Recently, methods based on local image features have shown promise for texture and object recognition tasks. This paper presents a large-scale evaluation of an approach that represents images as distributions (signatures or histograms) of features extracted from a sparse set of keypoint locations and learns a Support Vector Machine classifier with kernels based on two effective measures for comparing distributions, the Earth Mover’s Distance and the χ 2 distance. We first evaluate the performance of our approach with different keypoint detectors and descriptors, as well as different kernels and classifiers. We then conduct a comparative evaluation with several state-of-the-art recognition methods on four texture and five object databases. On most of these databases, our implementation exceeds the best reported results and achieves comparable performance on the rest. Finally, we investigate the influence of background correlations on recognition performance via extensive tests on the PASCAL database, for which ground-truth object localization information is available. Our experiments demonstrate that image representations based on distributions of local features are surprisingly effective for classification of texture and object images under challenging real-world conditions, including significant intra-class variations and substantial background clutter.

Abstract. The PASCAL Visual Object Classes Challenge ran from February to March 2005. The goal of the challenge was to recognize objects from a number of visual object classes in realistic scenes (i.e. not pre-segmented objects). Four object classes were selected: motorbikes, bicycles, cars and people. Twelve teams entered the challenge. In this chapter we provide details of the datasets, algorithms used by the teams, evaluation criteria, and results achieved. 1

Imagine a video taken on a sunny beach, can a computer automatically tell what is happening in the scene? Can it identify different human activities in the video, such as water surfing, people walking and lying on the beach? To automatically classify or localize different actions in video sequences is very useful for a variety of tasks, such as video surveillance, objectlevel video summarization, video indexing, digital library organization, etc. However, it remains a challenging task for computers to achieve robust action recognition due to cluttered background, camera motion, occlusion, and geometric and photometric variances of objects. For example, in a live video of a skating competition, the skater moves rapidly across the rink, and the camera also moves to follow the skater. With moving camera, non-stationary background, and moving target, few vision algorithms could identify, categorize and

Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can learn an object category from just its name, by utilizing the raw output of image search engines available on the Internet. We develop a new model, TSI-pLSA, which extends pLSA (as applied to visual words) to include spatial information in a translation and scale invariant manner. Our approach can handle the high intra-class variability and large proportion of unrelated images returned by search engines. We evaluate the models on standard test sets, showing performance competitive with existing methods trained on hand prepared datasets. 1.

The paper gives a snapshot of the state of the art in affine covariant region detectors, and compares their performance on a set of test images under varying imaging conditions. Six types of detectors are included: detectors based on affine normalization around Harris [24, 34] and Hessian points [24], as proposed by Mikolajczyk and Schmid and by Schaffalitzky and Zisserman; a detector of ‘maximally stable extremal regions’, proposed by Matas et al. [21]; an edge-based region detector [45] and a detector based on intensity extrema [47], proposed by Tuytelaars and Van Gool; and a detector of ‘salient regions’, proposed by Kadir, Zisserman and Brady [12]. The performance is measured against changes in viewpoint, scale, illumination, defocus and image compression. The objective of this paper is also to establish a reference test set of images and performance software, so that future detectors can be evaluated in the same framework. 1

Given a large dataset of images, we seek to automatically determine the visually similar object and scene classes together with their image segmentation. To achieve this we combine two ideas: (i) that a set of segmented objects can be partitioned into visual object classes using topic discovery models from statistical text analysis; and (ii) that visual object classes can be used to assess the accuracy of a segmentation. To tie these ideas together we compute multiple segmentations of each image and then: (i) learn the object classes; and (ii) choose the correct segmentations. We demonstrate that such an algorithm succeeds in automatically discovering many familiar objects in a variety of image datasets, including those from Caltech, MSRC and LabelMe. 1.

