Papers by Anwar H. Al-Saleh
Determine distances area of traffic lights using image processing algorithms
Nucleation and Atmospheric Aerosols, 2022
Iraqi journal of science, Apr 30, 2023
Optical Character Recognition (OCR) research includes computer vision, artificial intelligence, a... more Optical Character Recognition (OCR) research includes computer vision, artificial intelligence, and pattern recognition. Character recognition has garnered a lot of attention in the last decade due to its broad variety of uses and applications, including multiple-choice test data, business documents (e.g., ID cards, bank notes, passports, etc.), and automatic number plate recognition. This paper introduces an automatic recognition system for printed numerals. The automatic reading system is based on extracting local statistical and geometrical features from the text image. Those features are represented by eight vectors extracted from each digit. Two of these features are local statistical (A, A th), and six are local geometrical (P 1 , P 2 , P 3 , P 4 , P 5 , and P 6). Thus, the database created consists of 1120 statistical and geometrical features. For the purpose of recognition, the features of the test image are compared with the features of all the images saved in the database depending on the value of the Minimum Distance (MD). All digits (0-9) were identified with 100% accuracy. The average computational time required to recognize a numeral at any font size is 0.06879 seconds.
Indonesian Journal of Electrical Engineering and Computer Science
Image segmentation is an image processing technique that concentrated on finding and locating the... more Image segmentation is an image processing technique that concentrated on finding and locating the parts of an image such as objects and boundaries. The purpose of locating these parts is for use in further processing analysis of an image such as recognition tasks, and content-based image retrieval. This paper introduces the segmentation procedure using a proposed template of features with watershed or morphology operations. Features template based on segmentation process conveys pixels’ intensities property perceived by the threshold value of histogram representation and texture feature where the regions are characterized by their texture content using standard deviation (SD) filtering. Wiener filter and histogram equalization (HE) techniques are used as preprocessing operations to enhance the image quality. The edge detector operator is hybridized to boost the segmentation process. Some statistical metrics are used for assessing and analyzing the performance of the stages in the pr...
SPE International Heavy Oil Conference and Exhibition, 2018
Flow zonation and permeability estimation is a common task in reservoir characterization. Typical... more Flow zonation and permeability estimation is a common task in reservoir characterization. Typically, integration of openhole log data with a conventional and special core analysis solves this problem. We present a Bayesian-based method for identifying hydraulic flow units in uncored wells using the theory of hydraulic flow units (HFUs) and subsequently compute permeability using wireline log data. We use a nonlinear optimization scheme on the basis of the probability plot to determine pertinent statistical parameters of each flow unit. Next, we couple these results with the F-test and the Akaike's criteria with the purpose of establishing the optimal number of HFUs present in the core data set. Then, we allocate the core data into their respective HFUs using the Bayes' theorem as clustering rule. Finally, we apply an inversion algorithm on the basis of Bayesian inference to predict permeability using only wireline data. We illustrate the application of the procedure with a carbonate reservoir having extensive conventional core data. The results show that the Bayesian-based clustering and inversion technique delivers permeability estimates that agree with the core data and with the results obtained from a pressure transient analysis.
