Computer Science Theses and Dissertations
Permanent URI for this collectionhttp://hdl.handle.net/1903/2756
Browse
2 results
Search Results
Item Learning Binary Code Representations for Effective and Efficient Image Retrieval(2016) Ozdemir, Bahadir; Davis, Larry S; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)The size of online image datasets is constantly increasing. Considering an image dataset with millions of images, image retrieval becomes a seemingly intractable problem for exhaustive similarity search algorithms. Hashing methods, which encodes high-dimensional descriptors into compact binary strings, have become very popular because of their high efficiency in search and storage capacity. In the first part, we propose a multimodal retrieval method based on latent feature models. The procedure consists of a nonparametric Bayesian framework for learning underlying semantically meaningful abstract features in a multimodal dataset, a probabilistic retrieval model that allows cross-modal queries and an extension model for relevance feedback. In the second part, we focus on supervised hashing with kernels. We describe a flexible hashing procedure that treats binary codes and pairwise semantic similarity as latent and observed variables, respectively, in a probabilistic model based on Gaussian processes for binary classification. We present a scalable inference algorithm with the sparse pseudo-input Gaussian process (SPGP) model and distributed computing. In the last part, we define an incremental hashing strategy for dynamic databases where new images are added to the databases frequently. The method is based on a two-stage classification framework using binary and multi-class SVMs. The proposed method also enforces balance in binary codes by an imbalance penalty to obtain higher quality binary codes. We learn hash functions by an efficient algorithm where the NP-hard problem of finding optimal binary codes is solved via cyclic coordinate descent and SVMs are trained in a parallelized incremental manner. For modifications like adding images from an unseen class, we propose an incremental procedure for effective and efficient updates to the previous hash functions. Experiments on three large-scale image datasets demonstrate that the incremental strategy is capable of efficiently updating hash functions to the same retrieval performance as hashing from scratch.Item IMAGE RETRIEVAL BASED ON COMPLEX DESCRIPTIVE QUERIES(2011) Siddiquie, Behjat; DAVIS, LARRY S; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)The amount of visual data such as images and videos available over web has increased exponentially over the last few years. In order to efficiently organize and exploit these massive collections, a system, apart from being able to answer simple classification based questions such as whether a specific object is present (or absent) in an image, should also be capable of searching images and videos based on more complex descriptive questions. There is also a considerable amount of structure present in the visual world which, if effectively utilized, can help achieve this goal. To this end, we first present an approach for image ranking and retrieval based on queries consisting of multiple semantic attributes. We further show that there are significant correlations present between these attributes and accounting for them can lead to superior performance. Next, we extend this by proposing an image retrieval framework for descriptive queries composed of object categories, semantic attributes and spatial relationships. The proposed framework also includes a unique multi-view hashing technique, which enables query specification in three different modalities - image, sketch and text. We also demonstrate the effectiveness of leveraging contextual information to reduce the supervision requirements for learning object and scene recognition models. We present an active learning framework to simultaneously learn appearance and contextual models for scene understanding. Within this framework we introduce new kinds of labeling questions that are designed to collect appearance as well as contextual information and which mimic the way in which humans actively learn about their environment. Furthermore we explicitly model the contextual interactions between the regions within an image and select the question which leads to the maximum reduction in the combined entropy of all the regions in the image (image entropy).