Figure 1: Exemplar snapshots of our interactive object categorization demo application. A user selects (sloppily) a region of interest and our algorithm associates an object class label with it. Despite large differences in pose, size, illumination and visual appearance the correct class label (e.g. cow, building, car...) is automatically associated with each selected object instance. Some of these test images were downloaded from the web and none were part of the training set. A video of the interactive demo may be found at the above web site. This paper presents a new algorithm for the automatic recognition of object classes from images (categorization). Compact and yet discriminative appearance-based object class models are automatically learned from a set of training images. The method is simple and extremely fast, making it suitable for many applications such as semantic image retrieval, web search, and interactive image editing. It classifies a region according to the proportions of different visual words (clusters in feature space). The specific visual words and the typical proportions in each object are learned from a segmented training set. The main contribution of this paper is two fold: i) an optimally compact visual dictionary is learned by pair-wise merging of visual words from an initially large dictionary. The final visual words are described by GMMs. ii) A novel statistical measure of discrimination is proposed which is optimized by each merge operation. High classification accuracy is demonstrated for nine object classes on photographs of real objects viewed under general lighting conditions, poses and viewpoints. The set of test images used for validation comprise: i) photographs acquired by us, ii) images from the web and iii) images from the recently released Pascal dataset. The proposed algorithm performs well on both texture-rich objects (e.g. grass, sky, trees) and structure-rich ones (e.g. cars, bikes, planes). 1.

Visual codebook based quantization of robust appearance descriptors extracted from local image patches is an effective means of capturing image statistics for texture analysis and scene classification. Codebooks are usually constructed by using a method such as k-means to cluster the descriptor vectors of patches sampled either densely (‘textons’) or sparsely (‘bags of features ’ based on keypoints or salience measures) from a set of training images. This works well for texture analysis in homogeneous images, but the images that arise in natural object recognition tasks have far less uniform statistics. We show that for dense sampling, k-means over-adapts to this, clustering centres almost exclusively around the densest few regions in descriptor space and thus failing to code other informative regions. This gives suboptimal codes that are no better than using randomly selected centres. We describe a scalable acceptance-radius based clusterer that generates better codebooks and study its performance on several image classification tasks. We also show that dense representations outperform equivalent keypoint based ones on these tasks and that SVM or Mutual Information based feature selection starting from a dense codebook further improves the performance. 1.

Abstract. Bag-of-features representations have recently become popular for content based image classification owing to their simplicity and good performance. They evolved from texton methods in texture analysis. The basic idea is to treat images as loose collections of independent patches, sampling a representative set of patches from the image, evaluating a visual descriptor vector for each patch independently, and using the resulting distribution of samples in descriptor space as a characterization of the image. The four main implementation choices are thus how to sample patches, how to describe them, how to characterize the resulting distributions and how to classify images based on the result. We concentrate on the first issue, showing experimentally that for a representative selection of commonly used test databases and for moderate to large numbers of samples, random sampling gives equal or better classifiers than the sophisticated multiscale interest operators that are in common use. Although interest operators work well for small numbers of samples, the single most important factor governing performance is the number of patches sampled from the test image and ultimately interest operators can not provide enough patches to compete. We also study the influence of other factors including codebook size and creation method, histogram normalization method and minimum scale for feature extraction. 1

Given a set of images containing multiple object categories, we seek to discover those categories and their image locations without supervision. We achieve this using generative models from the statistical text literature: probabilistic Latent Semantic Analysis (pLSA), and Latent Dirichlet Allocation (LDA). In text analysis these are used to discover topics in a corpus using the bag-of-words document representation. Here we discover topics as object categories, so that an image containing instances of several categories is modelled as a mixture of topics. The models are applied to images by using a visual analogue of a word, formed by vector quantizing SIFT like region descriptors. We investigate a set of increasingly demanding scenarios, starting with image sets containing only two object categories through to sets containing multiple categories (including airplanes, cars, faces, motorbikes, spotted cats) and background clutter. The object categories sample both intra-class and scale variation, and both the categories and their approximate spatial layout are found without supervision. We also demonstrate classification of unseen images and images containing multiple objects. Performance of the proposed unsupervised method is compared to the semi-supervised approach of [7].