Mohammed Altaei - Academia.edu (original) (raw)

Papers by Mohammed Altaei

Al-Nahrain journal of science, Jun 1, 2021

Agriculture is one of the most important professions in many countries, including Iraq, as the Ir... more Agriculture is one of the most important professions in many countries, including Iraq, as the Iraqi financial system depends on agricultural production and great attention should be paid to concerns about agricultural production. Because plants are exposed to many diseases and monitoring plant diseases with the help of specialists in the agricultural region can be very expensive. There is a need for a system capable of automatically detecting diseases. The aim of the research proposed is to create a model that classifies and predicts leaf diseases in plants. This model is based on a convolution network, which is a kind of deep learning. The dataset used in this study called (Plant Village) was downloaded from the kaggle website. The dataset contains 34,934 RGB images, and the deep CNN model can efficiently classify 15 different classes of healthy and diseased plants using the leaf images. The model used techniques to augment data and dropout. The Softmax output layer was used with the categorical cross-entropy loss function to apply the CNN model proposed with the Adam optimization technique. The results obtained by the proposed model were 97.42% in the training phase and 96.18% in the testing phase.

International Journal of Computer (IJC), Dec 16, 2017

In the present research, a face recognition method is proposed based on the concept of linear dis... more In the present research, a face recognition method is proposed based on the concept of linear discriminant analysis (LDA) method. The LDA requires input some of image models to analyze and discriminate them, the newly proposed idea is the use of a number of textural features instead of face image pixels to be input the LDA procedure. The employed textural features were ten, which are computed for each face image using the grey level co-occurrence matrix (GLCM) method. The proposed face recognition method consists of two phases: enrollment and recognition. The enrollment phase is responsible for collecting the features of each face image to be a comparable models stored in the database, while the recognition phase is responsible on comparing the extracted features of input unknown face with that stored in the database. The comparison results a number of percentage values, each refers to the similarity between the input unknown face with the models in the database. The recognition decision is then issued according to the comparison results. The results showed that the system performed the recognition test with a recognition percent of about 94%, whereas the validation test showed that the system performance was about 92%. Frequent practices showed that the behavior of the recognition is acceptable and it is enjoying with the ability to be improved.

Al-Nahrain journal of science, Dec 1, 2018

Image restoration is reconstructing the true image starting from degraded (blurred and noisy) ima... more Image restoration is reconstructing the true image starting from degraded (blurred and noisy) image version. This problem could be handled as blind or non-blind mode depending on whether functional knowledge or point spread function (PSF) knowledge is available. These knowledge are related to the type and parameters of the additive noise such as; distribution, mean, and variance. Accordingly, the present work aims to restore the original image using adaptive Mead's algorithm applied on degraded version. The proposed method is individually applied on the three color components; red, green, and blue (RGB) of the image. The results are quantitatively and qualitatively compared to the original one using two quality measures, they are: mean squared error (MSE) and cross correlation coefficient (CCC). Results showed valued performance of the proposed method when restoring the degraded images. Quality measures proved that the blue component was reconstructed better than the red, and the red was reconstructed better than the green component. Frequent tests showed the matching score between the reconstructed image and the original one was about 97%, which ensure the validation of the proposed method and correct path of computations.

Iraqi journal of science, Sep 30, 2021

Digital images are open to several manipulations and dropped cost of compact cameras and mobile p... more Digital images are open to several manipulations and dropped cost of compact cameras and mobile phones due to the robust image editing tools. Image credibility is therefore become doubtful, particularly where photos have power, for instance, news reports and insurance claims in a criminal court. Images forensic methods therefore measure the integrity of image by apply different highly technical methods established in literatures. The present work deals with copy move forgery images of Media Integration and Communication Center Forgery (MICC-F2000) dataset for detecting and revealing the areas that have been tampered portion in the image, the image is sectioned into non overlapping blocks using Simple liner iterative clustering (SLIC) method. Then, Scale invariant feature transform (SIFT) descriptor is applied on the grey of the handled image to gives distinctive key points that classified by K-Nearest neighbor to detect and localize the forged portion in the tempered image. The forgery detection results gave a performance percent of about 98%, which reflects the ability of the KNN classifier that cooperated with SIFT descriptor to detect the forged portions even if the forged area is rotated or scaled or both of them.

