A hierarchical object localization and image retrieval framework

Download
2006
Uysal, Mutlu
This thesis proposes an object localization and image retrieval framework, which trains a discriminative feature set for each object class. For this purpose, a hierarchical learning architecture, together with a Neighborhood Tree is introduced for object labeling. Initially, a large variety of features are extracted from the regions of the pre-segmented images. These features are, then, fed to the training module, which selects the "best set of representative features", suppressing relatively less important ones for each class. During this study, we attack various problems of the current image retrieval and classification systems, including feature space design, normalization and curse of dimensionality. Above all, we elaborate the semantic gap problem in comparison to human visual system. The proposed system emulates the eye-brain channel in two layers. The first layer combines relatively simple classifiers with low level, low dimensional features. Then, the second layer implements Adaptive Resonance Theory, which extracts higher level information from the first layer. This two-layer architecture reduces the curse of dimensionality and diminishes the normalization problem. The concept of Neighborhood Tree is introduced for identifying the whole object from the over-segmented image regions. The Neighborhood Tree consists of the nodes corresponding to the neighboring regions as its children and merges the regions through a search algorithm. Experiments are performed on a set of images from Corel database, using MPEG-7, Haar and Gabor features in order to observe the power and the weakness of the proposed system. The "Best Representative Features" are found in the training phase using Fuzzy ARTMAP [1], Feature-based AdaBoost [2], Descriptor-based AdaBoost, Best Representative Descriptor [3], majority voting and the proposed hierarchical learning architecture. During the

Suggestions

An image retrieval system based on region classification
Özcanli-Özbay, Özge Can; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2004)
In this thesis, a Content Based Image Retrieval (CBIR) system to query the objects in an image database is proposed. Images are represented as collections of regions after being segmented with Normalized Cuts algorithm. MPEG-7 content descriptors are used to encode regions in a 239-dimensional feature space. User of the proposed CBIR system decides which objects to query and labels exemplar regions to train the system using a graphical interface. Fuzzy ARTMAP algorithm is used to learn the mapping between f...
Semantic service discovery with heuristic relevance calculation
Özyönüm, Müge; Doğru, Ali Hikmet; Department of Computer Engineering (2010)
In this thesis, a semantically aided web service and restful service search mechanism is presented that makes use of an ontology. The mechanism relates method names, input and output parameters for ontology guided matches and offers results with varying relevance corresponding to the matching degree. The mechanism is demonstrated using an experimental domain that is tourism and travel. An ontology is created to support a set of web services that exist in this domain.
A simulation tool for mc6811
Sarıkan (Tuncer), Nazlı; Güran, Hasan; Department of Electrical and Electronics Engineering (2004)
The aim of this thesis study is to develop a simulator for an 8-bit microcontroller and the written document of this thesis study analyses the process of devoloping a software for simulating an 8 bit microcontroller, MC68HC11. In this simulator study a file processing including the parsing of the assembler code and the compilation of the parsed instructions is studied. Also all the instruction execution process containing the cycle and instruction execution and the interrupt routine execution is observed th...
A Static analysis approach for service oriented software engineering (SOSE) designs
Çermikli, Can; Doğru, Ali Hikmet; Department of Computer Engineering (2010)
In this thesis, a static analysis approach is introduced in order to develop correct business processes according to the Web Service Business Process Execution Language (WS-BPEL) specification. The modeling of the business processes are conducted with Business Process Execution Language (BPEL) which is a popular orchestrator of Service Oriented Architectures (SOA) based system through the description of workflow. This approach is also integrated to the Service Oriented Software Engineering (SOSE) design tec...
Extended Target Tracking Using Polynomials With Applications to Road-Map Estimation
Lundquist, Christian; Orguner, Umut; Gustafsson, Fredrik (Institute of Electrical and Electronics Engineers (IEEE), 2011-01-01)
This paper presents an extended target tracking framework which uses polynomials in order to model extended objects in the scene of interest from imagery sensor data. State-space models are proposed for the extended objects which enables the use of Kalman filters in tracking. Different methodologies of designing measurement equations are investigated. A general target tracking algorithm that utilizes a specific data association method for the extended targets is presented. The overall algorithm must always ...
Citation Formats
M. Uysal, “A hierarchical object localization and image retrieval framework,” Ph.D. - Doctoral Program, Middle East Technical University, 2006.