Object recognition and segmentation via shape models

Altınoklu, Metin Burak
In this thesis, the problem of object detection, recognition and segmentation in computer vision is addressed with shape based methods. An efficient object detection method based on a sparse skeleton has been proposed. The proposed method is an improved chamfer template matching method for recognition of articulated objects. Using a probabilistic graphical model structure, shape variation is represented in a skeletal shape model, where nodes correspond to parts consisting of lines and edges correspond to pairwise relation between parts. For edge support function of lines, directional chamfer matching cost is calculated. The performance of the new method has been evaluated with experiments using databases especially suitable for shape based object detection methods. The proposed method performs well, and it is much faster as compared to related methods.


Hierarchical representations for visual object tracking by detection
Beşbınar, Beril; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2015)
Deep learning is the discipline of training computational models that are composed of multiple layers and these methods have improved the state of the art in many areas such as visual object detection, scene understanding or speech recognition. Rebirth of these fairly old computational models is usually related to the availability of large datasets, increase in the computational power of current hardware and more recently proposed unsupervised training methods that exploit the internal structure of very lar...
Visual object detection and tracking using local convolutional context features and recurrent neural networks
Kaya, Emre Can; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2018)
Visual object detection and tracking are two major problems in computer vision which have important real-life application areas. During the last decade, Convolutional Neural Networks (CNNs) have received significant attention and outperformed methods that rely on handcrafted representations in both detection and tracking. On the other hand, Recurrent Neural Networks (RNNs) are commonly preferred for modeling sequential data such as video sequences. A novel convolutional context feature extension is introduc...
Shape : representation, description, similarity and recognition
Arıca, Nafiz; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2003)
In this thesis, we study the shape analysis problem and propose new methods for shape description, similarity and recognition. Firstly, we introduce a new shape descriptor in a two-step method. In the first step, the 2-D shape information is mapped into a set of 1-D functions. The mapping is based on the beams, which are originated from a boundary point, connecting that point with the rest of the points on the boundary. At each point, the angle between a pair of beams is taken as a random variable to define...
Edge strength functions as shape priors in image segmentation
Erdem, Erkut; Erdem, Aykut; Tarı, Zehra Sibel (2005-12-01)
Many applications of computer vision requires segmenting out of an object of interest from a given image. Motivated by unlevel-sets formulation of Raviv, Kiryati and Sochen [8] and statistical formulation of Leventon, Grimson and Faugeras [6], we present a new image segmentation method which accounts for prior shape information. Our method depends on Ambrosio-Tortorelli approximation of Mumford-Shah functional. The prior shape is represented by a by-product of this functional, a smooth edge indicator functi...
Part-based data-driven shape interpolation
Aydınlılar, Melike; Sahillioğlu, Yusuf; Department of Computer Engineering (2018)
An active problem in digital geometry processing is shape interpolation which aims to generate a continuous sequence of in-betweens for a given source and target shape. Unlike traditional approaches that interpolate source and target shapes in isolation, recent data-driven approaches utilize multiple interpolations through intermediate database shapes, and consequently perform better at the expense of a database requirement. In contrast to the existing data-driven approaches that consider intermediate shape...
Citation Formats
M. B. Altınoklu, “Object recognition and segmentation via shape models,” Ph.D. - Doctoral Program, Middle East Technical University, 2016.