Multiple classifier boosting and tree-structured classifiers

Visual recognition problems often involve classification of myriads of pixels, across scales, to locate objects of interest in an image or to segment images according to object classes. The requirement for high speed and accuracy makes the problems very challenging and has motivated studies on efficient classification algorithms. A novel multi-classifier boosting algorithm is proposed to tackle the multimodal problems by simultaneously clustering samples and boosting classifiers in Section 2. The method is extended into an online version for object tracking in Section 3. Section 4 presents a tree-structured classifier, called Super tree, to further speed up the classification time of a standard boosting classifier. The proposed methods are demonstrated for object detection, tracking and segmentation tasks. © 2013 Springer-Verlag Berlin Heidelberg.

Temperature dependence of photoluminescence from single and ensemble InAs/GaAs quantum dots

We investigate the temperature dependence of photoluminescence from single and ensemble InAs/GaAs quantum dots systematically. As temperature increases, the exciton emission peak for single quantum dot shows broadening and redshift. For ensemble quantum dots, however, the exciton emission peak shows narrowing and fast redshift. We use a simple steady-state rate equation model to simulate the experimental data of photoluminescence spectra. It is confirmed that carrier-phonon scattering gives the broadening of the exciton emission peak in single quantum dots while the effects of carrier thermal escape and retrapping play an important role in the narrowing and fast redshift of the exciton emission peak in ensemble quantum dots.

Material transport in self-assembled InAs/GaAs quantum dot ensemble

Introducing the growth interruption between the InAs deposition and subsequent GaAs growth in self-assembled quantum dot (QD) structures, the material transport process in the InAs layers has been investigated by photoluminescence and transmission electron microscopy measurement. InAs material in structures without misfit dislocations transfers from the wetting layer to QDs corresponding to the red-shift of PL peak energy due to interruption. On the other hand, the PL peak shifts to higher energy in the structures with dislocations. In this case, the misfit dislocations would capture the InAs material from the surrounding wetting layer and coherent islands leading to the reduction of the size of these QDs. The variations in the PL intensity and Linewidth are also discussed.

Material transport in self-assembled InAs/GaAs quantum dot ensemble

Introducing the growth interruption between the InAs deposition and subsequent GaAs growth in self-assembled quantum dot (QD) structures, the material transport process in the InAs layers has been investigated by photoluminescence and transmission electron microscopy measurement. InAs material in structures without misfit dislocations transfers from the wetting layer to QDs corresponding to the red-shift of PL peak energy due to interruption. On the other hand, the PL peak shifts to higher energy in the structures with dislocations. In this case, the misfit dislocations would capture the InAs material from the surrounding wetting layer and coherent islands leading to the reduction of the size of these QDs. The variations in the PL intensity and Linewidth are also discussed.

A hyper-heuristic ensemble method for static job-shop scheduling.

We describe a new hyper-heuristic method NELLI-GP for solving job-shop scheduling problems (JSSP) that evolves an ensemble of heuristics. The ensemble adopts a divide-and-conquer approach in which each heuristic solves a unique subset of the instance set considered. NELLI-GP extends an existing ensemble method called NELLI by introducing a novel heuristic generator that evolves heuristics composed of linear sequences of dispatching rules: each rule is represented using a tree structure and is itself evolved. Following a training period, the ensemble is shown to outperform both existing dispatching rules and a standard genetic programming algorithm on a large set of new test instances. In addition, it obtains superior results on a set of 210 benchmark problems from the literature when compared to two state-of-the-art hyperheuristic approaches. Further analysis of the relationship between heuristics in the evolved ensemble and the instances each solves provides new insights into features that might describe similar instances.

Rough feature selection for intelligent classifiers

Q. Shen. Rough feature selection for intelligent classifiers. LNCS Transactions on Rough Sets, 7:244-255, 2007.

Boosting Nearest Neighbor Classifiers for Multiclass Recognition

This paper introduces an algorithm that uses boosting to learn a distance measure for multiclass k-nearest neighbor classification. Given a family of distance measures as input, AdaBoost is used to learn a weighted distance measure, that is a linear combination of the input measures. The proposed method can be seen both as a novel way to learn a distance measure from data, and as a novel way to apply boosting to multiclass recognition problems, that does not require output codes. In our approach, multiclass recognition of objects is reduced into a single binary recognition task, defined on triples of objects. Preliminary experiments with eight UCI datasets yield no clear winner among our method, boosting using output codes, and k-nn classification using an unoptimized distance measure. Our algorithm did achieve lower error rates in some of the datasets, which indicates that, in some domains, it may lead to better results than existing methods.

Example-Based Image Restoration via Boosted Classifiers

We propose a novel image registration framework which uses classifiers trained from examples of aligned images to achieve registration. Our approach is designed to register images of medical data where the physical condition of the patient has changed significantly and image intensities are drastically different. We use two boosted classifiers for each degree of freedom of image transformation. These two classifiers can both identify when two images are correctly aligned and provide an efficient means of moving towards correct registration for misaligned images. The classifiers capture local alignment information using multi-pixel comparisons and can therefore achieve correct alignments where approaches like correlation and mutual-information which rely on only pixel-to-pixel comparisons fail. We test our approach using images from CT scans acquired in a study of acute respiratory distress syndrome. We show significant increase in registration accuracy in comparison to an approach using mutual information.

Face Identification by a Cascade of Rejection Classifiers

Nearest neighbor search is commonly employed in face recognition but it does not scale well to large dataset sizes. A strategy to combine rejection classifiers into a cascade for face identification is proposed in this paper. A rejection classifier for a pair of classes is defined to reject at least one of the classes with high confidence. These rejection classifiers are able to share discriminants in feature space and at the same time have high confidence in the rejection decision. In the face identification problem, it is possible that a pair of known individual faces are very dissimilar. It is very unlikely that both of them are close to an unknown face in the feature space. Hence, only one of them needs to be considered. Using a cascade structure of rejection classifiers, the scope of nearest neighbor search can be reduced significantly. Experiments on Face Recognition Grand Challenge (FRGC) version 1 data demonstrate that the proposed method achieves significant speed up and an accuracy comparable with the brute force Nearest Neighbor method. In addition, a graph cut based clustering technique is employed to demonstrate that the pairwise separability of these rejection classifiers is capable of semantic grouping.