Conference PaperPDF Available

Directional interpolation of images based on visual properties and rank order filtering

Authors:

Abstract

The goal of this research is to develop interpolation techniques which preserve or enhance the local structure critical to image quality. Preliminary results are presented which exploit either the properties of vision or the properties of the image in order to achieve the goals. Directional image interpolation is considered which is based on a local analysis of the spatial image structure. The extension of techniques for the design of linear filters based on properties of human perception reported previously to enhance the perceived quality of interpolated images is considered
M12.25
DIRECTIONAL INTERPOLATION
OF
IMAGES BASED ON VISUAL PROPERTIES
AND RANK ORDER FILTERING
V.
Ralph Algazi, Gary
E.
Ford,
and Ravindra Potharlanka
CIPIC, Center for Image Processing and Integrated Computing
University of Califomia, Davis
The goal of our research is to develop interpolation
techniques which preserve or enhance the local structure
critical to image quality. In this paper, we present
preliminary results which exploit either the properties of
vision or the properties of the image
in
order to achieve our
goals. Few algorithms systematically take advantage of
both. The median filter, based solely
on
properties of data,
removes statistical outliers and thus isolated errors in
images, and preserves approximately the sharpness of
isolated image transitions. The visual quality of the resulting
images is problematic. Further, the edge preserving
property of the median filter does not extend to comers or
other
two
dimensional structures.
In
this paper, we consider directional image
interpolation, based
on
a local analysis of the spatial image
structure. We also consider the extension of techniques for
the design of linear filters based
on
properties of human
perception reported previously to enhance the perceived
quality of interpolated images.
I.
A BRIEF DISCUSSION AND OVERVIEW
OF INTERPOLATION TECHNIQUES
Interpolation is one of the fundamental signal processing
operations. For digital images, interpolation is necessary
when the display density of images is changed, except in the
case of the subsampling by an integer. Interpolation is also
required in any geometric transformation or warping of
images, even for the same spatial sampling density.
Interpolation is finally one of the intermediate operations in
the multirate processing of images.
Although interpolation may
be
considered with reference
to
the design of a low pass filter based
on
the frequency
content or bandwidth of images, such an approach is seldom
fruitful in image processing applications. First, the extent of
images is generally small,
so
that the use of large support
filters creates large artifacts at the boundary of images.
Second, the design philosophy for low pass filters which is
based
on
the approximation of an ideal low pass frequency
characteristic is inappmpriate for images
[l].
Finally,
if
one
is interested
in
preserving the whole range of detail available
in the original sample, the sampling is then exactly at the
Nyquist rate and formal fiter design specifications cannot be
formulated.
Our interest is in preserving, or even extending the
detailed information content in the image. In that context,
the classical or common interpolation schemes are pixel
replication, bilinear interpolation and bicubic interpolations
[4].
Bilinear and bicubic interpolations are small support
operations which attempt to preserve the detail by providing
a very high bandwidth. Of course, they result
in
significant
aliasing errors, observed most commonly as staircasing for
high contrast edges, or moire patterns for high detail parallel
lines or streaks.
11.
DIRECTIONAL FILTERING AND
INTERPOLATION
Directional interpolation recognizes that high detail areas
in images most often have a definite geometric structure or
pattern, such as
in
the case of edges. In such cases,
interpolation in the low frequency
direction,
along on edge,
is much better than interpolation
in
the high frequency
direction, across the edge. Thus, a directional interpolation
scheme has to perform a local andysis of the image structure
first, and then base the interpolation on that local structure if
a low frequency direction does exist. A number of
techniques have been developed through the years, which
perform image filtering by either analyzing the local image
structure or by performing operations which preserve some
types of local structure. The best known method which
preserves a specific image structure
is
the median filter
[5].
The median filter is best suited to remove outliers in a local
distribution of pixels within a data window. Because
of
the
use of exactly the mid value or median of the distribution, it
will also preserve a high contrast edge. For such an edge,
the distribution is bimodal and the median will transition,
with a single pixel shift of the data window, from one mode
of the distribution to the other. The median filter will not
preserve other local structures and perform quite poorly for
random noise.
Among methods for directional filtering based
on
image
analysis, directional smoothing does a local analysis
of
the
image and generates a direction dependent set of estimates
for each central pixel, from which the final estimate
is
chosen optimally
[6].
