Abstract—We present a novel approach for retrieval of object categories based on a novel type of image representation: the Generalized Correlogram (GC). In our image representation, the object is described as a constellation of GCs, where each one encodes information about some local part and the spatial relations from this part to others (that is, the part’s context). We show how such a representation can be used with fast procedures that learn the object category with weak supervision and efficiently match the model of the object against large collections of images. In the learning stage, we show that, by integrating our representation with Boosting, the system is able to obtain a compact model that is represented by very few features, where each feature conveys key properties about the object’s parts and their spatial arrangement. In the matching step, we propose direct procedures that exploit our representation for efficiently considering spatial coherence between the matching of local parts. Combined with an appropriate data organization such as Inverted Files, we show that thousands of images can be evaluated efficiently. The framework has been applied to different standard databases, and we show that our results are favorably compared against state-of-the-art methods in both computational cost and accuracy. Index Terms—Object recognition, retrieval, Boosting, spatial pattern, contextual information. 1

Incremental subspace methods have proven to enable efficient training if large amounts of training data have to be processed or if not all data is available in advance. In this paper we focus on incremental LDA learning which provides good classification results while it assures a compact data representation. In contrast to existing incremental LDA methods we additionally consider reconstructive information when incrementally building the LDA subspace. Hence, we get a more flexible representation that is capable to adapt to new data. Moreover, this allows to add new instances to existing classes as well as to add new classes. The experimental results show that the proposed approach outperforms other incremental LDA methods even approaching classification results obtained by batch learning. 1

A major shortcoming of discriminative recognition and detection methods is their noise sensitivity, both during training and recognition. This may lead to very sensitive and brittle recognition systems focusing on irrelevant information. This paper proposes a method that selects generative and discriminative features. In particular, we boost classical Haar-like features and use the same features to approximate a generative model (i.e., eigenimages). A modified error function for boosting ensures that only features are selected that show a good discrimination and reconstruction. This allows a robust feature selection using boosting. Thus, we can handle problems where discriminant classifiers fail while still retaining the discriminative power. Our experiments show that we can significantly improve the recognition performance when learning from noisy data. Moreover, the feature type used allows efficient recognition and reconstruction. 1.

Abstract In the paper we propose a novel method for incremental visual learning by combining reconstructive and discriminative subspace methods. This is achieved by embedding LDA learning and classification into the incremental PCA framework. The combined subspace consists of a truncated PCA subspace and a few additional basis vectors that encompass the discriminative information, which would be lost by the discarded principal vectors. As such it contains both sufficient reconstructive information to enable incremental learning, and the previously extracted discriminative information to enable efficient classification as well. We demonstrate that we are able to efficiently update the current model with new instances of the already learned classes as well as to introduce new classes. 1

Abstract—In this paper, we have developed a new scheme for achieving multilevel annotations of large-scale images automatically. To achieve more sufficient representation of various visual properties of the images, both the global visual features and the local visual features are extracted for image content representation. To tackle the problem of huge intraconcept visual diversity, multiple types of kernels are integrated to characterize the diverse visual similarity relationships between the images more precisely, and a multiple kernel learning algorithm is developed for SVM image classifier training. To address the problem of huge interconcept visua similarity, a novel multitask learning algorithm is developed to learn the correlated classifiers for the sibling image concepts under the same parent concept and enhance their discrimination and adaptation power significantly. To tackle the problem of huge intraconcept visual diversity for the image concepts at the higher levels of the concept ontology, a novel hierarchical boosting algorithm is developed to learn their ensemble classifiers hierarchically. In order to assist users on selecting more effective hypotheses for image classifier training, we have developed a novel hyperbolic framework for large-scale image visualization and interactive hypotheses assessment. Our experiments on large-scale image collections have also obtained very positive results. Index Terms—Concept ontology, hierarchical boosting, interactive hypotheses assessment, interconcept visual similarity, intraconcept visual diversity, multiple kernel learning, multitask learning. I.

This paper presents a novel method for image classification. It differs from previous approaches by computing image similarity based on region matching. Firstly, the images to be classified are segmented into regions or partitioned into regular blocks. Next, low-level features are extracted from each segment or block, and the similarity between two images is computed as the cost of a pairwise matching of regions according to their related features. Experiments are performed to verify that the proposed approach improves the quality of image classification. In addition, unsupervised clustering results are presented to verify the efficacy of this image similarity measure.

[A unifying review for optimization-oriented speech recognition]

We present a new technique that employs support vector machines (SVMs) and Gaussian mixture densities (GMDs) to create a generative/discriminative object classification technique using local image features. In the past, several approaches to fuse the advantages of generative and discriminative approaches were presented, often leading to improved robustness and recognition accuracy. Support vector machines are a well known discriminative classification framework but, similar to other discriminative approaches, suffer from a lack of robustness with respect to noise and overfitting. Gaussian mixtures, on the contrary, are a widely used generative technique. We present a method to directly fuse both approaches, effectively allowing to fully exploit the advantages of both. The fusion of SVMs and GMDs is done by representing SVMs in the framework of GMDs without changing the training and without changing the decision boundary. The new classifier is evaluated on the PASCAL VOC 2006 data. Additionally, we perform experiments on the USPS dataset and on four tasks from the UCI machine learning repository to obtain additional insights into the properties of the proposed approach. It is shown that for the relatively rare cases where SVMs have problems, the combined method outperforms both individual ones.

This documentation describes how to set up and execute the software package I designed and implemented for my Ph.D. research, object and concept recognition for Content-based Image Retrieval.