A crowding multi-objective genetic algorithm for image parsing

• Published in: Neural computing & applications 2016-11, Vol.27 (8), p.2217-2227
• Main Authors: John Joseph, Ferdin Joe, Auwatanamongkol, Surapong
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Crowding; Data Mining and Knowledge Discovery; Genetic algorithms; Histograms; Image Processing and Computer Vision; Labelling; Multiple objective analysis; Object recognition; Optimization; Pixels; Predictive Analytics Using Machine Learning; Probability and Statistics in Computer Science; Representations; Support vector machines
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-015-2000-2

Image parsing is a process of understanding the contents of an image. The process normally involves labeling pixels or superpixels of a given image with classes of objects that may exist in the image. The accuracy of such labeling for the existing methodologies still needs to be improved. The parsing method needs to be able to identify multiple instances of objects of different classes and sizes. In our previous work, a novel feature representation for an instance of objects in an image was proposed for object recognition and image parsing. The feature representation consists of the histogram vector of 2 g of visual word ids of the two successive clockwise neighbors of any superpixels in the object instance and the shape vector of the instance. Using the feature representation, the instance can be classified with very high accuracy by the per class support vector machines (SVMs). A multi-objective genetic algorithm is also proposed to find a subset of image segments that would best constitute an instance for a class of objects, i.e., maximizing the SVM classification score and the size of the instance. However, the genetic algorithm can only identify a single instance for each class of objects, despite the fact that many instances of the same class may exist. In this paper, a crowding genetic algorithm is used instead to search for multiple optimal solutions and help alleviate this deficiency. The experimental results show that this crowding genetic algorithm performs better than the previously proposed method as well as the existing methodologies, in terms of class-wise and pixel-wise accuracy. The qualitative results also clearly show that this method can effectively identify multiple object instances existing in a given image.