Visual Codebook Research Articles

A Review of Codebook Models in Patch-Based Visual Object Recognition

The codebook model-based approach, while ignoring any structural aspect in vision, nonetheless provides state-of-the-art performances on current datasets. The key role of a visual codebook is to provide a way to map the low-level features into a fixed-length vector in histogram space to which standard classifiers can be directly applied. The discriminative power of such a visual codebook determines the quality of the codebook model, whereas the size of the codebook controls the complexity of the model. Thus, the construction of a codebook is an important step which is usually done by cluster analysis. However, clustering is a process that retains regions of high density in a distribution and it follows that the resulting codebook need not have discriminant properties. This is also recognised as a computational bottleneck of such systems. In our recent work, we proposed a resource-allocating codebook, to constructing a discriminant codebook in a one-pass design procedure that slightly outperforms more traditional approaches at drastically reduced computing times. In this review we survey several approaches that have been proposed over the last decade with their use of feature detectors, descriptors, codebook construction schemes, choice of classifiers in recognising objects, and datasets that were used in evaluating the proposed methods.

Improvements in image categorization using codebook ensembles

The problem of object category classification by committees or ensembles of classifiers, each of which is based on one diverse codebook, is addressed in this paper. Two methods of constructing visual codebook ensembles are proposed in this study. The first technique introduces diverse individual visual codebooks using different clustering algorithms. The second uses various visual codebooks of different sizes for constructing an ensemble with high diversity. Codebook ensembles are trained to capture and convey image properties from different aspects. Based on these codebook ensembles, different types of image representations can be acquired. A classifier ensemble can be trained based on different expression datasets from the same training image set. The use of a classifier ensemble to categorize new images can lead to improved performance. Detailed experimental analysis on a Pascal VOC challenge dataset reveals that the present ensemble approach performs well, consistently improves the performance of visual object classifiers, and results in state-of-the-art performance in categorization.

Creating Efficient Visual Codebook Ensembles for Object Categorization

An image comprises information, such as color, texture, shape, and intensity, which humans use in parallel for perception. Based on this knowledge, three methods of constructing visual codebook ensembles are proposed in this paper. The first technique introduced diverse individual visual codebooks by randomly choosing interesting points. The second technique was based on a random subtraining image data set with random interesting points. The third method directly utilized different patch information for constructing an ensemble with high diversity. The codebook ensembles were learned to capture and convey image properties from different aspects. Based on these codebook ensembles, different types of image presentations could be obtained. A classification ensemble could be learned based on the different expression data sets from the same training image set. The use of a classification ensemble to categorize new images can lead to improved performance. The detailed experimental analyses on several data sets revealed that the present ensemble approaches were resistant to variations in view, lighting, occlusion, and intraclass variations. In addition, they resulted in state-of-the-art performance in categorization.

Efficient and Effective Visual Codebook Generation Using Additive Kernels

Common visual codebook generation methods used in a bag of visual words model, for example, k-means or Gaussian Mixture Model, use the Euclidean distance to cluster features into visual code words. However, most popular visual descriptors are histograms of image measurements. It has been shown that with histogram features, the Histogram Intersection Kernel (HIK) is more effective than the Euclidean distance in supervised learning tasks. In this paper, we demonstrate that HIK can be used in an unsupervised manner to significantly improve the generation of visual codebooks. We propose a histogram kernel k-means algorithm which is easy to implement and runs almost as fast as the standard k-means. The HIK codebooks have consistently higher recognition accuracy over k-means codebooks by 2-4% in several benchmark object and scene recognition data sets. The algorithm is also generalized to arbitrary additive kernels. Its speed is thousands of times faster than a naive implementation of the kernel k-means algorithm. In addition, we propose a one-class SVM formulation to create more effective visual code words. Finally, we show that the standard k-median clustering method can be used for visual codebook generation and can act as a compromise between the HIK / additive kernel and the k-means approaches.

