Aboul Ella Hassanien (Abo)

n/a

Face sketch recognition is one of the recent biometrics,
which is used to identify criminals. In this paper, a
proposed model is used to identify face sketch images based
on local invariant features. In this model, two local invariant
feature extraction methods, namely, Scale Invariant Feature
Transform (SIFT) and Local Binary Patterns (LBP) are used
to extract local features from photos and sketches. Minimum
distance and Support Vector Machine (SVM) classifiers are used
to match the features of an unknown sketch with photos. Due to
high dimensional features, Direct Linear Discriminant Analysis
(Direct-LDA) is used. CHUK face sketch database images is used
in our experiments. The experimental results show that SIFT
method is robust and it extracts discriminative features than LBP.
Moreover, different parameters of SIFT and LBP are discussed
and tuned to extract robust and discriminative features.

Grey Wolf Optimization (GWO) algorithm is a
new meta-heuristic method, which is inspired by grey wolves,
to mimic the hierarchy of leadership and grey wolves hunting
mechanism in nature. This paper presents a hybrid model that
employs grey wolf optimizer (GWO) along with support vector
machines (SVMs) classification algorithm to improve the classification
accuracy via selecting the optimal settings of SVMs
parameters. The proposed approach consists of three phases;
namely pre-processing, feature extraction, and GWO-SVMs
classification phases. The proposed classification approach was
implemented by applying resizing, remove background, and
extracting color components for each image. Then, feature
vector generation has been implemented via applying PCA
feature extraction. Finally, GWO-SVMs model is developed
for selecting the optimal SVMs parameters. The proposed
approach has been implemented via applying One-againstOne
multi-class SVMs system using 3-fold cross-validation. The
datasets used for experiments were constructed based on real
sample images of bell pepper at different stages, which were
collected from farms in Minya city, Upper Egypt. Datasets
of total 175 images were used for both training and testing
datasets. Experimental results indicated that the proposed
GWO-SVMs approach achieved better classification accuracy
compared to the typical SVMs classification algorithm.

Thermal imaging is a technology with property of
seeing objects in the darkness. Such property makes this technology
very important tool for security and surveillance applications.
In this paper, a thermal image authentication technique using
hash function is proposed. In this technique, the thermal images
are used as cover images and bits from secret data (i.e. messages
or images) are then hidden in the cover images. This is achieved
by using the hash function and IntegerWavelet Transform (IWT).
1, 2 and 3 bits per bytes have been hidden in both horizontal
and vertical components of wavelet transform. The proposed
technique has been evaluated based on mean square error (MSE),
peak signal to noise ratio (PSNR), image fidelity (IF) and standard
deviation (SD). The results have shown better performance of the
proposed technique comparing with the most related work.

Abstract—This paper presents a bio-inspired optimized classification approach for assessing water quality. As fish liver histopathology is a good biomarker for detecting water pollution, the proposed classification approach uses fish liver microscopic images in order to detect water pollution and determine water
quality. The proposed approach includes three phases; preprocessing, feature extraction, and classification phases. Color histogram and Gabor wavelet transform have been utilized for feature extraction phase. The Machine Learning (ML) Support Vector Machines (SVMs) classification algorithm has been employed,
along with the bio-inspired Gray Wolf Optimization (GWO) algorithm for optimizing SVMs parameters, in order to classify water pollution degree. Experimental results showed that the average accuracy achieved by the proposed GWO-SVMs classification approach exceeded 95% considering a variety of
water pollutants.

Apoptosis is an imperative constituent of various processes including proper
progression and functioning of the immune system, embryonic development as well
as chemical-induced cell death. Improper apoptosis is a reason in numerous human/
animal’s conditions involving ischemic damage, neurodegenerative diseases,
autoimmune disorders and various types of cancer. An outstanding feature of
neurodegenerative diseases is the loss of specific neuronal populations. Thus, the
detection of the dead cells is a necessity. This paper proposes a novel algorithm to
achieve the dead cells detection based on color intensity and contrast changes and
aims for fully automatic apoptosis detection based on image analysis method. A
stained cultures images using Caspase stain of albino rats hippocampus specimens
using light microscope (total 21 images) were used to evaluate the system
performance. The results proved that the proposed system is efficient as it achieved
high accuracy (98.89 ± 0.76 %) and specificity (99.36 ± 0.63 %) and good mean
sensitivity level of (72.34 ± 19.85 %).