Journal of Robotics and Control (JRC), 2023

Wireless Sensor Network (WSN) is a high potential technology used in many fields (agriculture, ea... more Wireless Sensor Network (WSN) is a high potential technology used in many fields (agriculture, earth, environmental monitoring, resources union, health, security, military, and transport, IoT technology). The band width of each cluster head is specific, thus, the number of sensors connected to each cluster head is restricted to a maximum limit and exceeding it will weaken the connection service between each sensor and its corresponding cluster head. This will achieve the research objective which refers to reaching the state where the proposed system energy is stable and not consuming further more cost. The main challenge is how to distribute the cluster heads regularly on a specified area, that's why a solution was supposed in this research implies finding the best distribution of the cluster heads using a genetic algorithm. Where using an optimization algorithm, keeping in mind the cluster heads positions restrictions, is an important scientific contribution in the research field of interest. The novel idea in this paper is the crossover of two-dimensional integer encoded individuals that replacing an opposite region in the parents to produce the children of new generation. The mutation occurs with probability of 0.001, it changes the type of 0.05 sensors found in handled individual. After producing more than 1000 generations, the achieved results showed lower value of fitness function with stable behavior. This indicates the correct path of computations and the accuracy of the obtained results. The genetic algorithm operated well and directed the process towards improving the genes to be the best possible at the last generation. The behavior of the objective function started to be regular gradually throughout the produced generations until reaching the best product in the last generation where it is shown that all the sensors are connected to the nearest cluster head. As a conclusion, the genetic algorithm developed the sensors' distribution in the WSN model, which confirms the validity of applying of genetic algorithms and the accuracy of the results.

Al-Nahrain journal of science, Mar 1, 2021

Due to the extreme robust image editing techniques, digital images are subject to multiple manipu... more Due to the extreme robust image editing techniques, digital images are subject to multiple manipulations and decreased costs for digital camera and smart phones. Therefore, image credibility is becoming questionable, specifically when images have strong value, such as news report and insurance claims in a crime court. Therefore, image forensic methods test the integrity of the images by applying various highly technical methods set out in the literature. The present work deals with one important research module is the recognition of forged part that applied on copy move forgery images. Two datasets MICC-F2000 and CoMoFoD are used, these datasets are usually adopted in the field of interest. The module concerned with recognizing which is the source image portion and which is the target one of that already detected. Thus, the two detected tampered parts of the image are recognized the original one from them, the other is then referred as forged or tampered part. The proposed module used the buster net of three neural networks that basically adopted the principle of training by using Convolution Neural Network (CNN) to extract the most important features in the images. The first and second networks are parallel working to detect and identify areas that have been tampered with, and then display them through two masks. While the last network classifier takes a copy of these two catchers to decide which is the source image portion from the two detected ones. The achieved recognition results were about F-score 98.98% even if the forged area is rotated or scaled or both of them. Also, the recognition results of the forged image part was 98% when using images do not contributed in the training phase, which refers to that the proposed module is more confident and reliable.

Nucleation and Atmospheric Aerosols, 2020

Iraqi journal of science, Jan 28, 2019

This research is concerned with designing and simulating an auto control system for a car provide... more This research is concerned with designing and simulating an auto control system for a car provided with obstacle avoidance sensors. This car is able to pass through predefined path an around the detected obstacles, and then come back to the intended path. The IR sensor detects the existence of the obstacle through an assumed range of detection, while the visual sensor (camera) feeds back an image including the path that contains an obstacle, which can be useful for determining the obstacle's length, speed, and direction. According to such information, the controller creates transient away point along the longitudinal axis of the obstacle which is the same as the transverse axis of the simulator path at an assumed distance from the obstacle. The robotic car will direct toward the transient point for avoiding the obstacle, which directly comeback into the original rout once when reaching the transient point. This strategy enables the car to move far away from the obstacle and then return it into planned path.

International Journal of Advanced Research in Computer Science, Feb 20, 2018

This paper presents a method for SIC to classify a PatternNet satellite image dataset taken from ... more This paper presents a method for SIC to classify a PatternNet satellite image dataset taken from Google Earth and Google Map Application newly adopted in 2017, this SIC method use firstly a pre-processing step to verify the way of how represent the gray level of each sample image using multiple features based descriptors to handling the problem of selecting the descriptors for SIC. It suggested to use several type of texture feature extraction method, each of these method tested with the Support Vector Machine (SVM) to verify its ability to extract d a discriminative features. Also the feature selection method used to remove the less informative features of each method to get the more relevant features, finally the decision result of each feature extraction method from the classifier tested with feature combination methods, it is used to improve the final decision of the SIC method by combine multi feature extraction method.

Periodicals of Engineering and Natural Sciences (PEN), May 20, 2023

In this paper, we propose an efficient image hiding method that combines image encryption and cha... more In this paper, we propose an efficient image hiding method that combines image encryption and chaotic mapping to introduce adaptive data hiding for improving the security and robustness of image data hiding in cover audio. The feasibility of using chaotic maps to hide encrypted image in the high frequency band of the audio is investigated. The proposed method was based on hiding the image data in the noisiest part of the audio, which is the high frequency band that was extracted by the zero crossing filter. Six types of digital images were used, each of size fit the length of used audio, this to facilitate the process of hiding them among the audio samples. The input image was encrypted by a one-time pad method, then its bits were hidden in the audio by the chaotic map. The process of retrieving the image from the audio was in the opposite way, where the image data was extracted from the high frequency band of the audio file, and then the extracted image was decrypted to produce the retrieved image. Four qualitative metrics were used to evaluate the hiding method in two paths: the first depends on comparing the retrieved image with the original image, while the second depends on comparing the audio containing the image data with the original audio once, and another time by comparing the cover audio with the original audio. The results of the quality metrics proved the efficiency of the proposed method, and it showed a slight and unnoticed effect between the research materials, which indicates the success of the hiding process and the validity of the research path.