An Adaptive Algorithm for Robust Visual Codebook Generation and Its Natural Scene Categorization Application

An Adaptive Algorithm for Robust Visual Codebook Generation and Its Natural Scene Categorization Application

Building descriptive and discriminative visual codebook for large-scale image applications

Inspired by the success of textual words in large-scale textual information processing, researchers are trying to extract visual words from images which function similar as textual words. Visual words are commonly generated by clustering a large amount of image local features and the cluster centers are taken as visual words. This approach is simple and scalable, but results in noisy visual words. Lots of works are reported trying to improve the descriptive and discriminative ability of visual words. This paper gives a comprehensive survey on visual vocabulary and details several state-of-the-art algorithms. A comprehensive review and summarization of the related works on visual vocabulary is first presented. Then, we introduce our recent algorithms on descriptive and discriminative visual word generation, i.e., latent visual context analysis for descriptive visual word identification [74], descriptive visual words and visual phrases generation [68], contextual visual vocabulary which combines both semantic contexts and spatial contexts [69], and visual vocabulary hierarchy optimization [18]. Additionally, we introduce two interesting post processing strategies to further improve the performance of visual vocabulary, i.e., spatial coding [73] is proposed to efficiently remove the mismatched visual words between images for more reasonable image similarity computation; user preference based visual word weighting [44] is developed to make the image similarity computed based on visual words more consistent with users' preferences or habits.

Latent visual context learning for web image applications

Recently, image representation based on bag-of-visual-words (BoW) model has been popularly applied in image and vision domains. In BoW, a visual codebook of visual words is defined, usually by clustering local features, to represent any novel image with the occurrence of its contained visual words. Given a set of images, we argue that the significance of each image is determined by the significance of its contained visual words. Traditionally, the significances of visual words are defined by term frequency-inverse document frequency (tf-idf), which cannot necessarily capture the intrinsic visual context. In this paper, we propose a new scheme of latent visual context learning (LVCL). The visual context among images and visual words is formulated from latent semantic context and visual link graph analysis. With LVCL, the importance of visual words and images will be distinguished from each other, which will facilitate image level applications, such as image re-ranking and canonical image selection. We validate our approach on text-query based search results returned by Google Image. Experimental results demonstrate the effectiveness and potentials of our LVCL in applications of image re-ranking and canonical image selection, over the state-of-the-art approaches.

Visual codebook construction for class-specific recognition

Creating a visual codebook is an important problem in object recognition. Using a compact visual codebook can boost computational efficiency and reduce memory cost. A simple and effective method is proposed for visual feature codebook construction. On the basis of a feedforward hierarchical model, a robust local descriptor is proposed and an a priori statistical scheme is applied to the class-specific feature-learning stage. The experiments show that the proposed approach achieves reliable performance with shorter codebook length, and incremental learning can be easily enabled.

Sparse B-spline polynomial descriptors for human activity recognition

The extraction and quantization of local image and video descriptors for the subsequent creation of visual codebooks is a technique that has proved very effective for image and video retrieval applications. In this paper we build on this concept and propose a new set of visual descriptors that provide a local space-time description of the visual activity. The proposed descriptors are extracted at spatiotemporal salient points detected on the estimated optical flow field for a given image sequence and are based on geometrical properties of three-dimensional piecewise polynomials, namely B-splines. The latter are fitted on the spatiotemporal locations of salient points that fall within a given spatiotemporal neighborhood. Our descriptors are invariant in translation and scaling in space-time. The latter is ensured by coupling the neighborhood dimensions to the scale at which the corresponding spatiotemporal salient points are detected. In addition, in order to provide robustness against camera motion (e.g. global translation due to camera panning) we subtract the motion component that is estimated by applying local median filters on the optical flow field. The descriptors that are extracted across the whole dataset are clustered in order to create a codebook of ‘visual verbs’, where each verb corresponds to a cluster center. We use the resulting codebook in a ‘bag of verbs’ approach in order to represent the motion of the subjects within small temporal windows. Finally, we use a boosting algorithm in order to select the most discriminative temporal windows of each class and Relevance Vector Machines (RVM) for classification. The presented results using three different databases of human actions verify the effectiveness of our method.

Combining visual dictionary, kernel-based similarity and learning strategy for image category retrieval

This paper presents a search engine architecture, RETIN, aiming at retrieving complex categories in large image databases. For indexing, a scheme based on a two-step quantization process is presented to compute visual codebooks. The similarity between images is represented in a kernel framework. Such a similarity is combined with online learning strategies motivated by recent machine-learning developments such as active learning. Additionally, an offline supervised learning is embedded in the kernel framework, offering a real opportunity to learn semantic categories. Experiments with real scenario carried out from the Corel Photo database demonstrate the efficiency and the relevance of the RETIN strategy and its outstanding performances in comparison to up-to-date strategies.