Content-Sensitive Screening in Black and White

Slides:



Advertisements
Similar presentations
Detection and Visualization of Defects in 3D Unstructured Models of Nematic Liquid Crystals Ketan Mehta* & T. J. Jankun-Kelly Viz Lab, Computer Science.
Advertisements

Wavelets Fast Multiresolution Image Querying Jacobs et.al. SIGGRAPH95.
Vision REU Week 3. Image registration  Used mutual information-based registration from ITK Ben SchoepkeREU Week 36/8/07 Fixed imageMoving image Pre-registrationPost-registration.
Contrast-Aware Halftoning Hua Li and David Mould April 22,
Prénom Nom Document Analysis: Document Image Processing Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
LING 111 Teaching Demo By Tenghui Zhu Introduction to Edge Detection Image Segmentation.
EI San Jose, CA Slide No. 1 Measurement of Ringing Artifacts in JPEG Images* Xiaojun Feng Jan P. Allebach Purdue University - West Lafayette, IN.
Color and Color Perception. a physicists view of color…
IEEE TCSVT 2011 Wonjun Kim Chanho Jung Changick Kim
Modeling Pixel Process with Scale Invariant Local Patterns for Background Subtraction in Complex Scenes (CVPR’10) Shengcai Liao, Guoying Zhao, Vili Kellokumpu,
Image Quilting for Texture Synthesis and Transfer Alexei A. Efros1,2 William T. Freeman2.
Introduction to Image Quality Assessment
WORD-PREDICTION AS A TOOL TO EVALUATE LOW-LEVEL VISION PROCESSES Prasad Gabbur, Kobus Barnard University of Arizona.
Half Toning. Continuous Half Toning Color Half Toning.
An Iterative Optimization Approach for Unified Image Segmentation and Matting Hello everyone, my name is Jue Wang, I’m glad to be here to present our paper.
Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.
HP - PURDUE CONFIDENTIAL Slide No. Fundamentals 1.
Input: Original intensity image. Target intensity image (i.e. a value sketch). Using Value Images to Adjust Intensity in 3D Renderings and Photographs.
Entropy and some applications in image processing Neucimar J. Leite Institute of Computing
Structure and Aesthetics in Non- Photorealistic Images Hua Li, David Mould, and Jim Davies Carleton University.
Introduction to electrical and computer engineering Jan P. Allebach School of Electrical and Computer Engineering
Screen Ruling, Print Resolution AM, FM and Hybrid Halftoning Sasan Gooran Linköping University LiU-Norrköping.
Clustered-dot-ordered Dither Bui Hai Thanh. Introduction Ordered dither Fixed pattern of number (halftone cell) Two approaches Dispersed: turn on the.
IDL GUI for Digital Halftoning Final Project for SIMG-726 Computing For Imaging Science Changmeng Liu
2/3/04© University of Wisconsin, CS559 Spring 2004 Last Time Color –Transforming between two color spaces –A gamut is the set of displayable colors in.
1 Mean shift and feature selection ECE 738 course project Zhaozheng Yin Spring 2005 Note: Figures and ideas are copyrighted by original authors.
Introduction to Visible Watermarking IPR Course: TA Lecture 2002/12/18 NTU CSIE R105.
City University of Hong Kong 18 th Intl. Conf. Pattern Recognition Self-Validated and Spatially Coherent Clustering with NS-MRF and Graph Cuts Wei Feng.
Multiscale Moment-Based Painterly Rendering Diego Nehab and Luiz Velho
Supervised Learning of Edges and Object Boundaries Piotr Dollár Zhuowen Tu Serge Belongie.
Stylization and Abstraction of Photographs Doug Decarlo and Anthony Santella.
EECS 274 Computer Vision Segmentation by Clustering II.
Scene Completion Using Millions of Photographs James Hays, Alexei A. Efros Carnegie Mellon University ACM SIGGRAPH 2007.
Associative Hierarchical CRFs for Object Class Image Segmentation
Image Emotional Semantic Query Based On Color Semantic Description Wei-Ning Wang, Ying-Lin Yu Department of Electronic and Information Engineering, South.
Non-Ideal Iris Segmentation Using Graph Cuts
What color does this represent? Each of these dots represents a PIXEL … a dot of color on a screen.
3-1 Chapter 3: Image Display The goodness of display of an image depends on (a) Image quality: i) Spatial resolution, ii) Quantization (b) Display device:
Machine Vision ENT 273 Regions and Segmentation in Images Hema C.R. Lecture 4.
Tree-Structured Method for LUT Inverse Halftoning IEEE Transactions on Image Processing June 2002.
Thresholding and Segmenting Objects The overall objective of image processing operations is to extract the objects of interest and to distinguish them.
Error Diffusion (ED) Li Yang Campus Norrköping (ITN), University of Linköping.
Contrast-Enhanced Black and White Images Hua Li and David Mould UNC Wilmington and Carleton University Presented by Ling Xu
Edge Preserving Spatially Varying Mixtures for Image Segmentation Giorgos Sfikas, Christophoros Nikou, Nikolaos Galatsanos (CVPR 2008) Presented by Lihan.
Shadow Detection in Remotely Sensed Images Based on Self-Adaptive Feature Selection Jiahang Liu, Tao Fang, and Deren Li IEEE TRANSACTIONS ON GEOSCIENCE.
Multiple Organ detection in CT Volumes Using Random Forests
Edge Detection using Mean Shift Smoothing
Structure and Aesthetics in Non-Photorealistic Images
Data Mining, Neural Network and Genetic Programming
Spatio-temporal Segmentation of Video by Hierarchical Mean Shift Analysis Daniel DeMenthon SMVP 2002.
1.3 Error Diffusion – Basic Concepts
Lossy Compression of Stochastic Halftones with JBIG2
Tone Dependent Color Error Diffusion
Multi-Class Error-Diffusion with Blue-Noise Property
Graphic Design & Illustration
School of Electrical and
School of Electrical and
Combining Sketch and Tone for Pencil Drawing Production
Tone Dependent Color Error Diffusion
Outline Announcement Texture modeling - continued Some remarks
Dingding Liu* Yingen Xiong† Linda Shapiro* Kari Pulli†
DIGITAL HALFTONING Sasan Gooran.
A Review in Quality Measures for Halftoned Images
Contrast-Aware Halftoning
Aline Martin ECE738 Project – Spring 2005
What Color is it?.
Tone Dependent Color Error Diffusion Halftoning
Gradient Domain Salience-preserving Color-to-gray Conversion
The Image The pixels in the image The mask The resulting image 255 X
Fig. 5 Curve and graph data processing workflows and their representative 3D-printed models. Curve and graph data processing workflows and their representative.
Presentation transcript:

