Search

Abstract: This paper presents a strategy to improve the AdaBoost algorithm with a quadratic combination of base classifiers. We observe that learning this combination is necessary to get better performance and is possible by constructing an intermediate learner operating on the combined linear and quadratic terms. This is not trivial, as the parameters of the base classifiers are not under direct control, obstructing the application of direct optimization. We propose a new method realizing iterative optimization indirectly. First we train a classifier by randomizing the labels of training examples. Subsequently, the input learner is called repeatedly with a systematic update of the labels of the training examples in each round. We show that the quadratic boosting algorithm converges under the condition that the given base learner minimizes the empirical error. We also give an upper bound on the VC-dimension of the new classifier. Our experimental results on 23 standard problems show that quadratic boosting compares favorably with AdaBoost on large data sets at the cost of training speed. The classification time of the two algorithms, however, is equivalent. [Copyright &y& Elsevier]

Abstract: This paper studies two types of spatial relationships that can be learned from training examples for object recognition. The first one employs deformable relationships between object parts with a Gaussian model, while the second one describes pairwise relationships between pixel intensity values using Bayesian networks. We perform experiments on a human face dataset and a horse dataset, imposing the same amount of annotation of training data, which can be seen as sending knowledge to the learning algorithms. The result indicates that the Bayesian network method compares favorably to the deformable model, as it can capture long-distance stable relations in the object appearance. We also conclude that both methods are superior to strictly spatial matching by template and strictly non-spatial classifiers. [Copyright &y& Elsevier]

This paper offers a sparse, multiscale representation of objects. It captures the object appearance by selection from a very large dictionary of Gaussian differential basis functions. The learning procedure results from the matching pursuit algorithm, while the recognition is based on polynomial approximation to the bases, turning image matching into a problem of polynomial evaluation. The method is suited for coarse recognition between objects and, by adding more bases, also for fine recognition of the object pose. The advantages over the common representation using PCA include storing sampled points for recognition is not required, adding new objects to an existing data set is trivial because retraining other object models is not needed, and significantly in the important case where one has to scan an image over multiple locations in search for an object, the new representation is readily available as opposed to PCA projection at each location. The experimental result on the COIL-100 data set demonstrates high recognition accuracy with real-time performance. [ABSTRACT FROM AUTHOR]

Grouping in vision can be seen as the process that organizes image entities into higher-level structures. Despite its importance, there is little consistency in the statement of the grouping problem in literature. In addition, most grouping algorithms in vision are inspired on a specific technique, rather than being based on desired characteristics, making it cumbersome to compare the behavior of various methods. This paper discusses six precisely formulated considerations for the design of generic grouping algorithms in vision: proper definition, invariance, multiple interpretations, multiple solutions, simplicity and robustness. We observe none of the existing algorithms for grouping in vision meet all the considerations. We present a simple algorithm as an extension of a classical algorithm, where the extension is based on taking the considerations into account. The algorithm is applied to three examples: grouping point sets, grouping poly-lines, and grouping flow-field vectors. The complexity of the greedy algorithm is O(nO[sub G]), where O[sub G] is the complexity of the grouping measure. [ABSTRACT FROM AUTHOR]