MATLAB Image Processing Research Articles

Lack of fusion mitigation in directed energy deposition with laser (DED-L) additive manufacturing through laser remelting

The void level of a component produced by additive manufacturing can be used to predict the mechanical properties and in most cases it is important to develop processing methodologies able to minimize it. Conventional techniques include parameter optimization and the hot isostatic pressing (HIP). However, in the former there is a limit where improvement becomes minimal and the latter, although it is effective for internal voids, is not efficient in the case of voids located near the surface, which are considered critical. This paper describes a study in which laser remelting was used as an alternative to achieve higher densification after processing using directed energy deposition with laser (DED-L). This technique has been investigated for powder bed (PB) processes, but has not been explored for DED. Understanding the behavior of different materials considering the same processing parameters is also relevant and has not been previously addressed. An ytterbium (Yb) fiber laser with a maximum nominal power of 10 kW and wavelength of 1070 nm was used. Iron and Inconel 625 powders were deposited on an SAE 1010 steel substrate to form beads with intentional voids. The DED-L was performed with a power of 450 W, scanning speed of 600 mm/min and powder feed rate of 10 g/min. The laser radiation was applied over the produced surface at three energy levels: 31.5 kJ/m, 38.2 kJ/m and 45 kJ/m. An in-house MATLAB image processing code was developed in order to assess the void percentage. The results indicated that most of the voids originating from the DED-L process were due to lack of fusion between beads and between the deposit and the substrate. For iron, the void percentage after DED-L varied between 5.3% and 7.1%. After remelting, this value reduced to 1.7% applying 45 kJ/m. It was also noted that in all samples the voids that were initially connected to the surface coalesced because of material redistribution. However, a low repeatability was observed. For Inconel, the void percentage after DED-L varied between 4.4% and 7.1%, and reduced to 3.7% applying 31.5 kJ/m. This reduction is not as significant as that observed for iron and also the degree of dispersion was lower for iron. Hence, laser remelting is able to mitigate voids resultant from DED-L and, consequently, achieve better quality due to a lower probability of component failure. Simultaneously, productivity can be enhanced since the equipment required is the same as that used for the deposition. However, new strategies are needed to increase the process robustness and reduce the degree of dispersion.

Fuzzy logic classification of mature tomatoes based on physical properties fusion

Grading of fruits and vegetables is an initial step after harvesting. It is also an essential operation before packaging. In the present study, different fuzzy algorithms for classification of mature tomato were applied and evaluated based on combinations of fruit color, size and hardness. Fuzzy membership functions of hardness were established by subjecting samples to Instron compression test as well as the rates of panelists. Each sample was also used for image processing to determine the color and size of fruit using Matlab image processing toolbox. Color and size fuzzy membership functions were established by published standard. The fuzzy If-Then rules were applied to classify the samples within five group outputs viz. “grade I”, “grade II”, “grade I-far market”, “processing”, and “storage”. Eighty-one fuzzy rules were reduced to 25 rules by combining the compatible rules. Six fuzzy algorithms with different fuzzifiers (zmf, sigmf, gbellmf) and defuzzifiers (bisector, mom, and centroid) were applied, and the outputs were compared to the panelists’ classifications in cross tables. According to the classification results, fuzzy algorithms grouped the fruits into correct classes with 90.9%, 92.3%, 88.7%, 87.4%, 92.4% and 93.3% accuracy for 6 models, respectively. The best result was observed with zmf and sigmf, and gbellmf as fuzzifier and mom as defuzzifier with 93.3% accuracy. Overly, the results revealed that the fusion of aforementioned tomato properties based on fuzzy membership functions could accurately classify the tomatoes in correct groups for different markets.

Improving the reconstruction of dental occlusion using a reconstructed-based identical matrix point technique

Digital dental models are widely used compared to dental impressions or plaster-dental models for occlusal analysis as well as fabrication of prosthodontic and orthodontic appliances. The digital dental model has been considered as one of the significant measures for the analysis of dental occlusion. However, the process requires more computation time with less accuracy during the re-establishment of dental occlusion. In this research, a modern method to re-establish dental occlusion has been designed using a Reconstructed-based Identical Matrix Point (RIMP) technique. The curvature of the dental regions has been reconstructed using distance mapping in order to minimize the computation time, and an iterative point matching approach is used for accurate re-establishment. Satisfactory restoration and occlusion tests have been analyzed using a dental experimental setup with high-quality digital camera images. Further, the high-quality camera images are converted to grayscale images for mathematical computation using MATLAB image processing toolbox. Besides, 70 images have been taken into consideration in which 30 planar view images has been utilized for experimental analysis. Indeed, based on the outcomes, the proposed RIMP outperforms overall accuracy of (91.50%) and efficiency of (87.50%) in comparison with conventional methods such as GLCM, PCR, Fuzzy C Means, OPOS, and OGS.

