Design and implementation of a novel visual analysis system for image clasiffication

Altintakan, Ümit Lütfü
Possibilities offered by the technology to create, share and disseminate image and video data have resulted in a rapid increase in the available visual data. However, the data is useless unless it is effectively accessed, which necessitates the semantic analysis of visual data. In this dissertation, we present a novel visual analysis system along with its application to image classification problem. We aim to address the challenges in the area originated from the semantic gap, and to facilitate the research efforts in the extraction of high-level semantic information from images. Our system differs from existing works, and contributes to the area in several aspects: A complete visual analysis system in an integrated architecture, a novel fuzzy learning approach in classifier training, a unique feature weighting scheme, a probabilistic classification method, a new high-level classifier fusion, and a new bag-of words model are some of the key contributions introduced in this dissertation. The experiments conducted on benchmark datasets have shown that our approaches can significantly improve the performance in image classification.


Alignment of uncalibrated images for multi-view classification
Arık, Sercan Ömer; Vural, Elif; Frossard, Pascal (2011-12-29)
Efficient solutions for the classification of multi-view images can be built on graph-based algorithms when little information is known about the scene or cameras. Such methods typically require a pairwise similarity measure between images, where a common choice is the Euclidean distance. However, the accuracy of the Euclidean distance as a similarity measure is restricted to cases where images are captured from nearby viewpoints. In settings with large transformations and viewpoint changes, alignment of im...
A Shadow based trainable method for building detection in satellite images
Dikmen, Mehmet; Halıcı, Uğur; Department of Geodetic and Geographical Information Technologies (2014)
The purpose of this thesis is to develop a supervised building detection and extraction algorithm with a shadow based learning method for high-resolution satellite images. First, shadow segments are identified on an over-segmented image, and then neighboring shadow segments are merged by assuming that they are cast by a single building. Next, these shadow regions are used to detect the candidate regions where buildings most likely occur. Together with this information, distance to shadows towards illuminati...
Analysis of nanoparticle Transmission Electron Microscopy data using a public-domain image-processing program, Image
Woehrle, GH; Hutchison, JE; Özkar, Saim; Finke, RG (2006-01-01)
The need to easily and quickly count larger numbers of nanoparticles, in order to obtain statistically useful size and size-distribution data, is addressed via the use of a readily available, free, public-domain program for particle counting, NIH-Image (and 2 others derived from it, Scion Image and Image J), collectively referred to herein as Image. The best protocols that we have found useful for the use of Image are reported; both appropriate as well as problematic applications of Image are then illustrat...
Camera electronics and image enhancement software for infrared detector arrays
Küçükkömürler, Alper; Akın, Tayfun; Department of Environmental Engineering (2012)
This thesis aims to design and develop camera electronics and image enhancement software for infrared detector arrays. It first discusses the camera electronics suitable for infrared detector arrays, then it concentrates on image enhancement software that are implemented including defective pixel correction, contrast enhancement, noise reduction and pseudo coloring. After that, testing and results of the implemented algorithms were presented. Camera electronics and circuit operation frequency are selected c...
Implement of three segmentation algorithms for CT images of torso
Öz, Sinan; Serinağaoğlu Doğrusöz, Yeşim; Department of Electrical and Electronics Engineering (2011)
Many practical applications in the field of medical image processing require valid and reliable segmentation of images. In this dissertation, we propose three different semi-automatic segmentation frameworks for 2D-upper torso medical images to construct 3D geometric model of the torso structures. In the first framework, an extended version of the Otsu’s method for three level thresholding and a recursive connected component algorithm are combined. The segmentation process is accomplished by first using Ext...
Citation Formats
Ü. L. Altintakan, “Design and implementation of a novel visual analysis system for image clasiffication,” Ph.D. - Doctoral Program, Middle East Technical University, 2013.