Inpainting has received a lot of attention in recent years and quality assessment is an important task to evaluate different image reconstruction approaches. In many cases inpainting methods introduce a blur in sharp transitions in image and image contours in the recovery of large areas with missing pixels and often fail to recover curvy boundary edges. Quantitative metrics of inpainting results currently do not exist and researchers use human comparisons to evaluate their methodologies and techniques. Most objective quality assessment methods rely on a reference image, which is often not available in inpainting applications. Usually researchers use subjective quality assessment by human observers. It is difficult and time consuming procedure. This paper focuses on a machine learning approach for no-reference visual quality assessment for image inpainting based on the human visual property. Our method is based on observation that Local Binary Patterns well describe local structural information of the image. We use a support vector regression learned on assessed by human images to predict perceived quality of inpainted images. We demonstrate how our predicted quality value correlates with qualitative opinion in a human observer study. Results are shown on a human-scored dataset for different inpainting methods.
Image alignment and mosaicing are usually performed on a set of overlapping images, using features in the area of
overlap for seamless stitching. In many cases such images have different size and shape. So we need to crop panoramas
or to use image extrapolation for them. This paper focuses on novel image inpainting method based on modified
exemplar-based technique. The basic idea is to find an example (patch) from an image using local binary patterns, and
replacing non-existed (‘lost’) data with it. We propose to use multiple criteria for a patch similarity search since often in
practice existed exemplar-based methods produce unsatisfactory results. The criteria for searching the best matching uses
several terms, including Euclidean metric for pixel brightness and Chi-squared histogram matching distance for local
binary patterns. A combined use of textural geometric characteristics together with color information allows to get more
informative description of the patches. In particular, we show how to apply this strategy for image extrapolation for
photo stitching. Several examples considered in this paper show the effectiveness of the proposed approach on several
test images.
This paper proposes a novel texture descriptor based indices of degrees of local approximating polynomials. An input image is divided into non-overlapping patches which are reshaped into a one-dimensional source vectors. These vectors are approximated using local polynomial functions of various degrees. For each element of the source vector, these approximations are ranked according to the difference between the original and approximated values. A set of indices of polynomial degrees form a local feature. This procedure is repeated for every pixel. Finally, a proposed texture descriptor is obtained from the frequency histogram of all obtained local features. A nearest neighbor classifier utilizing distance metric is used to evaluate a performance of the introduced descriptor on the following datasets: Brodatz, KTH-TIPS, KTH-TIPS2b, UCLA and Columbia-Utrecht (CUReT) with respect to different methods of texture analysis and classification. A proper parameter setup of the proposed texture descriptor is discussed. The results of this comparison demonstrate that the proposed method is competitive with the recent statistical approaches such as local binary patterns (LBP), local ternary patterns, completed LBP, Weber’s local descriptor, and VZ algorithms (VZ-MR8 and VZ-Joint). At the same time, on KTH-TIPS2-b and KTH-TIPS datasets, the proposed method is slightly inferior to some of the state-of-the-art methods.
This paper focuses on a machine learning approach for objective inpainting quality assessment. Inpainting has received a
lot of attention in recent years and quality assessment is an important task to evaluate different image reconstruction
approaches. Quantitative metrics for successful image inpainting currently do not exist; researchers instead are relying
upon qualitative human comparisons in order to evaluate their methodologies and techniques. We present an approach
for objective inpainting quality assessment based on natural image statistics and machine learning techniques. Our
method is based on observation that when images are properly normalized or transferred to a transform domain, local
descriptors can be modeled by some parametric distributions. The shapes of these distributions are different for noninpainted
and inpainted images. Approach permits to obtain a feature vector strongly correlated with a subjective image
perception by a human visual system. Next, we use a support vector regression learned on assessed by human images to
predict perceived quality of inpainted images. We demonstrate how our predicted quality value repeatably correlates
with a qualitative opinion in a human observer study.
A texture descriptor based on a set of indices of degrees of local approximating polynomials is proposed in this paper.
First, a method to construct 2D local polynomial approximation kernels (k-LPAp) for arbitrary polynomials of degree p
is presented. An image is split into non-overlapping patches, reshaped into one-dimensional source vectors and
convolved with the polynomial approximation kernels of various degrees. As a result, a set of approximations is
obtained. For each element of the source vector, these approximations are ranked according to the difference between the
original and approximated values. A set of indices of polynomial degrees form a local feature. This procedure is repeated
for each pixel. Finally, a proposed texture descriptor is obtained from the frequency histogram of all obtained local
features. A nearest neighbor classifier utilizing Chi-square distance metric is used to evaluate a performance of the
introduced descriptor. An accuracy of texture classification is evaluated on the following datasets: Brodatz, KTH-TIPS,
KTH-TIPS2b and Columbia-Utrecht (CUReT) with respect to different methods of texture analysis and classification.
The results of this comparison show that the proposed method is competitive with the recent statistical approaches such
as local binary patterns (LBP), local ternary patterns, completed LBP, Weber’s local descriptor, and VZ algorithms (VZMR8
and VZ-Joint). At the same time, on KTH-TIPS2-b and KTH-TIPS datasets, the proposed method is slightly
inferior to some of the state-of-the-art methods.
This paper focuses on novel image reconstruction method based on modified exemplar-based technique. The basic idea
is to find an example (patch) from an image using local binary patterns, and replacing non-existed (‘lost’) data with it.
We propose to use multiple criteria for a patch similarity search since often in practice existed exemplar-based methods
produce unsatisfactory results. The criteria for searching the best matching uses several terms, including Euclidean
metric for pixel brightness and Chi-squared histogram matching distance for local binary patterns. A combined use of
textural geometric characteristics together with color information allows to get more informative description of the
patches. Texture synthesis method proposed by Efros and Freeman for patch restoration is utilized in the proposed
method. It allows optimizing an overlap region between patches using minimum error boundary cut. Several examples
considered in this paper show the effectiveness of the proposed approach for large objects removal as well as recovery of
small regions on several test images.
In this paper an image inpainting approach based on the construction of a composite curve for the restoration of the
edges of objects in an image using the concepts of parametric and geometric continuity is presented. It is shown that this
approach allows to restore the curved edges in damaged image by interpolating the boundaries of objects by cubic
splines. A tensor analysis is used for classification of texture and non texture regions. After edge restoration stage, a
texture restoration based on exemplar based method is carried out. It finds the best matching patch from another source
region and copies it into the damaged region. For non texture regions a Telea method is applied.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.