Other methods for edge-preserving
smoothing filters
are
presented and discussed in
[7,8].
In a
recent publication,
an
edge preserving interpolation method
has
been
reported
[9].
The method first detects the presence
of a high contrast edge, then estimates its location and
orientation, and finally bases the interpolation
on
that edge
estimate. The method assumes a two level edge with
no
transition width. As
an
altemative to this ideal edge model,
the algorithm reverts to a bilinear interpolation. We frrst
consider a simple generalization
of
the model of an image
transition which works well for isolated edges.
A. Interpolation based on
a
planar transition
model
In
this work, we have restricted our attention
to
the
doubling of sample densities both in the horizontal and
vertical directions. We detect the local areas
of
the image
which can be modeled as a planar model for an isolated
transition. For such a simple model, we can perform a
detection test by evaluation of the local gradient and
Laplacian.
Directional Interpolation usine grad ients: Consider the
image I(j,k). At pixel location
j&,
evaluate the gradient
vector
=
VI using apdient
3x3
Operator such
as
the
Sobel Operator. Let
G
have components G,,G,. The
-
3005
-
CH2977-719110000-3005
$1.00
0
1991
IEEE
direction perpendicular to the gradient corresponds to
isointensity contours on the tangent plane to the surface.
kt
vlc,
has for components
V,=-G,,
Vy=Gx
and has
a direction
8
in
the
xy
plane
I1
I2
0
0
14"
I3
Values I1,I2,I3 and
b
are known. Weestimate IO by
directional interpolation of the four known values for
-x
x.
--<e<-
2 2
We compute
I,,
I,, and take
f,
=
Idl+Id2
If we have
an
exact isointensity line, then
IA,,I,2
should
Again, to compute I,,,I,, we perform a linear
2
be
the same, otherwise, averaging them is reasonable.
interpolation between the adjacent values on the grid.
with
a
=
-
tan
8,
and tan 0
=
p,
from which we obtain
-1
4
I,,
=
aI,
+
(1
-a&;
I,,
=
aI,
+
(1
-
a)I,
I,
=-[I, +I,
+I,+
I,
+P(I,
+
I, -I,
-I,)]
(1)
For
-
>
181
>
5
the figure is no longer valid. The intersected
values are on different axes. By symmetry,
it
is clear that
we have then
n
x
2
1
1
I,
=
-
I,
+
1,
+
I,
+
I,
+
-(Iz
+
I,
-
I,
-
I,)
-
4
'[
P
Thus, if we perform the test
tan
8=p,<l. For
p>l
we use
equapon
(1)
and for
p<l
we shall use equation
(2).
The test
ps1 is equivalent to testing
lGxlS
IGyI.
We have examined only case of interpolation, when
the unknown sample x is at the center of the square formed
by the four known pixels. The only other case for a
2:l
interpolation is shown below
0
0
I1
I2
/-
The approach is completely similar with two exceptions.
a) The nearest pixel changes for
tan
8
=
k
2
;
18126.56"
1
..
b) as
8
>
the nearest neighbors change again from
I,,
I,
to
$,
I,.
This second case is also applicable with
obvious symmetric transpositions, for horizontal
interpolation between known pixels.
Estimation of the gradient: We have assumed that the
gradient is determined by a
3x3
gradient operator.
However, in the case of interpolation it is not clear which
3x3
array is used to estimate the gradient. As before, there
are
2
cases
Case
1:
Averaging Pixels:
0
0
0 0
0 0
0
0
The averages #1 etc form
3x3
arrays which can
be
used to
estimate the gradient.
Case
2:
Averaging Pixels: We now have the situation
shown below
0
0
0
0
0
0
use nine averages as shown in
#1,
#2.
Because the figure is
not symmetric, we
use
either
4
pixel or
2
pixel averages. An
alternate method is to evaluate
two
gradients on the
two
3x3
arrays which straddle the unknown pixel and average the
results. The Laplacian
vz
is estimated by
using
the common
operator
The planar model is accepted
if
11c112
T, and
Vz
2
T,
(3)
where Ti and
T2
are determined empirically. When the test
fails, bilinear interpolation is applied. Results of
this
method
based on a planar model are shown in Figure
1.
