scheme is described which is called the Fourier parameterization. It is shown that the parameterization has uniform precision with respect to the affine transformation.

Genetic algorithm with competitive image labelling and least square

Abstract A multi-modal genetic algorithm using a dynamic population concept is introduced. Each image point is assigned a label and for a chromosome to survive, it must have at least one image point with its label. In this way, the genetic algorithm dynamically segments the scene into one or more objects and the background noise. A Repeated Least Square technique is applied to enhance the convergence performance. The integrated algorithm is tested using a 6 degrees of freedom template matching problem, and it is applied to some images that are challenging for genetic algorithm applications.