Algorithm mediated early detection of oral cancer from image analysis

To develop Automatic Oral Cancer Detection algorithm for identification and differentiation of premalignant lesions from buccal cavity images for early detection of oral cancer, which may reduce related fatalities in developing countries. The oral cavity images of normal, erythroplakia, and leukoplakia (20 images of each) were collected and processed using MATLAB image processing tools. First, maximum red value was used to differentiate between normal and abnormal. Second, mean red value was used for the selection of a processing path through YCbCr. Third, gray-level co-occurrence matrix (GLCM) based features were used to make final decisions. Images have been randomly divided and shuffled between training and test set to rigorously train the algorithm. With 100% efficiency, normal images were separated from abnormal images in the first step by applying R value distribution with a cutoff R value, 11,900. Further, images with a mean R value >200 and <200 were processed by segmentation of Y plane and Cr plane, respectively. For the final decision, abnormal images were analyzed through the GLCM using the entropy feature as one of the key indicators, which can apply to the differentiation decision with 89% efficiency. The developed algorithm can successfully differentiate premalignant lesions from normal. A graphic user interface was developed, which displays outcomes with reasonable accuracy.

MATLAB Image Processing Method using Histograms for Railway Track Crack Fault Detection

A software technique (i.e. image processing in MATLAB) has been explored in this project, which will aid in accurately detecting track cracks with minimal human interference. There will be a system in place to capture photographs of the track and send them to the server. i.e. to the rail employee's machine. The employee only needs to scan that picture. However, no special efforts are needed to detect cracks which will certainly benefit the employees of the railway. In addition, with less maintenance, the project's total cost is lower.

Automatic Attendance Recording System Using Facial Recognition

The student attendance is collected either manually or digitally through an RFID card. Recently, some of the institutions adopted the use of dynamic QR codes for attendance monitoring. However, these systems are challenging to maintain and time-consuming. The student can easily manipulate signatures for attendance monitoring. Moreover, the QR code system requires the application on both the lecturer and student sides. The lecturer needs to set up the QR code while using the mobile app to use the system. Therefore, it is time-consuming and sacrifices several minutes at the beginning of each class. The student also sometimes has difficulty in using the app leading to manual data insertion. Therefore, this project aims to solve this issue by using the facial recognition system on a lecturer’s laptop to collect the attendances. This project requires the use of a webcam and MATLAB to perform facial image recognition. This work utilizes face detection algorithm in the MATLAB image processing toolbox to build a system that will detect and recognize the frontal faces of students in a classroom. Firstly, several images of students will be recorded in a database. Then, a GUI-based application automatically identifies a face and matches it with the database created. Lecturers will use the GUI on their laptops, and students will show their faces to the web camera for their attendance to be taken. The system was tested successfully where student face was successfully recognized and recorded in the attendance monitoring system. Only registered user faces will be detected.

Identifying airport runway pavement diseases using complex signal analysis in GPR post-processing

Non-destructive detection of pavement diseases on airport runways is of great importance for airport maintenance and ensuring the normal use of airport runways. In this study, a full coverage scan of an airport pavement was conducted using the MALA three-dimensional ground penetrating radar (GPR). Based on complex signal analysis technology, the Hilbert transform were used to comprehensively interpret the anomalous features of the scanned images at specific disease location. The theoretical void volume of pavement diseases was calculated using MATLAB image processing and Origin software. The analysis showed that the main airport pavement diseases were loose layers and small holes, which were more comprehensively revealed by three-dimensional radar images. The three instantaneous parameter spectrums were used to verify and optimize the initial results obtained with the Reflexw post-processing software. The theoretical void volume was calculated using the pixel equivalent method. The void value of typical diseases was 49.38 m3, which was approximately 2.97 times of the calculated value with the rSlicer post-processing technique. This proposed technique can provide a reference for the exact recognition of disease types and the corresponding calculation of grouting reinforcements while overcoming the shortcomings of the single parameter method with multi-parameter analysis.

Development and Validation of an Online Analyzer for Particle Size Distribution in Conveyor Belts

