Image and Video Abstraction by Coherence‐Enhancing Filtering

Henry Kang; Jan Eric Kyprianidis

doi:10.1111/j.1467-8659.2011.01882.x

Image and Video Abstraction by Coherence‐Enhancing Filtering

Henry Kang, Jan Eric Kyprianidis

University of Missouri-St. Louis

Research output: Contribution to journal › Article › peer-review

Abstract

<div class="line" id="line-11"> <span style='color: rgb(28, 29, 30); font-family: "Open Sans", icomoon, sans-serif; font-size: 16px;'> In this work, we present a non&hyphen;photorealistic rendering technique to create stylized abstractions from color images and videos. Our approach is based on adaptive line integral convolution in combination with directional shock filtering. The smoothing process regularizes directional image features while the shock filter provides a sharpening effect. Both operations are guided by a flow field derived from the structure tensor. To obtain a high&hyphen;quality flow field, we present a novel smoothing scheme for the structure tensor based on Poisson's equation. Our approach effectively regularizes anisotropic image regions while preserving the overall image structure and achieving a consistent level of abstraction. Moreover, it is suitable for per&hyphen;frame filtering of video and can be efficiently implemented to process content in real&hyphen;time. </span></div>

Original language	American English
Journal	Computer Graphics Forum
Volume	30
DOIs	https://doi.org/10.1111/j.1467-8659.2011.01882.x
State	Published - Apr 2011

Disciplines

Computer Sciences

Access to Document

10.1111/j.1467-8659.2011.01882.xLicense: Unspecified

Cite this

@article{72069efc16e24ecc8cf051af29152c6a,

title = "Image and Video Abstraction by Coherence‐Enhancing Filtering",

abstract = " In this work, we present a non&hyphen;photorealistic rendering technique to create stylized abstractions from color images and videos. Our approach is based on adaptive line integral convolution in combination with directional shock filtering. The smoothing process regularizes directional image features while the shock filter provides a sharpening effect. Both operations are guided by a flow field derived from the structure tensor. To obtain a high&hyphen;quality flow field, we present a novel smoothing scheme for the structure tensor based on Poisson's equation. Our approach effectively regularizes anisotropic image regions while preserving the overall image structure and achieving a consistent level of abstraction. Moreover, it is suitable for per&hyphen;frame filtering of video and can be efficiently implemented to process content in real&hyphen;time. ",

author = "Henry Kang and Kyprianidis, {Jan Eric}",

note = "In this work, we present a non‐photorealistic rendering technique to create stylized abstractions from color images and videos. Our approach is based on adaptive line integral convolution in combinat...",

year = "2011",

month = apr,

doi = "10.1111/j.1467-8659.2011.01882.x",

language = "American English",

volume = "30",

journal = "Computer Graphics Forum",

}

TY - JOUR

T1 - Image and Video Abstraction by Coherence‐Enhancing Filtering

AU - Kang, Henry

AU - Kyprianidis, Jan Eric

N1 - In this work, we present a non‐photorealistic rendering technique to create stylized abstractions from color images and videos. Our approach is based on adaptive line integral convolution in combinat...

PY - 2011/4

Y1 - 2011/4

N2 - In this work, we present a non&hyphen;photorealistic rendering technique to create stylized abstractions from color images and videos. Our approach is based on adaptive line integral convolution in combination with directional shock filtering. The smoothing process regularizes directional image features while the shock filter provides a sharpening effect. Both operations are guided by a flow field derived from the structure tensor. To obtain a high&hyphen;quality flow field, we present a novel smoothing scheme for the structure tensor based on Poisson's equation. Our approach effectively regularizes anisotropic image regions while preserving the overall image structure and achieving a consistent level of abstraction. Moreover, it is suitable for per&hyphen;frame filtering of video and can be efficiently implemented to process content in real&hyphen;time.

AB - In this work, we present a non&hyphen;photorealistic rendering technique to create stylized abstractions from color images and videos. Our approach is based on adaptive line integral convolution in combination with directional shock filtering. The smoothing process regularizes directional image features while the shock filter provides a sharpening effect. Both operations are guided by a flow field derived from the structure tensor. To obtain a high&hyphen;quality flow field, we present a novel smoothing scheme for the structure tensor based on Poisson's equation. Our approach effectively regularizes anisotropic image regions while preserving the overall image structure and achieving a consistent level of abstraction. Moreover, it is suitable for per&hyphen;frame filtering of video and can be efficiently implemented to process content in real&hyphen;time.

UR - https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1467-8659.2011.01882.x

U2 - 10.1111/j.1467-8659.2011.01882.x

DO - 10.1111/j.1467-8659.2011.01882.x

M3 - Article

VL - 30

JO - Computer Graphics Forum

JF - Computer Graphics Forum

ER -

Image and Video Abstraction by Coherence‐Enhancing Filtering

Abstract

Disciplines

Access to Document

Other files and links

Cite this