Abstract: In this paper, we present a pedestrian detection descriptor called Fused Structure and Texture (FST) features based on the combination of the local phase information with the texture features. Since the phase of the signal conveys more structural information than the magnitude, the phase congruency concept is used to capture the structural features. On the other hand, the Center-Symmetric Local Binary Pattern (CSLBP) approach is used to capture the texture information of the image. The dimension less quantity of the phase congruency and the robustness of the CSLBP operator on the flat images, as well as the blur and illumination changes, lead the proposed descriptor to be more robust and less sensitive to the light variations. The proposed descriptor can be formed by extracting the phase congruency and the CSLBP values of each pixel of the image with respect to its neighborhood. The histogram of the oriented phase and the histogram of the CSLBP values for the local regions in the image are computed and concatenated to construct the FST descriptor. Several experiments were conducted on INRIA and the low resolution DaimlerChrysler datasets to evaluate the detection performance of the pedestrian detection system that is based on the FST descriptor. A linear Support Vector Machine (SVM) is used to train the pedestrian classifier. These experiments showed that the proposed FST descriptor has better detection performance over a set of state of the art feature extraction methodologies.
Abstract: Human skin detection recognized as the primary step in most of the applications such as face detection, illicit image filtering, hand recognition and video surveillance. The performance of any skin detection applications greatly relies on the two components: feature extraction and classification method. Skin color is the most vital information used for skin detection purpose. However, color feature alone sometimes could not handle images with having same color distribution with skin color. A color feature of pixel-based does not eliminate the skin-like color due to the intensity of skin and skin-like color fall under the same distribution. Hence, the statistical color analysis will be exploited such mean and standard deviation as an additional feature to increase the reliability of skin detector. In this paper, we studied the effectiveness of statistical color feature for human skin detection. Furthermore, the paper analyzed the integrated color and texture using eight classifiers with three color spaces of RGB, YCbCr, and HSV. The experimental results show that the integrating statistical feature using Random Forest classifier achieved a significant performance with an F1-score 0.969.
Abstract: Advances in spatial and spectral resolution of satellite
images have led to tremendous growth in large image databases. The
data we acquire through satellites, radars, and sensors consists of
important geographical information that can be used for remote
sensing applications such as region planning, disaster management.
Spatial data classification and object recognition are important tasks
for many applications. However, classifying objects and identifying
them manually from images is a difficult task. Object recognition is
often considered as a classification problem, this task can be
performed using machine-learning techniques. Despite of many
machine-learning algorithms, the classification is done using
supervised classifiers such as Support Vector Machines (SVM) as the
area of interest is known. We proposed a classification method,
which considers neighboring pixels in a region for feature extraction
and it evaluates classifications precisely according to neighboring
classes for semantic interpretation of region of interest (ROI). A
dataset has been created for training and testing purpose; we
generated the attributes by considering pixel intensity values and
mean values of reflectance. We demonstrated the benefits of using
knowledge discovery and data-mining techniques, which can be on
image data for accurate information extraction and classification from
high spatial resolution remote sensing imagery.
Abstract: Digital images are widely used in computer
applications. To store or transmit the uncompressed images
requires considerable storage capacity and transmission bandwidth.
Image compression is a means to perform transmission or storage of
visual data in the most economical way. This paper explains about
how images can be encoded to be transmitted in a multiplexing
time-frequency domain channel. Multiplexing involves packing
signals together whose representations are compact in the working
domain. In order to optimize transmission resources each 4 × 4
pixel block of the image is transformed by a suitable polynomial
approximation, into a minimal number of coefficients. Less than
4 × 4 coefficients in one block spares a significant amount of
transmitted information, but some information is lost. Different
approximations for image transformation have been evaluated as
polynomial representation (Vandermonde matrix), least squares +
gradient descent, 1-D Chebyshev polynomials, 2-D Chebyshev
polynomials or singular value decomposition (SVD). Results have
been compared in terms of nominal compression rate (NCR),
compression ratio (CR) and peak signal-to-noise ratio (PSNR)
in order to minimize the error function defined as the difference
between the original pixel gray levels and the approximated
polynomial output. Polynomial coefficients have been later encoded
and handled for generating chirps in a target rate of about two
chirps per 4 × 4 pixel block and then submitted to a transmission
multiplexing operation in the time-frequency domain.