Online measurement of particle size distribution in the crushing process is critical to reduce particle obstruction and to reduce energy consumption. Nevertheless, commercial systems to determine size distribution do not accurately identify large particles (20–250 mm), leading to particle obstruction, increasing energy consumption, and reducing equipment availability. To solve this problem, an online sensor prototype was designed, implemented, and validated in a copper ore plant. The sensor is based on 2D images and specific detection algorithms. The system consists of a camera (1024 p) mounted on the conveyor belt and image processing software, which improves the detection of large particle edges. The algorithms determine the geometry of each particle, from a sequence of digital photographs. For the development of the software, noise reduction algorithms were evaluated and selected, and a routine was designed to incorporate morphological mathematics (erosion, dilation, opening, lock) and segmentation algorithms (Roberts, Prewitt, Sobel, Laplacian–Gaussian, Canny, watershed, geodesic transform). The software was implemented (in MatLab Image Processing Toolbox) based on the 3D equivalent diameter (using major and minor axes, assuming an oblate spheroid). The size distribution adjusted to the Rosin Rammler function in the major axis. To test the sensor capabilities, laboratory images were used, where the results show a precision of 5% in Rosin Rambler model fitting. To validate the large particle detection algorithms, a pilot test was implemented in a large mining company in Chile. The accuracy of large particle detection was 60% to 67% depending on the crushing stage. In conclusion, it is shown that the prototype and software allow online measurement of large particle sizes, which provides useful information for screening equipment maintenance and control of crushers’ open size setting, reducing the obstruction risk and increasing operational availability.

APPLICATION OF ZONAL AND CURVATURE FEATURES TO NUMERALS RECOGNITION

Purpose of the study: The purpose of this work is to present an offline Optical Character Recognition system to recognise handwritten English numerals to help automation of document reading. It helps to avoid tedious and time-consuming manual typing to key in important information in a computer system to preserve it for a longer time.&#x0D; Methodology: This work applies Curvature Features of English numeral images by encoding them in terms of distance and slope. The finer local details of images have been extracted by using Zonal features. The feature vectors obtained from the combination of these features have been fed to the KNN classifier. The whole work has been executed using the MatLab Image Processing toolbox.&#x0D; Main Findings: The system produces an average recognition rate of 96.67% with K=1 whereas, with K=3, the rate increased to 97% with corresponding errors of 3.33% and 3% respectively. Out of all the ten numerals, some numerals like ‘3’ and ‘8’ have shown respectively lower recognition rates. It is because of the similarity between their structures.&#x0D; Applications of this study: The proposed work is related to the recognition of English numerals. The model can be used widely for recognition of any pattern like signature verification, face recognition, character or word recognition in another language under Natural Language Processing, etc.&#x0D; Novelty/Originality of this study: The novelty of the work lies in the process of feature extraction. Curves present in the structure of a numeral sample have been encoded based on distance and slope thereby presenting Distance features and Slope features. Vertical Delta Distance Coding (VDDC) and Horizontal Delta Distance Coding (HDDC) encode a curve from vertical and horizontal directions to reveal concavity and convexity from different angles.

Quantification method of suspended solids in micromodel using image analysis

Micromodel can provide valuable information to improve understanding of pore-scale transport phenomenon and can also be utilized to simulate the transport process at pore scale. This research aims to propose settlement option for quantification of suspended solids in micromodel. The micromodel is used to mimic the formation damage which occurs in reservoir formation that could simultaneously affect enhanced oil recovery. This is done by utilizing visual image interpretation through image analysis on micromodel chip. Following the quantification of suspended solids, the micromodel was injected with brine that eventually forms agglomeration. Images are taken from NIS-Element AR microscope automatically in RGB color profile and then made into grayscale and finally into binary modes. Since the micromodel is simulated in 2D form structure, the quantification method complemented with image analysis is focusing on the quantified area, µm2 region of interest categorized into 3 main groups of area B05, M45 and T50, respectively. This research will explore on segmentation and thresholding processes of the visual data acquired from micromodel experiment. An image-based computational algorithm is programmed in MATLAB Image Processing Toolbox and ImageJ; hence, suspended solids in porous media could be quantified from the visual image executed in micromodel.

Enhance the LZW Compression Ratio Through the Use of Image Preprocessing Techniques for Gray Scale Images

Compression ratios of encoding algorithms degrade due to signal distortion, additive noise, and hacker manipulation. Large file size costs too much disk space, difficult to analyze, and high bandwidth to transmit over the internet. In this case, compression is mandatory. LZW is a general dictionary-based lossless compression algorithm. It is fast, simple, and efficient when it includes lots of repetitive data or monochrome images. Images with little data repetition and too much-blurred signal, the compression ratio of the LZW algorithm downgraded. Besides this, the execution time of the LZW compression algorithm increases dramatically. To preprocess and analyze the image information the researcher uses LZW encoding algorithm, bit plane slicing technique, Adaptive Median Filter, and MATLAB image processing toolbox. The MATLAB public grayscale image, salt &amp; pepper, Gaussian locavore blurred, and Bayern pattern image data sets are used. Those images dataset is used to test the normal LZW encoding algorithm and the proposed encoding algorithm compression ratio step by step. The noised dataset, the filtered datasets, and bit plane dataset images are processed and recorded quality and compression ratio parameters. The enhanced encoding algorithm average compression ratio is better by far from the normal LZW encoding algorithm by 160%. Not only has the compression ratio, but demising also improved the algorithms execution time. And the image quality metrics measurement of mean square error, peak signal to noise ratio, and structural similarity index measurement are 0, 99, and 1 respectively. This implies the enhanced encoding algorithm could decompress fully without scarifying image quality. The LZW encoding algorithm developmental environment specifies to select tiff and gif image formats. In addition, the LZW encoding algorithm functions are not available in the MATLAB image processing toolbox. The researcher challenged to write a MATLAB script for each personal function. Still, there is room to extend the compression ratio of the LZW encoding algorithm using the image masking technique.