In this paper, we propose a new attribute reduction strat-
egy based on rough sets and grey wolf optimization (GWO). Rough sets
have been used as an attribute reduction technique with much success,
but current hill-climbing rough set approaches to attribute reduction are
inconvenient at nding optimal reductions as no perfect heuristic can
guarantee optimality. Otherwise, complete searches are not feasible for
even medium sized datasets. So, stochastic approaches provide a promis-
ing attribute reduction technique. Like Genetic Algorithms, GWO is a
new evolutionary computation technique, mimics the leadership hierar-
chy and hunting mechanism of grey wolves in nature. The grey wolf
optimization nd optimal regions of the complex search space through
the interaction of individuals in the population. Compared with GAs,
GWO does not need complex operators such as crossover and mutation,
it requires only primitive and easy mathematical operators, and is com-
putationally inexpensive in terms of both memory and runtime. Experi-
mentation is carried out, using UCI data, which compares the proposed
algorithm with a GA-based approach and other deterministic rough set
reduction algorithms. The results show that GWO is ecient for rough
set-based attribute reduction.

Image segmentation is an important task in the image processing
field. Efficient segmentation of images considered important for further object
recognition and classification. This paper presents a novel segmentation
approach based on Particle Swarm Optimization (PSO) and an adaptive
Watershed algorithm. An application of liver CT imaging has been chosen and
PSO approach has been applied to segment abdominal CT images. The
experimental results show the efficiency of the proposed approach and it
obtains overall accuracy 94% of good liver extraction.

Fish detection and identication are important steps towards
monitoring sh behavior. The importance of such monitoring step comes
from the need for better understanding of the sh ecology and issuing
conservative actions for keeping the safety of this vital food resource.
The recent advances in machine learning approaches allow many appli-
cations to easily analyze and detect a number of sh species. The main
competence between these approaches is based on two main detection
parameters: the time and the accuracy measurements. Therefore, this
paper proposes a sh detection approach based on BAT optimization
algorithm (BA). This approach aims to reduce the classication time
within the sh detection process. The performance of this system was
evaluated by a number of well-known machine learning classiers, KNN,
ANN, and SVM. The approach was tested with 151 images to detect the
Nile Tilapia sh species and the results showed that k-NN can achieve
high accuracy 90%, with feature reduction ratio close to 61% along with
a noticeable decrease in the classication time.

Fish detection and identication are important steps towards
monitoring sh behavior. The importance of such monitoring step comes
from the need for better understanding of the sh ecology and issuing
conservative actions for keeping the safety of this vital food resource.
The recent advances in machine learning approaches allow many appli-
cations to easily analyze and detect a number of sh species. The main
competence between these approaches is based on two main detection
parameters: the time and the accuracy measurements. Therefore, this
paper proposes a sh detection approach based on BAT optimization
algorithm (BA). This approach aims to reduce the classication time
within the sh detection process. The performance of this system was
evaluated by a number of well-known machine learning classiers, KNN,
ANN, and SVM. The approach was tested with 151 images to detect the
Nile Tilapia sh species and the results showed that k-NN can achieve
high accuracy 90%, with feature reduction ratio

This paper presents a bio-inspired optimized classification model for
assessing water quality. As fish gills histopathology is a good biomarker for indicating
water pollution, the proposed classification model uses fish gills microscopic
images in order to asses water pollution and determine water quality.
The proposed model comprises five phases; namely, case representation for
defining case attributes via pre-processing and feature extraction steps, retrieve,
reuse/adapt, revise, and retain phases. Wavelet transform and edge detection algorithms
have been utilized for feature extraction stage. Case-based reasoning
(CBR) has been employed, along with the bio-inspired Gray Wolf Optimization
(GWO) algorithm, for optimizing feature selection and the k case retrieval parameters
in order to asses water pollution. The datasets used for conducted experiments
in this research contain real sample microscopic images for fish gills
exposed to copper and water pH in different histopathlogical stages. Experimental
results showed that the average accuracy achieved by the proposed GWO-CBR
classification model exceeded 97.2% considering variety of water pollutants.