A new contrast metrics to estimate the amount of distortion in image edges affected by the motion of the rotating object
Nucleation and Atmospheric Aerosols, 2023
Iraqi journal of science, Jan 30, 2023
The texture analysis of cancer cells leads to a procedure to distinguish spatial differences with... more The texture analysis of cancer cells leads to a procedure to distinguish spatial differences within an image and extract essential information. This study used two test tumours images to determine cancer type, location, and geometric characteristics (area, size, dimensions, radius, etc.). The suggested algorithm was designed to detect and distinguish breast cancer using the segmentation-based threshold technique. The method of texture analysis Grey Level Size Zone method was used to extract 11
Silver Prism Interface Plasmon Resonance for Biosensor in Ir-Visible Spectrum Region
Materials Science Forum
The performance of a surface Plasmon resonance (SPR) sensor with silver film was demonstrated. Th... more The performance of a surface Plasmon resonance (SPR) sensor with silver film was demonstrated. The Kretschmann setup's evanescent field, which can activate the sensor. The sensitivity and FWHM of the SPR sensor drop as the thickness of the silver layer in the metallic film increases. Using water as a sensing medium, it can create a simulation model at various thicknesses of the silver layers placed on the semicircular glass prism D-ZLAF50 with a thickness of dAg = 10–80 nm. The proposed sensor can function at wavelengths of up to 600,700nm in the visible area and the infrared region at wavelengths of 900 & 1000 nm. Optimum sensitivity (S = 100–140) may be observed in the visible and infrared spectrum with thicknesses ranging from dAg = (10–80) nm , ∆n = 0.1. At silver layer thicknesses, the values of SPR dip length and FWHM are excellent (40–60 nm).
Invariant Target Detection in Images through the Normalized 2-D Correlation Technique
arXiv (Cornell University), Feb 22, 2023
INTERNATIONAL CONFERENCE OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING ICCMSE 2021
Traffic light detection and recognition is important in advanced driver assistance systems in urb... more Traffic light detection and recognition is important in advanced driver assistance systems in urban environments when making the transition to autonomous driving. In this paper, an intelligent system was designed to recognize traffic lights in different times and conditions (day and night). The system depends on digital image processing techniques, which has three main stages: the image subtraction, the traffic signal segmentation, and distinction of traffic signals using Circular Hough Transform (CHT) method. The results indicated the efficiency and accuracy of the proposed system in detecting traffic signals, determining the area of each signal with time, and making the decision in detecting the state of the signal, whether it is bright or dark with time.
Nucleation and Atmospheric Aerosols, 2022
Abstract. The evaluation metric for images taken in different environments such as the effect of... more Abstract. The evaluation metric for images taken in different environments such as the effect of different levels of water depth is a critical need in inland and coastal water environments. The difficulties are due to the poor lighting conditions in addition to the absorption/scattering effects which degraders image’s optical properties in final. Image range finder technique allows to obtain an information of scene such as background, shape and depth measures of objects. The presented work estimated the distance-water depth variation by using two laser pointers of different wavelengths inside a white cork box fills with water in sequential depths starting from 0cm to 20cm with increasing in water level equal to 2cm for each case. The presented analytical study introduced four geometric models with progressive curves resulted in distance-water depth variations with an increasing relationship occupied by good matching in their fitting curve with average absolute value equal to 9.5 for measuring the distance between centers of the two laser spots and 1.2 for water depth estimation. The latter estimation matches the real values starting from water depth equal to 6cm and more. At final, the area variation for the red spot laser is more significant and detectable than for green one.
Traitement Du Signal, Jun 30, 2022
Static hand gesture recognition is critical in the development of a system for humancomputer inte... more Static hand gesture recognition is critical in the development of a system for humancomputer interaction. Many human-computer interactions, such as human-robot interaction, game control, control of smart home devices, and others, use hand gestures as a fundamental and natural language of the body. The direction of rotation of static hand gestures is the subject of this research, and the focus is on six degrees of rotation (0°, 45°, 90°, 180°, 270°, and 315°). This work presents an ideal approach that can recognize the angle of hand gestures based on the Aggregate Channel Features (ACF) detector. This approach consists of three main stages: preprocessing (image labelling), computer training, and hand angle detection based on the ACF detector. The training process consists of 25 stages. The static hand gesture dataset contained 569 images (361 for training and 208 for testing). The average time cost to detect all hand gesture angles was 0.9445 seconds, and all hand angles were recognized with 100% accuracy. This is a strong indication that supports our approach.