The method tuns out to
be
fairly similar to what was
reported in
[9]
in
many of its details, except that a specific
test for the magnitude of the Laplacian is made here, while
in
[9]
only the edge magnitude is used. The results for our
method seem to be somewhat better visually.
B.
Interpolation
for
other local image
structures. Use
of
Quartiles.
Other local image structures commonly encountered, for
which image analysis may provide an improvement in the
interpolation scheme, are streaks and comers. Streaks or
lines are local linear structures which are narrower
than
the
analysis window width. Wedges or comers also have a
definite local structure characterized by two intersecting
directions within an analysis window. Thus, three types of
local structures, edges, streaks and comers, are worth
detecting to improve interpolation. They
are
all characterized
by a bimodal distribution within the analysis window.
These two modes
are
not necessary symmemc with respect
to the median as in the case of an isolated edge. This
observation suggest the use of rank order statistics, within,
the analysis window, to the occurrence of one of the
three structures of interest. Once the presence of of
-
3006
-
these three structures is detected, a 'spatial analysis has to
be
performed to determine the type of structure and its
orientation. Because of the small analysis window, we limit
our study to the use of quartiles. Within an analysis
window, say 3x3, we group the eight exterior pixel values
into quartiles, Qi,@,Q3,Q4. In each quartile there are two
ordered values
Qj,
i=1.
...,
4, j=1,2. A preliminary test for
the detection of a local structure is
where T3 is a threshold determined experimentally. Thus,
the statistic of (4) is an indicator of a bimodal distribution,
which allows for asymmetric modes. Preliminary
experiments show that such a detection scheme has promise
for the detection of the high contrast local structures
including streaks and comers.
Suatial Analvsis: When the test of (4) indicate that a local
skcture may be present, we analyze the distribution of pixel
values in 8 possible directions. Instead of pixels, we also
use a statistic in each of the
8
directions, such as the mean of
a 2
or
4 pixel cluster. As indicated earlier, we expect that the
spatial structure of interest is characterized by a bimodal
distribution, but the modes are not always distributed about
the median. Thus, we classify the pixels into two classes,
High
(H)
and Low
(L)
by using a threshold between the
adjacent quartiles with the largest separation, i.e. the largest
of Qi+l,l-Qi,~
;
i=1,2,3. Thus the number of high and
lows within an analysis window is no longer the same. We
have, for example, the patterns shown below
HLL HHL
LXL HxL
LHH LLL
Case 1 Case 2
Case 1 corresponds to possible streaks and case 2 to a
possible corner. To confirm the presence of a streak we
analyze further
the
immediate neighbors of x
so
as
to
classify
x as H or
L
and perform an interpolation in the appropriate
direction. For a comer, a local analysis about x is used to
resolve whether x should be estimated only from the high
values within the window. Experimental evaluation is not
complete, but preliminary tests indicate that such a method
complements the interpolation schemes discussed earlier and
provides useful results for streaks, which are often
encountered in images.
C . Directional enhancement
of
interpolated
images based on visual properties.
In
[
13 we have developed an approach to the design of
FIR filters based on properties of visual perception. This
formulation results in an optimization
in
both the spatial and
frequency domain,
so
as
to achieve some desired frequency
behavior, while maintaining the quality of the image in the
vicinity of the edge. This second condition requires a spatial
domain constraint so as to avoid excessive rippling, common
in filters with sharp frequency domain transitions. In [2,3],
we have extended this approach to image enhancement in the
horizontal and vertical directions while controlling the noise
variance increase due to the enhancement process. Here we
use the same basic formalism to provide for selective
enhancement in one of four possible directions.
Because we wish to maintain directionality, we now
design one dimensional filter of horizontal, vertical or
diagonal orientations. Thus, we process the image with four
distinct directional FIR filters to enhance the quality of the
image. Since the image will be modified by the enhancement
filters, this step in the processing will be performed as a last
step on an image interpolated to the final display resolution.
Q31-QI2
><T3 (4)
D.
Some Experimental Results
We show in Figure 1 some of the results obtained by the
methods reported in this paper. The original, Figure la, is a
512x512 image. The other images are originally 256x256
interpolated to 512x512. Figure lb shows bilinear
interpolation with significant visual artifacts due to aliasing
errors. Figure IC shows the result of directional
interpolation using the planar model of Section EA. Figure
Id illustrates the results of applying a directional
enhancement as discussed in Section 1I.C. The results
obtained are quite
good
in
the
removal of all remaining
artifacts due to aliasing errors along horizontal, vertical or
diagonal high contrast edges. The enhancement filter cannot
improve portions of the images where the directional image
structure has not been preserved by directional interpolation.
