Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 38 for “"Text-Image"”.
-
Text-image Restoration And Text Alignment For Multi-engine Optical Character Recognition Systems
… This thesis will focus on morphological image preprocessing and morphological text restoration that goes to OCR engines. This method is similar to the one used in restoration partial finger prints. Series of morphological dilating and eroding filters of various mask shapes and sizes were …
-
Cut, Paste, Patch: A Study of Text-Image Relationships in Safavid Single-Page Compositions
Even though the relationship between text and image in Timurid (1370–1507) and Safavid (1501–1722) illustrated manuscripts have been explored for the past several decades, the connection between painting and poetry in the single-page folios composed in the sixteenth and seventeenth centuries has …
-
The Third Story: An Exploration of Intergrating Ironic Counterpoint into the Multimodal Text-image Relationship of Children's Picturebooks
… the intricate multimodal interactions between text and image in children's picturebooks, with a particular emphasis on the implementation of "ironic counterpoint" as a narrative device. Recognizing the complexity inherent in multimodal narratives, this study aims to clarify how the interplay of …
-
Socio-Cultural Communication System--a Communication Mechanism For Multi-Media Information Access System for Non-Literate and Linguistically Diverse Users
… based on a web-browser. The client will send the text/image/audio/video request to the request interpreter (RI) and it will then process the request and respond with text, image, audio, or video link information. Audio/video is streamed using a streaming server. This helps in reducing the play …
-
Adaptive restoration of text images containing touching and broken characters
… are essential. However, distortions in document images cause character recognition errors, thereby, reducing the accuracy of OCR systems. In document images, most OCR errors are caused by broken and touching characters. This thesis presents an adaptive system to restore text images distorted by …
-
Unsupervised feature analysis for high dimensional big data
… unsupervised feature analysis, we focus on text-image web news data and propose a multi-view unsupervised feature selection method and a text-image topic model. Specifically, for single-view unsupervised feature selection, we propose a new method that is called Robust Unsupervised Feature …
-
Character recognition and information retrieval
… and information retrieval, that are used for text processing. Character recognition translates text image data to a computer-coded format; information retrieval stores these data and provides efficient access to the text. The necessity of their eventual coupling is obvious. Their sequential …
-
Review of steganalysis of digital images
… hidden messages into cover multimedia such as text, image, audio and video. Steganalysis is the counterpart of steganography, which wants to identify if there is data hidden inside a digital medium. In this study, some specific steganographic schemes such as HUGO and LSB are studied and the …
-
Effect of OCR errors on short documents
… short documents. OCR recognizes and translates text image into ASCII format. When this data is retrieved in response to a query, the retrieval performance depends on the efficiency of the OCR device used. Measures like recall, precision and ranking were used to gauge the retrieval performance. …
-
The Book as a Cultural Object: Exploring the Symbolism of Artist's Books
… artists are exploring how the interaction of text, image, typography, and design interact to effect the meaning of a book. This thesis explores the history of the book to see how the symbolic meanings associated with religion, politics, immortality and power developed, and how artists combine …
-
Application of multirate digital signal processing to image compression
… digital communication and digital processing of images and video, image compression is drawing considerable interest as a means of reducing computer storage and communication channels bandwidth requirements. This thesis presents a method for the compression of grayscale images which is based on …
-
M3D: Multimodal MultiDocument Fine-Grained Inconsistency Detection
… a set of multimodal documents, which include text, image(s), video(s), and audio(s). We also introduce a new benchmark (M^3DC) of claims requiring multimodal multidocument reasoning, which we construct using a novel claim synthesis technique. Experiments show that our approach significantly …
-
I want to tell you my name : augmented reality as conservation method for between words and images by Ernestine White-Mifetu and Toni Giselle Stuart
… preserve the various elements separately as text, image, or recording in stasis. AR as a conservation method allows the presentation of both reality and an altered version side-by-side, adding to what the viewer can already see. AR may thus be a modern solution to the ephemerality of …
-
A comparative, iconographic study of early-modern, religious emblems
… opposed notions, or manipulating the text/image relationship in quite different ways. Understanding how these emblems functioned, therefore, necessitates close reading, indeed, reading in the way the emblems were intended to be read. This study, therefore, will address the question of …
-
Mediating Gender Violence: "Witnessing Publics," Activism, and the Ethics of Human Rights Claim Making
… represent violence against indigenous women--in text, image, and action--as human rights "evidence." By ethics I mean the deliberate use of morals, stated or unstated, in the representation of human rights abuses. In New York, my research focuses on the production, launch, and circulation of a …
-
Geometric correction of historical Arabic documents
… are not sensitive to the characteristics of text in Arabic documents and therefore cannot be applied successfully. Text line segmentation and baseline detection algorithms have been investigated to propose a new more suitable one for warped Arabic historical document images. Advanced ideas …
-
Emergent Capabilities of Generative Models: “Software 3.0” and Beyond
… distance, metrics that are used to evaluate image synthesis quality. We then introduce a GAN framework, GANalyze, that allows one to make targeted manipulations to various cognitive attributes of GAN generated imagery, such as memorability and emotional valence, and use this framework to …
-
Son of Samurai, Daughter of Butterfly: fashioning Japan in the sartorial culture of the United Kingdom, 1980-2006
… sartorial culture is consumed in the form of text, image and artefact. A variety of methodological approaches are mobilised in the analysis of data from retail outlets, cultural institutions and media publications. Material pertaining to "high-concept designers" whose outputs are largely …
-
Multimodal Human Behavior Modeling: From Understanding to Generation
… In contrast with learning objects, scenes and textures, human behaviors are inherently purposeful, guided by underlying intentions and goals. Additionally, human behaviors involve precise and adaptive interactions with the environment, characterized by fine-grained and nuanced control. The two …
-
A grammar of sentiment thinking about sentimental jewellery towards making new art about love and loss.
… the sentimental artefact through development of text/image vocabularies that are conceived as providing a ‘grammar of sentiment’ through which to articulate aspects of human feeling. It is this exploration that constitutes my main contribution to knowledge.
Page 1 of 2