Iraqi journal of science, Feb 27, 2022

Agriculture improvement is a national economic issue that extremely depends on productivity. The ... more Agriculture improvement is a national economic issue that extremely depends on productivity. The explanation of disease detection in plants plays a significant role in the agriculture field. Accurate prediction of the plant disease can help treat the leaf as early as possible, which controls the economic loss. This paper aims to use the Image processing techniques with Convolutional Neural Network (CNN). It is one of the deep learning techniques to classify and detect plant leaf diseases. A publicly available Plant village dataset was used, which consists of 15 classes, including 12 diseases classes and 3 healthy classes. The data augmentation techniques have been used. In addition to dropout and weight regularization, which leads to good classification results by preventing the model from over fitting. The model was optimized with the Adam optimization technique. The obtained results in terms of performance were 98.08% in the testing stage and 99.24% in the training stage. Next, the baseline model was improved using early stopping, and the accuracy increased to 98.34% on the testing set and 99.64% on the training set. The substantial success rate makes it a valuable advisory method to detect and identify transparently.

Journal of Al-Nahrain University-Science, Mar 1, 2010

This paper aims at enabling computers to recognize faces without human intervention. This is acco... more This paper aims at enabling computers to recognize faces without human intervention. This is accomplished by capturing five images for the face under test, the information of five images are concentrated in one integral image by using KL transforms. The wavelet transform was used to diminution the integrated image, DCT was applied on the first band of the wavelet transformed image to extract the recognition features. The recognition features assumed to be driven from the first six DCT coefficients. The recognition was established by searching a match between the features extracted from the test image and library of the face image models. The performance of the designed recognition system gave a promising verification percentage of about 83% in which the contribution weights of the adopted features were unequally.

American Scientific Research Journal for Engineering, Technology, and Sciences, Feb 25, 2017

The use of efficient image classification methods gains most interest due to its close relation w... more The use of efficient image classification methods gains most interest due to its close relation with the improvements happen in the fields of compression and communications. Fractal geometry is receiving increased attention as a quantitative and qualitative model for natural phenomena description, which can establish an active classification technique when applied on satellite image. In this paper, the used satellite image is taken by Landsat for Al-Kut city in Iraq. Different parts of this image that contains different visible classes are chosen manually to be a training area. The training areas are passing two stages: segmentation and classification. To credit effective segmentation, the training areas are segmented by a hybrid technique consists of two sequenced methods: Diagonal (Dg) method that operated inside the quadtree (Q) method. The hybrid method segments each squared image block into either four quadrants or two triangular blocks according to uniformity criterion. Then, unsupervised classification is applied depending on the fractal feature. The fractional Brownian motion (FBM) is the fractal feature that employed for classification. The classification is implemented for each image segment; squared or triangular. The results of FBM are grouped into five deferent clusters; each represents distinct class of image. The center of each group and its dispersion distance are stored in a database table to be used in the classification of whole image. The classification results gave 95% classification score, which ensures the ability of FBM to recognize different satellite image regions when used as fractal feature.

Iraqi journal of science, 2011

The motivation we address in this paper is to find out a generic method used to segment and class... more The motivation we address in this paper is to find out a generic method used to segment and classify different types of conceptual images. A novel median based method was proposed as primary stage for image segmentation, in which the image is partitioned into fixed sized quadrants called kernels. The size of kernels in a specific image is determined according to the spectral uniformity measurements. Later, Ant Colony Optimization (ACO) is used to find out the optimal number of classes may exist in the image, and then classify the image in terms of the determined classes. Different types of images with different semantic concepts were used to test the proposed classification method. The results obtained by ACP ensure the success of the proposed method and the effective performance of classification.

Periodicals of Engineering and Natural Sciences (PEN), Jun 24, 2022

Wireless sensor network is one of the main technology trends that used in several different appli... more Wireless sensor network is one of the main technology trends that used in several different applications for collecting, processing, and distributing a vast range of data. It becomes an essential core technology for many applications related to sense surrounding environment. In this paper, a two-dimensional WSN scheme was utilized for obtaining various WSN models that intended to be optimized by genetic algorithm for achieving optimized WSN models. Such optimized WSN models might contain two cluster heads that are close to each other, in which the distance between them included in the sensing range, and this demonstrates the presence of a redundant number of cluster heads. This problem exceeded by reapplying the clustering of all sensors found in the WSN model. The distance measure was used to detect handled problem, while K-means clustering was used to redistributing sensors around the alternative cluster head. The result was extremely encouraging in rearranging the dispersion of sensors in the detecting region with a conservative method of modest number of cluster heads that acknowledge the association for all sensors nearby.

2023 Al-Sadiq International Conference on Communication and Information Technology (AICCIT)

Nucleation and Atmospheric Aerosols, 2023

Using survival function and transmuted formula to produce lifetime models with application on rea... more Using survival function and transmuted formula to produce lifetime models with application on real data set

Periodicals of Engineering and Natural Sciences (PEN)

THE SECOND INTERNATIONAL SCIENTIFIC CONFERENCE (SISC2021): College of Science, Al-Nahrain University