In this paper we have presented some new results on
image interpolation which are based on an analysis
of
the
structure of images in a small window. Because of the
sparsity of data which is available for such analysis, we have
focussed on simple high contrast directional structures, such
as edges, streaks and corners. For edges, we have
examined a simple planar transition model which perform
fairly well on
our
test images.
In
order to detect streaks and
comers, we propose a local analysis of images which group
pixel values into quartiles. Finally, we have applied some of
our previous work on the design of filters based on
properties of human perception to the design of directional
filters which enhance structure. Our results are encouraging
and indicate that this is a promising approach to an area of
research with a number of applications in high quality
imaging.
References:
111.
DISCUSSION [AND CONCLUSIONS
1.
2.
3.
4.
5.
6.
7.
8.
9.
T.A. Hentea and V.R. Algazi. "Perceptual Models and
the Filtering of High-Contrast Achromatic Images".
IEEE
Transactions
on
Systems, Man, and Cybernetics,
V.R. Algazi. "Fir Anisotropic Filters for Image
Enhancement".
Proceedings ICASSP
Vol.
3,
1986
V.R. Algazi, G.E. Ford, and E. Hildum. "Digital
Representation and Storage of High Quality Color
Images by Anisotropic Enhancement and
Subsampling".
Proc. ICASSP
'89,
pp. 1846-1 849.
1989
A.K.
Jain.
Fundamentals
of
Digital Image Processing.
SMC- 14(2)230-246. 1984
.-
Prentice
Hall.
1988.
T.S. Huang and G.Y. Tang. "A Fast Two Dimensional
Median Filtering Algorithm".
IEEE
Trans. ASSP.,
27:13-18. 1979
M. Nagao et T. Matsuyama. "Edge Preserving
Smoothing".
Computer Graphics and Image
Processing,
9:394-407, Academic
Press,
April 1979.
D. Harwood, M. Subbarao, H. Hakalatiti and
L.S.
Davis. "A New Class of Edge-Preserving
Smoothing
Filters".
Pattern Recognition Letters
6: 155-162,
(1987).
T.
Pavlidis. "Algorithms for Image Processing and
Computer Graphics,"
Computer Scfence Press.
K.
Jensen and D. Anastassiou. Spatial Resolution
Enhancement of Images Using Nonlinear Interpolation".
Proc. ICASSP
1990, pp. 2045-2048.
This
research
supported
in
pan
by the
Research
Program
(MICRO)
ofthc
University
of
Cd-
ifomia
and
by
Pacific
Bell
and
HCW~II
Packard
-
3007
-
a)
Original
b)
Linear
Interpolation
c) Directional
Interpolation
d)
Directional Enhancement
Figure
1:
Some
Experimental
Results
-
3008
-
... More complex interpolation methods have been proposed to generate higher-quality images than conventional interpolation methods. One of the methods is the directional interpolation of images based on visual properties and rank order filtering [6]. In this method, a gradient filter is applied to detect edges, corners, and streaks such that the interpolation does not cause incorrect restoration. ...
... Those components are separately interpolated utilizing one-dimensional FIR filters in the direction of those structures. The rest of the image is recovered by adopting simple linear interpolation [6]. ...
... However, in recent years there have been efforts to create image quality algorithms that are able to overcome these limitations [5,6]. The residual neural network architecture described with Figure 1 in Section 2.1, is taken into account for RTISR in this paper. ...
Article
Full-text available
Advanced algorithms of image quality enhancement have been attracting substantial attention recently due to the successful business model of video streaming services. The extremely high image quality in video streaming demands a significant increase in the transmit data rate. In turn, the required ultrahigh data rate causes the saturation of the video streaming service network if there is no remedy for this situation. Compression algorithms have contributed to the energy-efficient transmission of data; however, they have almost reached the upper bound. The demand for ultrahigh image quality by the user is significantly increasing. Meanwhile, minimizing data transmission is inevitable in energy-efficient communications. Therefore, to improve energy efficiency, we propose to decrease the image resolution at the transmitter (Tx) and upscale the image at the receiver (Rx). However, standard upscaling does not yield ultrahigh-quality images. Deep machine learning contributes to image super-resolution techniques with the cost of enormous time and resources at the user end. Hence, it is inappropriate for real-time applications. With this motivation, this paper proposes a deep machine learning-based real-time image super-resolution with a residual neural network on the prevalent resources at the user end. The proposed scheme provides better quality than conventional image upscaling such as interpolation. The comprehensive simulation verifies that our scheme substantially outperforms the conventional methods, utilizing the seven-layer residual neural network.