Introducing two Mathematical Models using Data Functional Approximation to Determine the Shadow Angles and Lengths in North of Baghdad City
Journal of Physics: Conference Series, 2021
In this study, two models are presented to estimate a shadow angle and length of an object locate... more In this study, two models are presented to estimate a shadow angle and length of an object located outdoor during daytime. A stick, with 50 cm length and diameter 1 cm, used to measure the shadow angle and length from 9 am to 3 pm for 1st, 11th, 12th, 21st, 22nd, and 31st of August, 1st, 11th, 12th, 21st, 22nd, and 30th of September, 11th, 12th, 25th, 26th, and 31st of October, 8th, 16th, 17th, 25th, 26th, and 30th of November, 1st, 16th, 17th, 22nd, and 23rd December 2019. The introduced model’s results, for shadow angles and shadow lengths, show good agreement with the real data. The Normalize mean square error (NMSE) criterion used to measure the quality matching between the real and modeled data. The highest value of NMSE between the real and result shadow angles and shadow length from model is 0.006% and 0.003% respectively.
Automatic Number Extraction from Fixed Imaging Distance
Iraqi Journal of Science
Developed countries are facing many challenges to convert large areas of existing services t... more Developed countries are facing many challenges to convert large areas of existing services to electronic modes, reflecting the current nature of workflow and the equipment utilized for achieving such services. For instance, electricity bill collection still tend to be based on traditional approaches (paper-based and relying on human interaction) making them comparatively time-consuming and prone to human error. This research aims to recognize numbers in mechanical electricity meters and convert them to digital figures utilizing Optical Character Recognition (OCR) in Matlab. The research utilized the location of red region in color electricity meters image to determine the crop region that contain the meters numbers, then extracts this numbers region and convert it into binary image and extract the numbers as a text using OCR technique. A camera for the Iphone 6 (8-megapixel) is used to take a snapshot of the meter screen. The red box in the meter is used to calculate the window...
Iraqi Journal of Science
The features of plasmonic surface frequency sensor technology, such as the small number of ... more The features of plasmonic surface frequency sensor technology, such as the small number of sensor samples required, electromagnetic interference, and high sensitivity, have been found to be highly important.. In this paper, a simulation program was created in Matlab_b2018 by adopting Fresnel equations for calculating the reflectivity of the electromagnetic wave between different media. A surface plasmon resonance sensor based on electromagnetic wavelengths within the range (100 nm to 1000 nm) has been proposed. The transfer matrix was used for a system consisting of four different media. The first medium is a semicircular BK7 glass prism, the second medium is a gold layer (40 nm thick), then a bismuth layer of variable thicknes(10–80) nm, and the last medium is air as the sensing medium. The surface plasmon resonance (SPR) technique was adopted based on the Kretschmann configuration in the simulation of the proposed system. The simulation results showed that there is no SPR w...
Movi-color target analysis based on using minimum distance classification
Mustansiriyah Journal for Sciences and Education, 2017
The demand increased last decades to modify optical photography systems and increase its quality ... more The demand increased last decades to modify optical photography systems and increase its quality to classify and analyze movement in a video clip. This is very important in many applications like vision computing system (Robots). The process of detection movement of a target is not easy process because it is controlled by many physical parameters like motion, image quality and filming environment. Moreover, it dose effect by the real 3D scene projection on 2D image. This work focused to study, analyze and classify images of moving targets for different distances (D) between camera and target in the video scene with constant background. Where many statistics properties are calculated and studied like object area (A (i)), object centre (C x , C y) and find its function with distance (D). The distance between the target and the camera is estimated accurately depending on target's area (A) as a function of distance. It is found that there is a good match between the real and the estimated distance depending on mean square difference (MSD=0-160.7 x 10-3).
