Abstract. Robots need to ground their external vocabulary and internal symbols in observations of the world. In recent works, this problem has been approached through combinations of open-ended category learning and interaction with other agents acting as teachers. In this paper, a complementary path is explored, in which robots also resort to semantic searches in digital collections of text and images, or more generally in the Internet, to ground vocabulary about objects. Drawing on a distinction between broad and narrow (or general and specific) categories, different methods are applied, namely global shape contexts to represent broad categories, and SIFT local features to represent narrow categories. An unsupervised image clustering and ranking method is proposed that, starting from a set of images automatically fetched on the web for a given category name, selects a subset of images suitable for building a model of the category. In the case of broad categories, image segmentation and object extraction enhance the chances of finding suitable training objects. We demonstrate that the proposed approach indeed improves the quality of the training object collections. 1

In this paper the support vector machine is utilized to recognize the object from the given image. The proposed method for object recognition is associated with the reduction of feature vector by Kernel Principal Component Analysis (KPCA) and recognition using the Support Vector Machine (SVM) classifier. Also in this paper the feature extraction method extracts features from global descriptors of the image. In the feature extraction process for an image, global features are extracted and formed as feature vector. For the entire training image the feature vector is generated and dimension reduction is done using KPCA. The reduced feature vector is used to train the SVM classifier. Later test images are given as input and tested the performance of the Classifier. To prove the efficiency of the SVM Classifier, Back Propagation Neural Network is used for the object recognition. From the comparison, SVM classifier outperforms.

This document outlines the strategy of the Universidade de Aveiro entry for the Software League of the Semantic Robot Vision Challenge’2009. We have chosen to use a variety of classifiers that will rank the images from our workset according to the probability of containing a certain object. Afterwards a meta-level classier will, based on those various rankings, decide whether an image has a requested object. So far we have three classifiers: a classier based on SIFT for specific (narrow) categories, and a voting combination of two shape-based classifiers for more general (broad) categories. Learning Stage In the first stage of the challenge, lasting 2 hours, classification models for the requested objects are created.