Abstract: Background modeling and subtraction in video
analysis has been widely used as an effective method for moving
objects detection in many computer vision applications. Recently, a
large number of approaches have been developed to tackle different
types of challenges in this field. However, the dynamic background
and illumination variations are the most frequently occurred problems
in the practical situation. This paper presents a favorable two-layer
model based on codebook algorithm incorporated with local binary
pattern (LBP) texture measure, targeted for handling dynamic
background and illumination variation problems. More specifically,
the first layer is designed by block-based codebook combining with
LBP histogram and mean value of each RGB color channel. Because
of the invariance of the LBP features with respect to monotonic
gray-scale changes, this layer can produce block wise detection results
with considerable tolerance of illumination variations. The pixel-based
codebook is employed to reinforce the precision from the output of the
first layer which is to eliminate false positives further. As a result, the
proposed approach can greatly promote the accuracy under the
circumstances of dynamic background and illumination changes.
Experimental results on several popular background subtraction
datasets demonstrate very competitive performance compared to
previous models.
Abstract: The aim of this paper is to propose a general
framework for storing, analyzing, and extracting knowledge from
two-dimensional echocardiographic images, color Doppler images,
non-medical images, and general data sets. A number of high
performance data mining algorithms have been used to carry out this
task. Our framework encompasses four layers namely physical
storage, object identification, knowledge discovery, user level.
Techniques such as active contour model to identify the cardiac
chambers, pixel classification to segment the color Doppler echo
image, universal model for image retrieval, Bayesian method for
classification, parallel algorithms for image segmentation, etc., were
employed. Using the feature vector database that have been
efficiently constructed, one can perform various data mining tasks
like clustering, classification, etc. with efficient algorithms along
with image mining given a query image. All these facilities are
included in the framework that is supported by state-of-the-art user
interface (UI). The algorithms were tested with actual patient data
and Coral image database and the results show that their performance
is better than the results reported already.
Abstract: Digital cameras to reduce cost, use an image sensor to
capture color images. Color Filter Array (CFA) in digital cameras
permits only one of the three primary (red-green-blue) colors to be
sensed in a pixel and interpolates the two missing components
through a method named demosaicking. Captured data is interpolated
into a full color image and compressed in applications. Color
interpolation before compression leads to data redundancy. This
paper proposes a new Vector Quantization (VQ) technique to
construct a VQ codebook with Differential Evolution (DE)
Algorithm. The new technique is compared to conventional Linde-
Buzo-Gray (LBG) method.
Abstract: One of the tasks of optical surveillance is to detect
anomalies in large amounts of image data. However, if the size of the
anomaly is very small, limited information is available to distinguish
it from the surrounding environment. Spectral detection provides a
useful source of additional information and may help to detect
anomalies with a size of a few pixels or less. Unfortunately, spectral
cameras are expensive because of the difficulty of separating two
spatial in addition to one spectral dimension. We investigate the
possibility of modifying a simple spectral line detector for outdoor
detection. This may be especially useful if the area of interest forms a
line, such as the horizon. We use a monochrome CCD that also
enables detection into the near infrared. A simple camera is attached
to the setup to determine which part of the environment is spectrally
imaged. Our preliminary results indicate that sensitive detection of
very small targets is indeed possible. Spectra could be taken from the
various targets by averaging columns in the line image. By imaging a
set of lines of various widths we found narrow lines that could not be
seen in the color image but remained visible in the spectral line
image. A simultaneous analysis of the entire spectra can produce
better results than visual inspection of the line spectral image. We are
presently developing calibration targets for spatial and spectral
focusing and alignment with the spatial camera. This will present
improved results and more use in outdoor application.
Abstract: In this paper, we present a comparative study of three
methods of 2D face recognition system such as: Iso-Geodesic Curves
(IGC), Geodesic Distance (GD) and Geodesic-Intensity Histogram
(GIH). These approaches are based on computing of geodesic
distance between points of facial surface and between facial curves.
In this study we represented the image at gray level as a 2D surface in
a 3D space, with the third coordinate proportional to the intensity
values of pixels. In the classifying step, we use: Neural Networks
(NN), K-Nearest Neighbor (KNN) and Support Vector Machines
(SVM). The images used in our experiments are from two wellknown
databases of face images ORL and YaleB. ORL data base was
used to evaluate the performance of methods under conditions where
the pose and sample size are varied, and the database YaleB was used
to examine the performance of the systems when the facial
expressions and lighting are varied.
