Generalization and localization based style imitation for grayscale images

Date

2003-01-01

Author

Nar, F
Cetin, A

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

45
views

0
downloads

An example based rendering (EBR) method based on generalization and localization that uses artificial neural networks (ANN) and k-Nearest Neighbor (k-NN) is proposed. The method involves learning phase and application phase, which means that once a transformation filter is learned, it can be applied to any other image. In learning phase, error back-propagation learning algorithm is used to learn general transformation filter using unfiltered source image and filtered output image. ANNs are usually unable to learn filter-generated textures and brush strokes hence these localized features are stored in a feature instance table for using with k-NN during application phase. In application phase, for any given grayscale image, first ANN is applied then k-NN search is used to retrieve local features from feature instances considering texture continuity to produce desired image. Proposed method is applied up to 40 image filters that are collection of computer-generated and human-generated effects/styles. Good results are obtained when image is composed of localized texture/style features that are only dependent to intensity values of pixel itself and its neighbors.

URI

https://hdl.handle.net/11511/66021

Journal

COMPUTER AND INFORMATION SCIENCES - ISCIS 2003

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

Conditional Random Fields for Land Use/Land Cover Classification and Complex Region Detection Can, Gulcan; Firat, Orhan; Yarman Vural, Fatoş Tunay (2012-11-09) Developing a complex region detection algorithm that is aware of its contextual relations with several classes necessitates statistical frameworks that can encode contextual relations rather than simple rule-based applications or heuristics. In this study, we present a conditional random field (CRF) model that is generated over the results of a robust local discriminative classifier in order to reveal contextual relations of complex objects and land use/land cover (LULC) classes. The proposed CRF model enco...
Meta Soft Label Generation for Noisy Labels Algan, Gorkem; Ulusoy, İlkay (2021-01-01) The existence of noisy labels in the dataset causes significant performance degradation for deep neural networks (DNNs). To address this problem, we propose a Meta Soft Label Generation algorithm called MSLG, which can jointly generate soft labels using meta-learning techniques and learn DNN parameters in an end-to-end fashion. Our approach adapts the meta-learning paradigm to estimate optimal label distribution by checking gradient directions on both noisy training data and noise-free meta-data. In order t...
Direction of arrival estimation for nonuniform linear arrays by using array interpolation Tuncer, Temel Engin; Friedlander, B. (2007-07-03) [1] A new approach is proposed for DOA estimation in nonuniform linear arrays (NLA) based on array interpolation. A Wiener formulation is presented to improve the condition number of the mapping matrix as well as the performance for noisy observations. Noniterative and iterative methods for DOA estimation are proposed. These methods use an initial DOA which is then significantly improved by the subsequent processing. Partially augmentable nonredundant arrays (PANA) and partly filled NLA (PFNLA) are consider...
Multi–target implementation of a domain specific language for extended feature models Demirtaş, Görkem; Oğuztüzün, Mehmet Halit S.; Department of Computer Engineering (2018) Translation of feature models to constraint logic programs is an effective method to enable their automated analysis using existing constraint solvers. More flexibility can be offered for building and application of analysis operations on extended feature models by providing a syntax and mechanism for interfacing the host solver with user defined constraint predicates. These constraints, such as global constraints, can be provided by the constraint solver runtime or by the translator itself as a part of the...
Gaussian graphical approaches in estimation of biological systems Ayyıldız, Ezgi; Purutçuoğlu Gazi, Vilda; Department of Statistics (2013) The Gaussian Graphical Model (GGM) is one of the well-known deterministic inference methods which is based on the conditional independency of nodes in the system. In this study we consider to implement this approach in small and relatively large networks under different singularity and sparsity conditions. In inference of these systems we perform lasso and L-1 penalized lasso regression approaches and select the best ﬁtted model to the data by using different criteria. Among many alternatives, we apply the ...

Citation Formats

F. Nar and A. Cetin, “Generalization and localization based style imitation for grayscale images,” COMPUTER AND INFORMATION SCIENCES - ISCIS 2003, pp. 465–473, 2003, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/66021.