EvoIASP Logo

Detailed Programme

Evolutionary Computation in Image Analysis, Signal Processing and Pattern Recognition.

Evolutionary algorithms have been shown to be tools which can be used effectively in the development of systems (software or hardware) for image analysis, signal processing and pattern recognition in complex domains of high industrial and social relevance.

After starting in 1999 as a workshop, EvoIASP has been the first European event specifically dedicated to the applications of evolutionary computation to image analysis and signal processing (IASP), as well as to Pattern Recognition, and gives European and non-European researchers in those fields, as well as people from industry, an opportunity to present their latest research and to discuss current developments and applications, besides fostering closer future interaction between members of the three scientific communities.

Areas of Interest and Contributions

Topics of interest include, but are not limited to:


Accepted papers will appear in the proceedings of EvoStar, published in a volume of the Springer Lecture Notes in Computer Science, which will be available at the Conference.Submissions must be original and not published elsewhere. The submissions will be peer reviewed by at least three members of the program committee. The authors of accepted papers will have to improve their paper on the basis of the reviewers comments and will be asked to send a camera ready version of their manuscripts. At least one author of each accepted work has to register for the conference and attend the conference and present the work.The reviewing process will be double-blind, please omit information about the authors in the submitted paper.

Submission Details

Submissions must be original and not published elsewhere. They will be peer reviewed by members of the program committee. The reviewing process will be double-blind, so please omit information about the authors in the submitted paper.

Submit your manuscript in Springer LNCS format.

Please provide up to five keywords in your Abstract

Page limit: 12 pages to http://myreview.csregistry.org/evoapps14/.


Submission deadline: 1 November 2013 11 November 2013
Notification: 06 January 2014
Camera ready: 01 February 2014
EvoIASP: 23-25 April 2014


Further information on the conference and co-located events can be
found in: http://www.evostar.org

EvoIASP Programme

Thurs 1430-1610  EvoIASP 1 : Best EvoIASP paper candidates 
Chair: Stefano Cagnoni

Evolutionary algorithm for dense pixel matching in presence of distortions    (EvoIASP best paper candidate)   Ana Carolina dos Santos Paulino, Jean-Christophe Nebel, Francisco Flórez-Revuelta
Dense pixel matching is an essential step required by many computer vision applications. While a large body of work as addressed quite successfully the rectified scenario, accurate pixel correspondence between an image and a distorted version remains very challenging. Exploiting an analogy between sequences of genetic material and images, we propose a novel genetics inspired algorithm where image variability is treated as the product of a set of image mutations. As a consequence, correspondence for each scanline of the initial image is formulated as the optimisation of a path in the second image minimising a fitness function penalising mutations. This optimisation is performed by a evolutionary algorithm which, in addition to provide fast convergence, implicitly ensures consistency between successive scanlines. Performance evaluation on locally and globally distorted images validates our bio-inspired approach.

Is a Single Image Sufficient for Evolving Edge Features by Genetic Programming?   (EvoIASP best paper candidate)     Wenlong Fu, Mark Johnston, Mengjie Zhang
Typically, a single natural image is not sufficient to train a program to extract edge features in edge detection when only training images and their ground truth are provided. However, a single training image might be considered as proper training data when domain knowledge, such as used in Gaussian-based edge detection, is provided. In this paper, we employ Genetic Programming (GP) to automatically evolve Gaussian-based edge detectors to extract edge features based on training data consisting of a single image only. The results show that a single image with a high proportion of true edge points can be used to train edge detectors which are not significantly different from rotation invariant surround suppression. When the programs separately evolved from eight single images are considered as weak classifiers, the combinations of these programs perform better than rotation invariant surround suppression.

Improving Graph-Based Image Segmentation Using Automatic Programming   (EvoIASP best paper candidate)   Lars Vidar Magnusson, Roland Olsson
This paper investigates how Felzenszwalb's and Huttenlocher's graph-based segmentation algorithm can be improved by automatic programming. We show that computers running Automatic Design of Algorithms Through Evolution (ADATE), our system for automatic programming, have induced a new graph-based algorithm that is 12 percent more accurate than the original without affecting the runtime efficiency. The result shows that ADATE is capable of improving an effective image segmentation algorithm and suggests that the system can be used to improve image analysis algorithms in general.


Thurs 1630-1810  EvoIASP 2 
Chair: Stefano Cagnoni

New Representations in PSO for Feature Construction in Classification     Yan Dai, Bing Xue, Mengjie Zhang
Feature construction can improve the classification performance by constructing high-level features using the original low-level features and function operators. Particle swarm optimisation (PSO) is an powerful global search technique, but it can not be directly used for feature construction because of its representation scheme. This paper proposes two new representations, pair representation and array representation, which allow PSO to direct evolve function operators. Two PSO based feature construction algorithms (PSOFCPair and PSOFCArray) are then developed. The two new algorithms are examined and compared with the first PSO based feature construction algorithm (PSOFC), which employs an inner loop to select function operators. Experimental results show that both PSOFCPair and PSOFCArray can increase the classification performance by constructing a new high-level feature. PSOFCArray outperforms PSOFCPair and achieves similar results to PSOFC, but uses significantly shorter computational time. This paper represents the first work on using PSO to directly evolve function operators for feature construction.

GPU-based Point Cloud Recognition using Evolutionary Algorithms     Roberto Ugolotti, Giorgio Micconi, Jacopo Aleotti, Stefano Cagnoni
In this paper, we describe a method for recognizing objects in the form of point clouds acquired with a laser scanner. This method is fully implemented on GPU and uses bio-inspired metaheuristics, namely PSO or DE, to evolve the rigid transformation that best aligns some references extracted from a dataset to the target point cloud. We compare the performance of our method with an established method based on Fast Point Feature Histograms (FPFH). The results prove that FPFH is more reliable under simple and controlled situations, but PSO and DE are more robust with respect to common problems as noise or occlusions.

A New Binary Particle Swarm Optimisation Algorithm for Feature Selection     Bing Xue, Su Nguyen, Mengjie Zhang
Feature selection aims to select a small number of features from a large feature set to achieve similar or better classification performance than using all features. This paper develops a new binary particle swam optimisation (PSO) algorithm (named PBPSO) based on which a new feature selection approach (PBPSOfs) is developed to reduce the number of features and increase the classification accuracy. The performance of PBPSOfs is compared with a standard binary PSO based feature selection algorithm (BPSOfs) and two traditional feature selection algorithms on 14 benchmark problems of varying difficulty. The results show that PBPSOfs can be successfully used for feature selection to select a small number of features and improve the classification performance over using all features. PBPSOfs further reduces the number of features selected by BPSOfs and simultaneously increases the classification accuracy, especially on datasets with a large number of features. Meanwhile, PBPSOfs achieves better performance than the two traditional feature selection algorithms. In addition, the results also show that PBPSO as a general binary optimisation technique can achieve better performance than standard binary PSO and uses less computational time.