Abstract: In this paper, a spatial multiple-kernel fuzzy C-means (SMKFCM) algorithm is introduced for segmentation problem. A linear combination of multiples kernels with spatial information is used in the kernel FCM (KFCM) and the updating rules for the linear coefficients of the composite kernels are derived as well. Fuzzy cmeans (FCM) based techniques have been widely used in medical image segmentation problem due to their simplicity and fast convergence. The proposed SMKFCM algorithm provides us a new flexible vehicle to fuse different pixel information in medical image segmentation and detection of MR images. To evaluate the robustness of the proposed segmentation algorithm in noisy environment, we add noise in medical brain tumor MR images and calculated the success rate and segmentation accuracy. From the experimental results it is clear that the proposed algorithm has better performance than those of other FCM based techniques for noisy medical MR images.
Abstract: In some applications, such as image recognition or
compression, segmentation refers to the process of partitioning a
digital image into multiple segments. Image segmentation is typically
used to locate objects and boundaries (lines, curves, etc.) in images.
Image segmentation is to classify or cluster an image into several
parts (regions) according to the feature of image, for example, the
pixel value or the frequency response. More precisely, image
segmentation is the process of assigning a label to every pixel in an
image such that pixels with the same label share certain visual
characteristics. The result of image segmentation is a set of segments
that collectively cover the entire image, or a set of contours extracted
from the image. Several image segmentation algorithms were
proposed to segment an image before recognition or compression. Up
to now, many image segmentation algorithms exist and be
extensively applied in science and daily life. According to their
segmentation method, we can approximately categorize them into
region-based segmentation, data clustering, and edge-base
segmentation. In this paper, we give a study of several popular image
segmentation algorithms that are available.
Abstract: In this paper, we present a new segmentation approach
for focal liver lesions in contrast enhanced ultrasound imaging. This
approach, based on a two-cluster Fuzzy C-Means methodology,
considers type-II fuzzy sets to handle uncertainty due to the image
modality (presence of speckle noise, low contrast, etc.), and to
calculate the optimum inter-cluster threshold. Fine boundaries are
detected by a local recursive merging of ambiguous pixels. The
method has been tested on a representative database. Compared to
both Otsu and type-I Fuzzy C-Means techniques, the proposed
method significantly reduces the segmentation errors.
Abstract: This paper presents the local mesh co-occurrence
patterns (LMCoP) using HSV color space for image retrieval system.
HSV color space is used in this method to utilize color, intensity and
brightness of images. Local mesh patterns are applied to define the
local information of image and gray level co-occurrence is used to
obtain the co-occurrence of LMeP pixels. Local mesh co-occurrence
pattern extracts the local directional information from local mesh
pattern and converts it into a well-mannered feature vector using gray
level co-occurrence matrix. The proposed method is tested on three
different databases called MIT VisTex, Corel, and STex. Also, this
algorithm is compared with existing methods, and results in terms of
precision and recall are shown in this paper.
Abstract: In this paper, we present a new segmentation approach
for liver lesions in regions of interest within MRI (Magnetic
Resonance Imaging). This approach, based on a two-cluster Fuzzy CMeans
methodology, considers the parameter variable compactness
to handle uncertainty. Fine boundaries are detected by a local
recursive merging of ambiguous pixels with a sequential forward
floating selection with Zernike moments. The method has been tested
on both synthetic and real images. When applied on synthetic images,
the proposed approach provides good performance, segmentations
obtained are accurate, their shape is consistent with the ground truth,
and the extracted information is reliable. The results obtained on MR
images confirm such observations. Our approach allows, even for
difficult cases of MR images, to extract a segmentation with good
performance in terms of accuracy and shape, which implies that the
geometry of the tumor is preserved for further clinical activities (such
as automatic extraction of pharmaco-kinetics properties, lesion
characterization, etc.).
Abstract: Optic disk segmentation plays a key role in the mass
screening of individuals with diabetic retinopathy and glaucoma
ailments. An efficient hardware-based algorithm for optic disk
localization and segmentation would aid for developing an automated
retinal image analysis system for real time applications. Herein,
TMS320C6416DSK DSP board pixel intensity based fractal analysis
algorithm for an automatic localization and segmentation of the optic
disk is reported. The experiment has been performed on color and
fluorescent angiography retinal fundus images. Initially, the images
were pre-processed to reduce the noise and enhance the quality. The
retinal vascular tree of the image was then extracted using canny
edge detection technique. Finally, a pixel intensity based fractal
analysis is performed to segment the optic disk by tracing the origin
of the vascular tree. The proposed method is examined on three
publicly available data sets of the retinal image and also with the data
set obtained from an eye clinic. The average accuracy achieved is
96.2%. To the best of the knowledge, this is the first work reporting
the use of TMS320C6416DSK DSP board and pixel intensity based
fractal analysis algorithm for an automatic localization and
segmentation of the optic disk. This will pave the way for developing
devices for detection of retinal diseases in the future.