... More advanced upscalers have followed geometric principles to improve image quality. For example, edge-directed interpolation uses adaptive filters to improve edge smoothness [2,18], or bandlet methods use both adaptive upsampling and filtering [24]. Later on, machine learning has been able to use examples of pristine high-resolution images to learn a mapping from low-resolution [30]. ...
... This indicates that the different branches of the single convolutional layer used in eSR-TM are solving the upscaling problem independently for each sub-pixel image. This is in contrast with the smooth scaling filters used in the classical edge-directed interpolation [2,18] and also compared to smooth directional filters observed in CNNs superresolution interpretations in [28]. Next, in Figure 8 we compute the Pearson correlation between upscaling and matching filters for eSR-TM with k = 7 and C = 16. ...
... More advanced upscalers have followed geometric principles to improve image quality. For example, edge-directed interpolation uses adaptive filters to improve edge smoothness [2,17], or bandlet methods use both adaptive upsampling and filtering [21]. Later on, machine learning has been able to use examples of pristine high-resolution images to learn a mapping from low-resolution [27]. ...
... This indicates that the different branches of the single convolutional layer used in eSR-TM are solving the upscaling problem independently for each sub-pixel image. This is in contrast with the smooth scaling filters used in the classical edge-directed interpolation [2,17] and also compared to smooth directional filters observed in CNNs superresolution interpretations in [25]. Next, in Figure 8 we compute the Pearson correlation between upscaling and matching filters for eSR-TM with k = 7 and C = 16. ...
Preprint
Full-text available
Classic image scaling (e.g. bicubic) can be seen as one convolutional layer and a single upscaling filter. Its implementation is ubiquitous in all display devices and image processing software. In the last decade deep learning systems have been introduced for the task of image super-resolution (SR), using several convolutional layers and numerous filters. These methods have taken over the benchmarks of image quality for upscaling tasks. Would it be possible to replace classic upscalers with deep learning architectures on edge devices such as display panels, tablets, laptop computers, etc.? On one hand, the current trend in Edge-AI chips shows a promising future in this direction, with rapid development of hardware that can run deep-learning tasks efficiently. On the other hand, in image SR only few architectures have pushed the limit to extreme small sizes that can actually run on edge devices at real-time. We explore possible solutions to this problem with the aim to fill the gap between classic upscalers and small deep learning configurations. As a transition from classic to deep-learning upscaling we propose edge-SR (eSR), a set of one-layer architectures that use interpretable mechanisms to upscale images. Certainly, a one-layer architecture cannot reach the quality of deep learning systems. Nevertheless, we find that for high speed requirements, eSR becomes better at trading-off image quality and runtime performance. Filling the gap between classic and deep-learning architectures for image upscaling is critical for massive adoption of this technology. It is equally important to have an interpretable system that can reveal the inner strategies to solve this problem and guide us to future improvements and better understanding of larger networks.
... More advanced upscalers have followed geometric principles to improve image quality. For example, edge-directed interpolation uses adaptive filters to improve edge smoothness [4], [5], or bandlet methods use both adaptive upsampling and filtering [6]. Later on, machine learning has been able to use examples of pristine high-resolution images to learn a mapping from low-resolution [7]. ...
Article
Full-text available
Multi-Grid Back-Projection (MGBP) is a fully-convolutional network architecture that can learn to restore images and videos with upscaling artifacts. Using the same strategy of multi-grid partial differential equation (PDE) solvers this multiscale architecture scales computational complexity efficiently with increasing output resolutions. The basic processing block is inspired in the iterative back-projection (IBP) algorithm and constitutes a type of cross-scale residual block with feedback from low resolution references. The architecture performs in par with state-of-the-arts alternatives for regression targets that aim to recover an exact copy of a high resolution image or video from which only a downscale image is known. A perceptual quality target aims to create more realistic outputs by introducing artificial changes that can be different from a high resolution original content as long as they are consistent with the low resolution input. For this target we propose a strategy using noise inputs in different resolution scales to control the amount of artificial details generated in the output. The noise input controls the amount of innovation that the network uses to create artificial realistic details. The effectiveness of this strategy is shown in benchmarks and it is explained as a particular strategy to traverse the perception-distortion plane.