Neuroquantology, 2020
For this study, two equations are used to predict the length of the shadow. The first model estim... more For this study, two equations are used to predict the length of the shadow. The first model estimates the shadow lengths for sticks with length 10, 20, 30, 40, and 50 cm per day for September. The second model estimates the length of the shadow for any September day with a length stick of 50 cm. Those models formed the shadow's behavior depending on a stick's length and index day in September. The suggested system used to track the shadow path at north of Baghdad, Iraq from 7 a.m. to 5 p.m. on September 1st, 21st, and 30th, 2019. Depending on the Adj-R Square criteria, the result from the two models shows a good match with the (real) measured data.
Enhance Video Film using Retnix method
Journal of Physics: Conference Series, 2018
An enhancement technique used to improve the studied video quality. Algorithms like mean and stan... more An enhancement technique used to improve the studied video quality. Algorithms like mean and standard deviation are used as a criterion within this paper, and it applied for each video clip that divided into 80 images. The studied filming environment has different light intensity (315, 566, and 644Lux). This different environment gives similar reality to the outdoor filming. The outputs of the suggested algorithm are compared with the results before applying it. This method is applied into two ways: first, it is applied for the full video clip to get the enhanced film; second, it is applied for every individual image to get the enhanced image then compiler them to get the enhanced film. This paper shows that the enhancement technique gives good quality video film depending on a statistical method, and it is recommended to use it in different application.
Motion detection typically is the case for applications using a fixed camera such as video survei... more Motion detection typically is the case for applications using a fixed camera such as video surveillance applications or traffic monitoring applications. This research directed to detect a movement within a single scene and build a new background based on the correlation method. The recorded footages scenes (vehicle and human) were outdoor at different day times using a fixed camera. The suggested algorithms proved it is effective to extract and detect a moving object within video frames. Moreover, the suggested algorithms show stability at different environments like shadow, sun light angle and daytime. The proposed study gives less error ratio depending on mean square different and builds a background using 8 frames only comparing with other studies.
NeuroQuantology, 2020
Systematic fact gaps on retrieved imagery were imposed by failure of the (SLC) on ETM+ leading to... more Systematic fact gaps on retrieved imagery were imposed by failure of the (SLC) on ETM+ leading to elimination of potential to provide spatially continuous fields. While a number of algorithms were developed for filling these gaps, the majority of the suggested algorithms can only be applied on fairly homogeneous areas. The retrieving band aspect and element may be challenging if they are utilized to heterogeneous landscapes. In this study, we adopted the criterion of correlation between satellite images to determine spatially match between images. Three different multi temporal images were used in filling the gaps in a period not exceeding 48 days, and two algorithms are presented. In the first algorithm, we got one image free of gaps, when using three images of different times, for a period not exceeding 48 days, while in the second algorithm, we got images free of gaps within a period of time not exceeding 16 days depending on the images resulting from the first algorithm. Simulated and true SLC-off ETM+ bands have been used to examine the performance of the proposed method via comparing with the original data so as to examine the resulting bands from the first and the second algorithms which are based on the correlation model. The statistical reviews indicate that in the proposed methods we can get better values of un-scanned pixels accurately, specifically in target images (vegetation, soil and water).
Indonesian Journal of Electrical Engineering and Computer Science, 2019
The task of recognizing the shape of Arabic letters using modified algorithms discussed in this p... more The task of recognizing the shape of Arabic letters using modified algorithms discussed in this paper. The difficulty of recognizing these letters is summarized in the shape of the Arabic letter within a word from a large set of letters has a similar shape. Moreover, the shape of the letter is different depending on its position begin, middle, end within a word. Therefore, it is necessary to introduce new geometric features to categorize each letter. The suggested algorithm with 19 features is used in this paper. These features, like define points for each letter, divide a letter to blocks, edge detection and other features are shown in the suggested algorithm. The introduced geometric features give a high accuracy to recognize printed Arabic letter within a word or text. Minimum distance criteria used to estimate the error of the recognition process between the database and the tested Arabic letter. This method is good to explain the behaviour of the designed algorithm code to dist...
Uploads
Papers by Anwar H. Al-Saleh