Automatic cartoon generation by learning the style of an artist

Download
2012
Kuruoğlu, Betül
In this study, we suggest an algorithm for generating cartoons from face images automatically. The suggested method learns drawing style of an artist and applies this style to the face images in a database to create cartoons. The training data consists of a set of face images and corresponding cartoons, drawn by the same artist. Initially, a set of control points are labeled and indexed to characterize the face in the training data set for both images and corresponding caricatures. Then, their features are extracted to model the style of the artist. Finally, a similarity matrix of real face image set and the input image are constructed. With the help of the similarity matrix, Distance-Weighted Nearest Neighbor algorithm calculates the exaggeration coefficients which caricaturist would have designed for the input image in his mind. In caricature generation phase, Moving Least Squares algorithm is applied to distort the input image based on these coefficients. Caricatures generated by this approach successfully cover most of the caricaturist’s key characteristics in his drawing.

Suggestions

Camera auto-calibration using a sequence of 2D images with small rotations
Hassanpour, R; Atalay, Mehmet Volkan (Elsevier BV, 2004-07-02)
In this study, we describe an auto-calibration algorithm with fixed but unknown camera parameters. We have modified Triggs' algorithm to incorporate known aspect ratio and skew values to make it applicable for small rotation around a single axis. The algorithm despite being a quadratic one is easy to solve. We have applied the algorithm to some artificial objects with known size and dimensions for evaluation purposes. In addition, the accuracy of the algorithm has been verified using synthetic data. The des...
Extending Correlation Filter-Based Visual Tracking by Tree-Structured Ensemble and Spatial Windowing
Gundogdu, Erhan; Özkan, Huseyin; Alatan, Abdullah Aydın (Institute of Electrical and Electronics Engineers (IEEE), 2017-11-01)
Correlation filters have been successfully used in visual tracking due to their modeling power and computational efficiency. However, the state-of-the-art correlation filter-based (CFB) tracking algorithms tend to quickly discard the previous poses of the target, since they consider only a single filter in their models. On the contrary, our approach is to register multiple CFB trackers for previous poses and exploit the registered knowledge when an appearance change occurs. To this end, we propose a novel t...
Real-time arbitrary view rendering from stereo video and time-of-flight camere
Ateş, Tuğrul Kağan; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2010)
Generating in-between images from multiple views of a scene is a crucial task for both computer vision and computer graphics fields. Photorealistic rendering, 3DTV and robot navigation are some of many applications which benefit from arbitrary view synthesis, if it is achieved in real-time. Most modern commodity computer architectures include programmable processing chips, called Graphics Processing Units (GPU), which are specialized in rendering computer generated images. These devices excel in achieving h...
DDS based MIL-STD-1553B data bus interface simulation
Deniz, Ertan; Oğuztüzün, Mehmet Halit S.; Durak, Umut; Department of Computer Engineering (2012)
This thesis describes distributed simulation of MIL-STD-1553B Serial Data Bus interface and protocol based on the Data Distribution Service (DDS) middleware standard. The data bus connects avionics system components and transports information among them in an aircraft. It is important for system designers to be able to evaluate and verify their component interfaces at the design phase. The 1553 serial data bus requires specialized hardware and wiring to operate, thus it is expensive and complex to verify co...
Wavelet domain image resolution enhancement using cycle spinning and edge modelling
Temizel, Alptekin (2005-09-08)
In this paper we present a wavelet domain image resolution en-hancement algorithm. An initial high-resolution approximation to the original image is obtained by means of zero-padding in the wavelet domain. This is further processed using the cycle-spinning methodology which reduces ringing. A critical element of the algo-rithm is the adoption of a simplified edge profile suitable for the description of edge degradations such as blurring due to loss of resolution. Linear regression using a minimal training s...
Citation Formats
B. Kuruoğlu, “Automatic cartoon generation by learning the style of an artist,” M.S. - Master of Science, Middle East Technical University, 2012.