... More advanced upscalers have followed geometric principles to improve image quality. For example, edge-directed interpolation uses adaptive filters to improve edge smoothness [4], [5], or bandlet methods use both adaptive upsampling and filtering [6]. Later on, machine learning has been able to use examples of pristine high-resolution images to learn a mapping from low-resolution [7]. ...
Preprint
Full-text available
Multi-Grid Back-Projection (MGBP) is a fully-convolutional network architecture that can learn to restore images and videos with upscaling artifacts. Using the same strategy of multi-grid partial differential equation (PDE) solvers this multiscale architecture scales computational complexity efficiently with increasing output resolutions. The basic processing block is inspired in the iterative back-projection (IBP) algorithm and constitutes a type of cross-scale residual block with feedback from low resolution references. The architecture performs in par with state-of-the-arts alternatives for regression targets that aim to recover an exact copy of a high resolution image or video from which only a downscale image is known. A perceptual quality target aims to create more realistic outputs by introducing artificial changes that can be different from a high resolution original content as long as they are consistent with the low resolution input. For this target we propose a strategy using noise inputs in different resolution scales to control the amount of artificial details generated in the output. The noise input controls the amount of innovation that the network uses to create artificial realistic details. The effectiveness of this strategy is shown in benchmarks and it is explained as a particular strategy to traverse the perception-distortion plane.
... It was performed on Landsat 8 band 6 images by the Sobel directional filter, which is a discrete differential operator, that computes an approximation of the gradient of the image intensity function and calculates the gradient of the image intensity at each point and gives the direction of possible increase from light to dark and rate of change in direction. It's based on the use of core matrix that by convolution product enhances the discontinuities in the images, which are likely to be geological lineaments (Ikonomopoulos and Kunt 1985;Algazi et al. 1991;Paplinski 1998;Holub and Fridrich 2012;Hermi et al. 2017;Takorabt et al. 2018;Rezaei et al. 2019). A 5 × 5 core matrix was used to detect major lineaments and a 3 × 3 core matrix to generate the finest ones. ...
Article
In a changing climate, the more we understand the drainage networks distribution and structuration, the more we can better predict flood risks, and ensure better water resource management. The identification of geological lineaments is a basic approach for the study and analysis of surficial geological structuring that potentially controls the drainage networks distribution and subsurface water resources. Taking the North Oulmes region in Morocco as an example, an automatic lineament detection algorithm based on the Hough transform has been applied to the Landsat 8 OLI and Sentinel-1 SAR data. This technique was coupled with spatial filtering and field data with the aim of identifying surface geological structures that may control the drainage network. This study also presents an analysis of the drainage network which concerns the identification of similarities between its structuring and geological lineaments, through the analysis of rose diagrams and the identification of the different drainage network patterns. The results show that the geological lineaments identified by the algorithm are very satisfactory, geologically significant and represent a continuity towards the surface of the underlying structures. The findings of this study also show that, the conformation of the drainage network characteristics with the geological structures as well as the rectangular and trellis drainage patterns observed in the study area indicate that the distribution and structuring of the drainage network is mainly controlled by the geological structures trending NE-SW resulting from the Hercynian tectonic event.
Technical Report
Full-text available
In this technical report, we introduce Kenoobi Image Upscaler, an advanced AI model that enhances the quality of any image beyond imagination. The model uses advanced AI algorithms for color correction, shallow and deep feature extraction, and high-quality (HQ) image reconstruction. The model is trained using a large dataset of high-resolution images, and its performance is evaluated using various experiments. The results show that Kenoobi Image Upscaler can restore and enhance the details, colors, and textures of an image, creating a stunningly crisp and vibrant image.
