Composed Complex-Cue Histograms: An Investigation of the Information Content in Receptive Field Based Image Descriptors for Object Recognition

Oskar Linde and Tony Lindeberg

Computer Vision and Image Understanding, volume 116, number 4, pages 538-560, 2012.

Digitally published with DOI: 10.1016/j.cviu.2011.12.003 in December 2011.

Abstract

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 complex-cue 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 experimental 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 spatio-chromatic) differential invariants up to order two lead to very high recognition rates.

For the task of 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.

Keywords: image descriptor, histogram, object recognition, object categorization, Gaussian derivative, spatio-chromatic derivative, differential invariant, spatio-chromatic differential invariant, image feature, colour feature, scale-space, cue combination, multiple cues, multi-scale representation, computer vision.

Highlights

• new receptive-field histograms based on catalogue of scale-space operations.
• Gaussian derivatives and differential invariants from colour-opponent channels.
• composed histograms give better performance than primitive image features.
• capture the co-variation of different primitive image cues.
• sparse representation captures higher-dimensional histograms efficiently.
• different descriptors suitable for object recognition vs object categorization.
• intensity and spatio-chromatic differential invariants for object recognition.
• rotationally invariant differential invariants more robust to viewing variations.
• partial derivatives (N-jet) contain more information for object categorization.
• importance of higher-order cues based on second-order derivatives.
• surprisingly good performance can even be obtained with binary histograms.
• qualitative judgements in terms of polarity of local scale-space features.
• trinary histograms classify as clear positive, around zero or clear negative.
• dimensional reduction interpreted in terms of derivatives with respect to scale.

PDF: (4.2 Mb)

On-line version: (At the official site of the journal)

---

An earlier treatment on this topic can be found in:

• Linde and Lindeberg (2004) `Object recognition using composed receptive field histograms of higher dimensionality'', Proc 17th International Conference on Pattern Recognition ICPR 2004, (Cambridge, U.K), volume: 2, pages 1-6, August 2004.