Current Search:   Zolghadr, Esfandiar (x)

View All Items

  • CSV Spreadsheet
(1 - 2 of 2)
Context-based Image Concept Detection and Annotation
Title
Context-based Image Concept Detection and Annotation.
Creator
Zolghadr, Esfandiar, Furht, Borko, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description
Scene understanding attempts to produce a textual description of visible and latent concepts in an image to describe the real meaning of the scene. Concepts are either objects, events or relations depicted in an image. To recognize concepts, the decision of object detection algorithm must be further enhanced from visual similarity to semantical compatibility. Semantically relevant concepts convey the most consistent meaning of the scene. Object detectors analyze visual properties (e.g., pixel...
Show moreScene understanding attempts to produce a textual description of visible and latent concepts in an image to describe the real meaning of the scene. Concepts are either objects, events or relations depicted in an image. To recognize concepts, the decision of object detection algorithm must be further enhanced from visual similarity to semantical compatibility. Semantically relevant concepts convey the most consistent meaning of the scene. Object detectors analyze visual properties (e.g., pixel intensities, texture, color gradient) of sub-regions of an image to identify objects. The initially assigned objects names must be further examined to ensure they are compatible with each other and the scene. By enforcing inter-object dependencies (e.g., co-occurrence, spatial and semantical priors) and object to scene constraints as background information, a concept classifier predicts the most semantically consistent set of names for discovered objects. The additional background information that describes concepts is called context. In this dissertation, a framework for building context-based concept detection is presented that uses a combination of multiple contextual relationships to refine the result of underlying feature-based object detectors to produce most semantically compatible concepts. In addition to the lack of ability to capture semantical dependencies, object detectors suffer from high dimensionality of feature space that impairs them. Variances in the image (i.e., quality, pose, articulation, illumination, and occlusion) can also result in low-quality visual features that impact the accuracy of detected concepts. The object detectors used to build context-based framework experiments in this study are based on the state-of-the-art generative and discriminative graphical models. The relationships between model variables can be easily described using graphical models and the dependencies and precisely characterized using these representations. The generative context-based implementations are extensions of Latent Dirichlet Allocation, a leading topic modeling approach that is very effective in reduction of the dimensionality of the data. The discriminative contextbased approach extends Conditional Random Fields which allows efficient and precise construction of model by specifying and including only cases that are related and influence it. The dataset used for training and evaluation is MIT SUN397. The result of the experiments shows overall 15% increase in accuracy in annotation and 31% improvement in semantical saliency of the annotated concepts.
Show less
Date Issued
2016
PURL
http://purl.flvc.org/fau/fd/FA00004745, http://purl.flvc.org/fau/fd/FA00004745
Subject Headings
Computer vision--Mathematical models., Pattern recognition systems., Information visualization., Natural language processing (Computer science), Multimodal user interfaces (Computer systems), Latent structure analysis., Expert systems (Computer science)
Format
Document (PDF)
Application of wavelets to image and video coding
Title
Application of wavelets to image and video coding.
Creator
Zolghadr, Esfandiar, Florida Atlantic University, Furht, Borko, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description
In this thesis we applied wavelet transforms to image and video coding. First, a survey of various wavelets and their features is presented, including continuous, discrete, and orthogonal wavelets. Theories and concepts underlying one and two-dimensional wavelet transforms are introduced and compared to Fourier transform and sub-band coding. The core of the thesis is the implementation of two-dimensional and three-dimensional codec architectures and their application to coding images and...
Show moreIn this thesis we applied wavelet transforms to image and video coding. First, a survey of various wavelets and their features is presented, including continuous, discrete, and orthogonal wavelets. Theories and concepts underlying one and two-dimensional wavelet transforms are introduced and compared to Fourier transform and sub-band coding. The core of the thesis is the implementation of two-dimensional and three-dimensional codec architectures and their application to coding images and videos, respectively. We studied performance of the wavelet codec by comparing it to DCT and JPEG coding techniques. We applied these techniques for compression of a variety of test images and videos. We also analyzed the adaptability and scalability of 2D and 3D codec. Experimental results, presented in the thesis, illustrate the superior performance of wavelets compared to other coding techniques.
Show less
Date Issued
2003
PURL
http://purl.flvc.org/fcla/dt/13050
Subject Headings
Wavelets (Mathematics), Image compression, JPEG (Image coding standard)
Format
Document (PDF)