Technical Report
Full-text available
Kenoobi Artworx AI is an AI model that generates unique art pieces based on user input. It uses various AI methods such as variational autoencoder and noise schedule to create images that are owned by the user and can be used for NFT projects or shared on social media. The app offers different models, styles, and aspect ratios, and regular updates are provided to improve the AI methods. In this technical report, we provide details on the training process, image generation, experiments, limitations, and potential technology misuse. Introduction:
Article
Small infrared target localization and tracking are of great importance in early-warning systems. In order to accurately localize the target, a high-performance target detection algorithm is required. In this paper, a new detection algorithm is proposed, which effectively enhance the target area and eliminate noise and background clutter. The algorithm is inspired by the minimum variation directions interpolation. The detection performance of the method is investigated comprehensively in different situations. Also, to exclude the effect of thresholding on the detector's performance, a measure based on constant false alarm rate (CFAR) is employed. Experiments on multiple real-world infrared sequences demonstrate the effectiveness of the proposed method.
Chapter
To obtain high resolution images, some low resolution images must be processed and enhanced. In the literature, the mapping from the low resolution image to the high resolution image is a linear system and it is only enlarged by an integer scale. This paper presents a real scaling algorithm for image resolution enhancement. Using a virtual magnifier, an image resolution can be enhanced by a real scale number. Experimental results demonstrate that the proposed algorithm has a high quality for the enlarged image in the human visual system.
Article
A model based on research in the psychophysics of vision is developed for use in the design of image processing filters in order to quantify the results of image processing as perceived by a human observer. An alternate formulation of the classical frequency-domain filter design problem with both space and frequency-domain specifications is developed. New experimental results concerning the masking effect in the vicinity of edges are reported, and a structure of a model for detection of distortion in complex images is proposed. The ability of the model to predict the visibility of one-dimensional patterns in the vicinity of edges is tested. A distortion measure based on the model is introduced, and practical filter-design criteria are developed. Both FIR linear phase filters and IIR filters are used to demonstrate the applicability of the methods.
Article
A new smoothing algorithm is proposed, which looks for the most homogeneous neighborhood area around each point in a picture, and then gives each point the average gray level of the selected neighborhood area. It removes noise in a flat region without blurring sharp edges, nor destroying the details of the boundary of a region. This smoothing also has the ability to sharpen blurred edges.
Article
A new class of edge-preserving noise-cleaning filters are introduced which use both spatial and nearest-neighbor constraints on image pixels to smooth an image. They are simple, fast and good at preserving edges and thin structural details in images. Edges and corners of varying contrasts that may be present in real images have been simulated in synthesized random checkerboards. The performance of the new smoothing filters on the blurred and noisy checkerboards has been quantitatively compared with that of four other filters.
Conference Paper
This paper describes a technique for the enhancement of images by FIR filters which compensates for the decreased response of human vision at high spatial frequencies. Because many images contain mainly horizontal and vertical features, and because vision is less acute along diagonals, it is possible to design anisotropic enhancement filters which do not increase greatly the background noise. The anisotropic design methodology also incorporates other results on filter design based on human vision which have recently been reported by the author and coworkers.
Conference Paper
A nonlinear interpolation scheme for image-resolution enhancement is presented. The algorithm is based upon a source model emphasizing edges and incorporates a hybrid local edge-fitting operator which has been developed for this application. A small neighbourhood about each pixel in the low-resolution image is first mapped to a best-fit continuous-space step-edge. This bilevel approximation serves as a local template upon which the higher-resolution sampling grid can then be superimposed. Disputed values in regions of overlap are averaged to smooth errors. The result is an image of increased resolution with noticeably sharper edges and lower reconstruction error than produced by linear techniques
Conference Paper
The application of novel anisotropic filter design techniques based on properties of human vision to the processing of luminance and chrominance components of color images is considered. Applied independently, these anisotropic filters can be used for the sequential digital representation of images by subsampling. By using them with two-dimensional quadrature modulation of chrominance signals, they led to a novel scheme for color composite images in which the skewing of energy due to the anisotropy of the filters improves the juxtaposition of luminance and chrominance in the two-dimensional frequency domain. It is found that the image quality is substantially better than that of NTSC images for either sequential or composite techniques
Article
We present a fast algorithm for two-dimensional median filtering. It is based on storing and updating the gray level histogram of the picture elements in the window. The algorithm is much faster than conventional sorting methods. For a window size of m × n, the computer time required is 0(n).