15833

14137

كارشناسي ارشد

مخابرات سيستم

اصفهان : دانشگاه صنعتي اصفهان

1399

هشت، 113ص.: مصور، جدول، نمودار

محمد رضا احمدزاده

ابوالقاسم زيدآبادي نژاد، سعيد حياتي

رسول اميرفتاحي، فرزانه شايق

1399/07/15

كتابنامه

مهندسي برق

مهندسي برق و كامپيوتر

1399/07/21

2637250

A New Texture descriptor based on Wave Interference in Non homogenous Environments Shima Zaghian s zaghian@ec iut ac ir 9 July 2020 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language Farsi Supervisor Dr Mohammad Reza Ahmadzadeh Ahmadzadeh@iut ac ir Abstract Image Retrieval is one of the most important topics in image processing and computer vision Proper Image Retrievalof an image requires the selection of suitable features that discriminate different images Besides ideal features must beinvariant to factors such as rotation scaling brightness and noise The features that are used mostly in image processinginclude color shape and texture The texture is an important feature among many types of images So far many approacheshave been proposed to describe the texture including statistical structural filters based and models based methods Thisthesis presents a novel wave interference based rotation invariant feature for texture description In local pattern basedtechniques features are extracted from small circularly symmetric neighboring points These features require further pro cessing to incorporate rotation invariance The proposed method in this thesis is based on wave interference signals ina non homogeneous environment The non homogeneousity of the environment at each pixel of an image depends on itsgrayscale Therefore this method is inherently invariant to any amount of rotation and needs no more operations for achiev ing rotation invariance Also the proposed method works well against brightness changes Brodatz and VisTex databaseshave been used to evaluate the performance of the proposed method in image retrieval The results show that the averageprecision of retrieving all images in each class for Brodatz R and Vistex R databases is 99 99 and 98 15 respectively In comparison the best results obtained by other methods in these two databases are 72 90 and 43 98 respectively Also to evaluate the performance of the proposed method in image classification the Outex database is used in which theaccuracy of the proposed method is 95 6 Key Words 1 Image Processing 2 Texture Descriptor 3 Image Retrieval 4 Local Feature

محمد رضا احمدزاده

ابوالقاسم زيدآبادي نژاد، سعيد حياتي

رسول اميرفتاحي، فرزانه شايق