It is known that image comparison can prove cumbersome in both computational complexity and runtime, due to factors such as the rotation, scaling, and translation of the object in question. Due to the locality of Krawtchouk polynomials, relatively few descriptors are necessary to describe a given image, and this can be achieved with minimal memory usage. Using this method, not only can images be described efficiently as a whole, but specific regions of images can be described as well without cropping. Due to this property, queries can be found within a single large image, or collection of large images, which serve as a database for search. Krawtchouk descriptors can also describe collections of patches of 3D objects, which is explored in this paper, as well as a theoretical methodology of describing nD hyperobjects. Test results for an implementation of 3D Krawtchouk descriptors in GNU Octave, as well as statistics regarding effectiveness and runtime, are included, and the code used for testing will be published open source in the near future.
","abstract_html":"<p>It is known that image comparison can prove cumbersome in both computational complexity and runtime, due to factors such as the rotation, scaling, and translation of the object in question. Due to the locality of Krawtchouk polynomials, relatively few descriptors are necessary to describe a given image, and this can be achieved with minimal memory usage. Using this method, not only can images be described efficiently as a whole, but specific regions of images can be described as well without cropping. Due to this property, queries can be found within a single large image, or collection of large images, which serve as a database for search. Krawtchouk descriptors can also describe collections of patches of 3D objects, which is explored in this paper, as well as a theoretical methodology of describing nD hyperobjects. Test results for an implementation of 3D Krawtchouk descriptors in GNU Octave, as well as statistics regarding effectiveness and runtime, are included, and the code used for testing will be published open source in the near future. </p>","abstract_has_math":false,"creators":["DeVille, Julian"],"institution":"Eastern Kentucky University","degree_name":"Master of Science (MS)","degree_level":"Master's","degree_discipline":"Mathematics and Statistics","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-01-01T08:00:00Z","date_published":"2019-01-01T08:00:00Z","updated_at":"2026-07-24T02:15:47Z","subjects":["Artificial Intelligence","Bioinformatics","Computer Vision","Image Processing","Krawtchouk","Machine Learning","Computer Sciences","Partial Differential Equations"],"languages":[],"rights":["Copyright 2019 Julian DeVille"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://encompass.eku.edu/etd/605","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["DeVille, Julian"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:publisher","label":"Institution","values":["Encompass Digital Archive, Eastern Kentucky University"]},{"key":"dc:type","label":"Dc Type","values":["Master Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Mathematics and Statistics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Master's"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Eastern Kentucky University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial Intelligence","Bioinformatics","Computer Vision","Image Processing","Krawtchouk","Machine Learning","Computer Sciences","Partial Differential Equations"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2019 Julian DeVille"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://encompass.eku.edu/etd/605"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["It is known that image comparison can prove cumbersome in both computational complexity and runtime, due to factors such as the rotation, scaling, and translation of the object in question. Due to the locality of Krawtchouk polynomials, relatively few descriptors are necessary to describe a given image, and this can be achieved with minimal memory usage. Using this method, not only can images be described efficiently as a whole, but specific regions of images can be described as well without cropping. Due to this property, queries can be found within a single large image, or collection of large images, which serve as a database for search. Krawtchouk descriptors can also describe collections of patches of 3D objects, which is explored in this paper, as well as a theoretical methodology of describing nD hyperobjects. Test results for an implementation of 3D Krawtchouk descriptors in GNU Octave, as well as statistics regarding effectiveness and runtime, are included, and the code used for testing will be published open source in the near future.
"]},{"key":"dc:format","label":"Dc Format","values":["application/PDF"]},{"key":"dc:source","label":"Dc Source","values":["Encompass Digital Archive: Online Theses and Dissertations"]},{"key":"dc:title","label":"Title","values":["Efficient Local Comparison Of Images Using Krawtchouk Descriptors"]}]}],"canonical_facts":{"dc:creator":["DeVille, Julian"],"dc:description.abstract":["It is known that image comparison can prove cumbersome in both computational complexity and runtime, due to factors such as the rotation, scaling, and translation of the object in question. Due to the locality of Krawtchouk polynomials, relatively few descriptors are necessary to describe a given image, and this can be achieved with minimal memory usage. Using this method, not only can images be described efficiently as a whole, but specific regions of images can be described as well without cropping. Due to this property, queries can be found within a single large image, or collection of large images, which serve as a database for search. Krawtchouk descriptors can also describe collections of patches of 3D objects, which is explored in this paper, as well as a theoretical methodology of describing nD hyperobjects. Test results for an implementation of 3D Krawtchouk descriptors in GNU Octave, as well as statistics regarding effectiveness and runtime, are included, and the code used for testing will be published open source in the near future.
"],"dc:format":["application/PDF"],"dc:identifier":["https://encompass.eku.edu/etd/605"],"dc:publisher":["Encompass Digital Archive, Eastern Kentucky University"],"dc:rights":["Copyright 2019 Julian DeVille"],"dc:source":["Encompass Digital Archive: Online Theses and Dissertations"],"dc:subject":["Artificial Intelligence","Bioinformatics","Computer Vision","Image Processing","Krawtchouk","Machine Learning","Computer Sciences","Partial Differential Equations"],"dc:title":["Efficient Local Comparison Of Images Using Krawtchouk Descriptors"],"dc:type":["Master Thesis"],"thesis:degree_discipline":["Mathematics and Statistics"],"thesis:degree_level":["Master's"],"thesis:degree_name":["Master of Science (MS)"],"thesis:institution_name":["Eastern Kentucky University"]},"updated_at":"2026-07-24T02:15:47Z"}