UMD Theses and Dissertations
Permanent URI for this collectionhttp://hdl.handle.net/1903/3
New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a given thesis/dissertation in DRUM.
More information is available at Theses and Dissertations at University of Maryland Libraries.
Browse
2 results
Search Results
Item DISCRIMINATIVE LEARNING AND RECOGNITION USING DICTIONARIES(2013) Chen, Yi-Chen; Chellappa, Rama; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)In recent years, the theory of sparse representation has emerged as a powerful tool for efficient processing of data in non-traditional ways. This is mainly due to the fact that most signals and images of interest tend to be sparse or compressible in some dictionary. In other words, they can be well approximated by a linear combination of a few elements (also known as atoms) of a dictionary. This dictionary can either be an analytic dictionary composed of wavelets or Fourier basis or it can be directly trained from data. It has been observed that dictionaries learned directly from data provide better representation and hence can improve the performance of many practical applications such as restoration and classification. In this dissertation, we study dictionary learning and recognition under supervised, unsupervised, and semi-supervised settings. In the supervised case, we propose an approach to recognize humans in unconstrained videos, where the main challenge is exploiting the identity information in multiple frames and the accompanying dynamic signature. These identity cues include face, body, and motion. Our approach is based on video-dictionaries for face and body. We design video-dictionaries to implicitly encode temporal, pose, and illumination information. Next, we propose a novel multivariate sparse representation method that jointly represents all the video data by a sparse linear combination of training data. To increase the ability of our algorithm to learn nonlinearities, we apply kernel methods to learn the dictionaries. Next, we address the problem of matching faces across changes in pose in unconstrained videos. Our approach consists of two methods based on 3D rotation and sparse representation that compensate for changes in pose. We demonstrate the superior performance of our approach over several state-of-the-art algorithms through extensive experiments on unconstrained video datasets. In the unsupervised case, we present an approach that simultaneously clusters images and learns dictionaries from the clusters. The method learns dictionaries in the Radon transform domain. The main feature of the proposed approach is that it provides in-plane rotation and scale invariant clustering, which is useful in many applications such as Content Based Image Retrieval (CBIR). We demonstrate through experiments that the proposed rotation and scale invariant clustering provides not only good retrieval performances but also substantial improvements and robustness compared to traditional Gabor-based and several state-of-the-art shape-based methods. We then extend the dictionary learning problem to a generalized semi-supervised formulation, where each training sample is provided with a set of possible labels and only one label among them is the true one. Such applications can be found in image and video collections where one often has only partially labeled data. For instance, given an image with multiple faces and a caption specifying the names, we can be sure that each of the faces belong to one of the names specified, while the exact identity of each face is not known. Labeling involves significant amount of human effort and is expensive. This has motivated researchers to develop learning algorithms from partially labeled training data. In this work, we develop dictionary learning algorithms that utilize such partially labeled data. The proposed method aims to solve the problem of ambiguously labeled multiclass-classification using an iterative algorithm. The dictionaries are updated using either soft (EM-based) or hard decision rules. Extensive evaluations on existing datasets demonstrate that the proposed method performs significantly better than state-of-the-art approaches for learning from ambiguously labeled data. As sparsity plays a major role in our research, we further present a sparse representation-based approach to find the salient views of 3D objects. The salient views are categorized into two groups. The first are boundary representative views that have several visible sides and object surfaces that may be attractive to humans. The second are side representative views that best represent side views of the approximating convex shape. The side representative views are class-specific views and possess the most representative power compared to other within-class views. Using the concept of characteristic view class, we first present a sparse representation-based approach for estimating the boundary representative views. With the estimated boundaries, we determine the side representative views based on a minimum reconstruction error criterion. Furthermore, to evaluate our method, we introduce the notion of geometric dictionaries built from salient views for applications in 3D object recognition, retrieval and sparse-to-full reconstruction. By a series of experiments on four publicly available 3D object datasets, we demonstrate the effectiveness of our approach over state-of-the-art algorithms and baseline methods.Item Nautilus: for flute/piccolo and computer-processed sound(2006-08-04) Chen, Yi-Chen; Gibson, Robert; Music; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Nautilus for flute/piccolo, and computer-processed sound was completed in the spring of 2006. The electronic score for the piece was realized in Computer Music Studio B at University of Maryland. As the title suggests, this piece is in some ways a musical representation of the structure of a chambered nautilus shell and the sound of this structure when one "listens" to the shell by holding near the ear. An analog to the spiral structure of the nautilus shell is created by using trills and rising and falling glissandi in the flute and the electronic score. Some extended techniques of the flute, such as tongue-stopped notes and "jet whistle" sounds create timbres that resemble speaking directly into a nautilus shell. Nautilus can be roughly divided into four sections: the first section, which is also the longest section, opens with long and expressive phrases, and gradually introduces shorter and more rhythmic figures. In the second section, the flutist changes to piccolo. This is the most energetic and intense section, even somewhat agitated at times. The third section is a flute solo. The rapid shifts between fast-run figures and lyrical phrases creates a contradictory feeling, and a sense of tension, which is eventually resolved in the last section. The last section is tranquil and recalls the character of the opening section, leading to the conclusion.