Image classification via adaptive ensembles of descriptor-specific classifiers
An automated classification system usually consists of (i) a supervised learning algorithm for automatically generating classifiers from training data, and (ii) a representation scheme for converting the training objects into vectorial representations of their content. In this work, we take a detour from this tradition and present an approach to image classification based on an adaptive ensemble of classifiers, each specialized on classifying images based on a single “descriptor.” Each descriptor focuses on a different aspect, or perspective, of images; an ensemble of descriptor-specific classifiers can thus be seen as a committee of experts, each viewing the problem to be solved with a different slant, of from a different viewpoint. We test four different ways to set up such an ensemble, based on different ways of leveraging on the individual responses returned by each member of the ensemble, and on how confident these members are on their responses. We test this approach by using five different MPEG-7 descriptors on the task of assigning photographs of stone slabs to classes representing different types of stones. Our experimental results show important accuracy improvements with respect to a baseline in which a single classifier, working an all five descriptors at the same time, is employed.
Keywordsimage classification supervised learning classifier committees classifier ensembles metric spaces k-nearest neighbours classifier MPEG-7
Unable to display preview. Download preview PDF.
- 1.G. Amato, F. Falchi, C. Gennaro, F. Rabitti, P. Savino, and P. Stanchev, “Improving Image Similarity Search Effectiveness in a Multimedia Content Management System,” in Proc. 10th Intern. Workshop on Multimedia Information System (MIS’04) (College Park, US, 2004), pp. 139–146.Google Scholar
- 3.P. Ciaccia, M. Patella, and P. Zezula, “M-Tree: An Efficient Access Method for Similarity Search in Metric Spaces,” in Proc. 23rd Intern. Conf. on Very Large Data Bases (VLDB’97) (Athens, 1997), pp. 426–435.Google Scholar
- 4.L. Didaci and G. Giacinto, “Dynamic Classifier Selection by Adaptive k-Nearest-Neighbourhood Rule,” in Proc. 5th Intern. Workshop on Multiple Classifier Systems (MCS’04) (Cagliari, 2004), pp. 174–183.Google Scholar
- 5.T. G. Dietterich, “Ensemble Methods in Machine Learning,” in Proc. 1st Intern. Workshop on Multiple Classifier Systems (MCS’00) (Cagliari, 2000), pp. 1–15.Google Scholar
- 7.G. Giacinto and F. Roli, “Adaptive Selection of Image Classifiers,” in Proc. 9th Intern. Conf. on Image Analysis and Processing (ICIAP’97) (Firenze, 1997), pp. 38–45.Google Scholar
- 9.T. Joachimes, “Text Categorization with Support Vector Machines: Learning with Many Relevant Features,” in Proc. 10th Europ. Conf. on Machine Learning (ECML’98) (Chemnitz, 1998), pp. 137–142.Google Scholar
- 12.Introduction to MPEG-7: Multimedia Content Description Interface, Ed. by B. S. Manjunath, P. Salembier, and T. Sikora (John Wiley & Sons, New York, 2002).Google Scholar
- 14.V. D. Mazurov, The Committee Method in Optimization and Classification Problems (Nauka, Moscow, 1990) [in Russian].Google Scholar
- 17.E. Spyrou, H. Le Borgne, T. Mailis, E. Cooke, Y. Avrithis, and N. O’Connor, “Fusing MPEG-7 Visual Descriptions for Image Classification,” in Proc. 15th Intern. Conf. on Artificial Neural Networks (ICANN’05) (Warsaw, 2005), pp. 847–852.Google Scholar
- 22.Yiming Yang and Xin Liu, “A Re-Examination of Text Categorization Methods,” in Proc. 22nd ACM Intern. Conf. on Research and Development in Informational Retrieval (SIGIR’99) (Berkeley, 1999), pp. 42–49.Google Scholar
- 23.Yiming Yang, Jian Zhang, and B. Kisiel, “A Scalability Analysis of Classifiers in Text Categorization,” in Proc. 26th ACM Intern. Conf. on Research and Development in Information Retrieval (SIGIR’03) (Toronto, 2003), pp. 96–103.Google Scholar