Recent work has shown that effective methods for recognising objects or spatio-temporal events can be constructed based on receptive field responses summarised into histograms or other histogram-like image descriptors. This paper presents a set Of composed histogram features of higher dimensionality, which give significantly better recognition performance compared to the histogram descriptors of lower dimensionality that were used in the original papers by Swain & Ballard (1991) or Schiele & Crowley (2000). The use of histograms of higher dimensionality is made possible by a sparse representation for efficient computation and handling of higher-dimensional histograms. Results of extensive experiments are reported, showing how the performance of histogram-based recognition schemes depend upon different combinations of cues, in terms of Gaussian derivatives or differential invariants applied to either intensity information, chromatic information or both. It is shown that there exist composed higher-dimensional histogram descriptors with much better performance for recognising known objects than previously used histogram features. Experiments are also reported of classifying unknown objects into visual categories.

QC 20111025

Recent work has shown that effective methods for recognizing objects and spatio-temporal events can be constructed based on histograms of receptive field like image operations.This paper presents the results of an extensive study of the performance of different types of receptive field like image descriptors for histogram-based object recognition, based on different combinations of image cues in terms of Gaussian derivatives or differential invariants applied to either intensity information, colour-opponent channels or both. A rich set of composed complex-cue image descriptors is introduced and evaluated with respect to the problems of (i) recognizing previously seen object instances from previously unseen views, and (ii) classifying previously unseen objects into visual categories.It is shown that there exist novel histogram descriptors with significantly better recognition performance compared to previously used histogram features within the same class. Specifically, the experiments show that it is possible to obtain more discriminative features by combining lower-dimensional scale-space features into composed complexcue histograms. Furthermore, different types of image descriptors have different relative advantages with respect to the problems of object instance recognition vs. object category classification. These conclusions are obtained from extensive evaluations on two mutually independent data sets.For the task of recognizing specific object instances, combined histograms of spatial and spatio-chromatic derivatives are highly discriminative, and several image descriptors in terms rotationally invariant (intensity and spatiochromatic) differential invariants up to order two lead to very high recognition rates.For category classification, primary information is contained in both first-and second-order derivatives, where second-order partial derivatives constitute the most discriminative cue.Dimensionality reduction by principal component analysis and variance normalization prior to training and recognition can in many cases lead to a significant increase in recognition or classification performance. Surprisingly high recognition rates can even be obtained with binary histograms that reveal the polarity of local scale-space features, and which can be expected to be particularly robust to illumination variations. An overall conclusion from this study is that compared to previously used lower-dimensional histograms, the use of composed complex-cue histograms of higher dimensionality reveals the co-variation of multiple cues and enables much better recognition performance, both with regard to the problems of recognizing previously seen objects from novel views and for classifying previously unseen objects into visual categories.

This paper proposes a set of new image descriptors based on local histograms of basic operators. These descriptors are intended to serve in a first-level stage of an hierarcical representation of image structures. For reasons of efficiency and scalability, we argue that descriptors suitable for this purpose should be able to capture and separate invariant and variant properties. Unsupervised clustering of the image descriptors from training data gives a visual vocabulary, which allow for compact representations. We demonstrate the representational power of the proposed descriptors and vocabularies on image categorization tasks using wellknown datasets. We use image representations via statistics in form of global histograms of the underlying visual words, and compare our results to earlier reported work.