Content-Sensitive Screening in Black and White Hua Li and David Mould Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Outline Introduction Previous Work Our Method Discussion and Future Work Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Introduction Screening A process for printing by passing ink through a perforated screen (or pattern) over a region. Screen2 Screen1 Pattern2 Pattern1 Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Previous Methods Original Image Our Type I (Main Direction) Dithering Method (Ulichney, 1987) Manga Screening (grayscale) (Qu et al., 2008) Our Type I (Edge-exclusion) Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Motivated by Contrast-Aware Halftoning An variant of error diffusion algorithm The contrast-aware weight distribution The priority-based scheme Original Image Our Contrast-Aware Halftoning [Li and Mould 2010] Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Overview of Our Method Pattern Assignment OR Pattern Generation Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

PartI: Pattern Assignment Green: medium degree of content White: background trivial area Mean-shift segmentation [Comaniciu and Meer, 2002] Gradient map Yellow: uniform regions Blue: highly textured Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Our Method—Pattern Generation (I) Type I: Exclusion-based Masks Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Our Method—Pattern Generation (I) Type I: Tone changes Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Our Method—Pattern Generation (I) Random assignment without content consideration Edge-exclusion Type I: Main direction Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Dithering Manga Screening Our Type I 2018/11/9

Our Method—Pattern Generation (II) (a)Pixels on pattern edges from input images (b)Pixels on ETF feature edges ( c) The rest pixels A multi-stage process Stage I: Stage II: Stage III: Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Our Type II Dithering Method Manga Screening Our Type I Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

More Comparisons: Manga Screening Our Type II Our Type II Our Type I Dithering Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Discussion Both structure-preserving screening with natural looking. An automatic method. Powerful extensions from the multi-stage process. Performance: faster than manga screening. Open to color extensions. Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Future Work Refine the content-sensitive assignment and improve the multi-stage process; Introduce high-quality patterns into our method; Extend to color screening. Presented by Hua Li hli1@connect.carleton.ca 2018/11/9

Acknowledgement Thanks to: permission to use their original images and their results from Yingge Qu; grants from NSERC and Carleton University. Presented by Hua Li hli1@connect.carleton.ca 2018/11/9