Face extraction is considered a very important step in devel-
oping a recognition system. It is a challenging task as there are dierent
face expressions, rotations, and artifacts including glasses and hats. In
this paper, a face extraction model is proposed for thermal IR human face
images based on superpixel technique. Superpixels can improve the com-
putational eciency of algorithms as it reduces hundreds of thousands of
pixels to at most a few thousand superpixels. Superpixels in this paper
are formulated using the quick-shift method. The Quick-Shift's superpix-
els and automatic thresholding using a simple Otsu's thresholding help
to produce good results of extracting faces from the thermal images. To
evaluate our approach, 18 persons with 22,784 thermal images were used
from the Terravic Facial IR Database. The Experimental results showed
that the proposed model was robust against image illumination, face
rotations, and dierent artifacts in many cases compared to the most
related work.

The aim of geophysical inverse problem is to determine the
spatial distribution and depths to buried targets at a variety of scales;
it ranges from few centimetres to many kilometres. To identify ore bodies,
extension of archaeological targets, old mines, unexploded ordnance
(UXO) and oil traps, the linear geomagnetic inverse problem resulted
from the Fredholm integral equation of the first kind is solved using
many strategies. The solution is usually affected by the condition of
the kernel matrix of the linear system and the noise level in the data
collected. In this paper, regularized Kaczmarz method is used to get a
regularized solution. This solution is taken as an initial solution to bat
swarm algorithm (BA) as a global swarm-based optimizer to refine the
quality and reach a plausible model. To test efficiency, the proposed hybrid
method is applied to different synthetic examples of different noise
levels and different dimensions and proved an advance over using the
Kaczmarz method.

This paper proposes a recommender system to predict and suggest a
set of rehabilitation methods for patients with spinal cord injuries (SCI). The proposed
system automates, stores and monitors the heath conditions of SCI patients.
The International Classification of Functioning, Disability and Health classification
(ICF) is used to stores and monitors the progress in health status. A set of
similarity measures are utilized in order to get the similarity between patients and
predict the rehabilitation recommendations. Experimental results showed that the
proposed recommender system has obtained an accuracy of 98% via implementing
the cosine similarity measure.

Enzymes are important in our life due to its importance in the most biological processes. Thus, classification of the enzyme’s function is vital to save efforts and time in the labs. In this paper, we propose an approach based on sequence alignment to compute the similarity between any two sequences. In the proposed approach, two different sequence alignment methods are used, namely, local and global sequence alignment. There are different score matrices such as BLOSUM and PAM are used in the local and global alignment to calculate the similarity between the unknown sequence and each sequence of the training sequences. The results which obtained were acceptable to some extent compared to previous studies that have surveyed.

In this paper, a region-based image fusion approach were proposed based on the stationary wavelet transform (SWT) in conjunction with marker-controlled watershed segmentation technique. The SWT is redundant, linear and shift invariant and these properties allow SWT to be realized exploiting a recursive algorithm and gives a better approximation than the DWT. The performance of the fusion approach is illustrated via experimental results obtained with a broad series of images and the experimental results used the MODIS multi-spectral bands and Spot panchromatic band to validate the proposed image fusion technique. Moreover, the visual presentation and different evaluation criteria including the standard deviation, the entropy information, the correlation coefficient, the root mean square error, the peak signal to noise ratio and the structural similarity index was used to evaluate the obtained results. The proposed approach achieves superior results compared with the existing work.

In this paper, a plant identification approach using 2D digital leaves images is proposed. The approach made use of two methods of features extraction (one-dimensional (1D) and two-dimensional (2D) techniques) and the Bagging classifier. For the 1D-based method, PCA and LDA techniques were applied, while 2D-PCA and 2D-LDA algorithms were used for the 2D-based method. To classify the extracted features in both methods, the Bagging classifier, with the decision tree as a weak learner, was used. The proposed approach, with its four feature extraction techniques, was tested using Flavia dataset which consists of 1907 colored leaves images. The experimental results showed that the accuracy and the performance of our approach, with the 2D-PCA and 2D-LDA, was much better than using the PCA and LDA. Furthermore, it was proven that the 2D-LDA-based method gave the best plant identification accuracy and increasing the weak learners of the Bagging classifier leaded to a better accuracy. Also, a comparison with the most related work showed that our approach achieved better accuracy under the same dataset and same experimental setup.