Abstract: Background subtraction and temporal difference are
often used for moving object detection in video. Both approaches are
computationally simple and easy to be deployed in real-time image
processing. However, while the background subtraction is highly
sensitive to dynamic background and illumination changes, the
temporal difference approach is poor at extracting relevant pixels of
the moving object and at detecting the stopped or slowly moving
objects in the scene. In this paper, we propose a simple moving object
detection scheme based on adaptive background subtraction and
temporal difference exploiting dynamic background updates. The
proposed technique consists of histogram equalization, a linear
combination of background and temporal difference, followed by the
novel frame-based and pixel-based background updating techniques.
Finally, morphological operations are applied to the output images.
Experimental results show that the proposed algorithm can solve the
drawbacks of both background subtraction and temporal difference
methods and can provide better performance than that of each method.
Abstract: In this paper a novel color image compression
technique for efficient storage and delivery of data is proposed. The
proposed compression technique started by RGB to YCbCr color
transformation process. Secondly, the canny edge detection method is
used to classify the blocks into the edge and non-edge blocks. Each
color component Y, Cb, and Cr compressed by discrete cosine
transform (DCT) process, quantizing and coding step by step using
adaptive arithmetic coding. Our technique is concerned with the
compression ratio, bits per pixel and peak signal to noise ratio, and
produce better results than JPEG and more recent published schemes
(like CBDCT-CABS and MHC). The provided experimental results
illustrate the proposed technique that is efficient and feasible in terms
of compression ratio, bits per pixel and peak signal to noise ratio.
Abstract: In this paper, we are interested in the problem of
finding similar images in a large database. For this purpose we
propose a new algorithm based on a combination of the 2-D
histogram intersection in the HSV space and statistical moments. The
proposed histogram is based on a 3x3 window and not only on the
intensity of the pixel. This approach overcome the drawback of the
conventional 1-D histogram which is ignoring the spatial distribution
of pixels in the image, while the statistical moments are used to
escape the effects of the discretisation of the color space which is
intrinsic to the use of histograms. We compare the performance of
our new algorithm to various methods of the state of the art and we
show that it has several advantages. It is fast, consumes little memory
and requires no learning. To validate our results, we apply this
algorithm to search for similar images in different image databases.
Abstract: When neck pain is associated with pain, numbness, or
weakness in the arm, shoulder, or hand, further investigation is
needed as these are symptoms indicating pressure on one or more
nerve roots. Evaluation necessitates a neurologic examination and
imaging using an MRI/CT scan. A degenerating disc loses some
thickness and is less flexible, causing inter-vertebrae space to narrow.
A radiologist diagnoses an Intervertebral Disc Degeneration (IDD) by
localizing every inter-vertebral disc and identifying the pathology in
a disc based on its geometry and appearance. Accurate localizing is
necessary to diagnose IDD pathology. But, the underlying image
signal is ambiguous: a disc’s intensity overlaps the spinal nerve
fibres. Even the structure changes from case to case, with possible
spinal column bending (scoliosis). The inter-vertebral disc
pathology’s quantitative assessment needs accurate localization of the
cervical region discs. In this work, the efficacy of multilevel set
segmentation model, to segment cervical discs is investigated. The
segmented images are annotated using a simple distance matrix.
Abstract: Driver fatigue is an important factor in the increasing
number of road accidents. Dynamic template matching method was
proposed to address the problem of real-time driver fatigue detection
system based on eye-tracking. An effective vision based approach
was used to analyze the driver’s eye state to detect fatigue. The driver
fatigue system consists of Face detection, Eye detection, Eye
tracking, and Fatigue detection. Initially frames are captured from a
color video in a car dashboard and transformed from RGB into YCbCr
color space to detect the driver’s face. Canny edge operator was used
to estimating the eye region and the locations of eyes are extracted.
The extracted eyes were considered as a template matching for eye
tracking. Edge Map Overlapping (EMO) and Edge Pixel Count
(EPC) matching function were used for eye tracking which is used to
improve the matching accuracy. The pixel of eyeball was tracked
from the eye regions which are used to determine the fatigue state of
the driver.