Surface Roughness Analysis of 3D Printed Microchannels and Processing Characteristics of Abrasive Flow Finishing

Because of the low surface roughness of three-dimensional (3D) printed microchannels, in some environments, the use requirements cannot be met, and, at the same time, they are difficult to process. Therefore, a surface roughness analysis of 3D printed microchannels and post-processing using abrasive flow technology are proposed. The value of the inner surface roughness of the straight pipe part was calculated by using the least-squares method combined with the definite integral. Using the equal area principle, MATLAB curve fitting was used to numerically calculate the semicircular pipe section, and the relationship between the value of surface roughness and the bending radius of the scanning layer thickness is given. Use MATLAB image processing technology to study the processing area. The roughness of the inner wall of the pipeline was analyzed by laser confocal, stereo, and scanning electron microscopes. The results show that the roughness of the inner surface of the pipe increases with an increase in the thickness of the sweeping layer, an increase in the inclination angle, and a decrease in the radius of curvature. In the case of abrasive flow processing, the longer the processing time, the greater the grinding amount and the greater the amount of grinding outside the pipe wall in each one-way machining; further, the processing has obvious directionality.

Low velocity impact and compression after impact behaviour of polyester pin-reinforced foam filled honeycomb sandwich panels

Hybridization of sandwich panels and their different components have drawn huge attention due to the significant improvement in their attributes. Hybrid core of ‘Polyester Pin-reinforced Foam filled Honeycomb Sandwich panels’ (PFHS) were fabricated and compared with unreinforced ‘Foam filled Honeycomb Sandwich panels’ (FHS) in terms of low velocity impact and Compression After Impact (CAI) performance. The impact damage area was calculated by employing MATLAB image processing technique. Incorporating through thickness pins for connecting faces and core is an effectual way to improve interfacial bonding, specific bending stiffness and also imparts out of plane properties for sandwich panels. The low velocity impact tests performed on the sandwich panels revealed that the polyester pin reinforcement in foam filled honeycomb sandwich panel improved the load bearing capacity, total absorbed energy and reduced the impact damage area significantly. In CAI test, debond, wrinkling of face sheet, and buckling of face sheet and core are the major modes of failure. The addition of the pins enhanced the compressive strength for all the impact energy levels.

Measurement of the five morphological indexes of follicles using image processing toolbox

This study aims to investigate the morphological characteristics of mature follicles with clinical value. The five morphological indexes of follicles in 72 natural ovulation cycles were measured. The shoot time of follicle photos was the day before ovulation. Measurement software was the MATLAB Image Processing Toolbox. The measured average area, perimeter, equivalent circle diameter, and roundness were 301.29 ± 8.52 mm2, 62.23 ± 6.82 mm, 20.21 ± 3.08 mm, and 0.89 ± 0.05, respectively; and the maximal diameter was 23.12 ± 3.06 mm. Image Processing Toolbox is a simple and convenient measurement software. The standardization of the reference indexes of follicular morphology has important clinical application value in reproductive medicine.

Determination of tyre-ground interaction parameters through image processing in Matlab

Determination of tyre-ground interaction parameters through image processing in Matlab

Determination of tyre-ground interaction parameters through image processing in Matlab

Determination of tyre-ground interaction parameters through image processing in Matlab

Development of an Automated Multidirectional Pest Sampling Detection System Using Motorized Sticky Traps

Insect detection and counting constitute a considerable challenge in the field of agriculture. However, among various biotic issues of agricultural production, pest infestation is a major challenge, with the humid environment surrounding the crops encouraging the survival and proliferation of pests. In addition, electronic traps need protection, especially from rain. This study describes the design and development of a prototype for an automatic pest sampling and detection system for agricultural crops. To the best of our knowledge, the proposed system is the first motorized automatic trap developed to handle monitoring operations in two directions of precise movement (i.e., clockwise and counterclockwise) and cover four directions of insect sampling that provides additional details of insect infestation direction. A square-shaped sticky box was designed, and an optical sensor was attached to a scalable arm. The movements of the sticky box and the camera arm were generated by motors. Preprocessing was conducted by using morphological operations, whereas insect detection and counting were implemented by an algorithm of connected components labeling that applied by using MATLAB image processing toolbox. Different kernel functions, such as disk, diamond, square, and sphere, were used as matching functions for the insect detection and counting algorithm. The average accuracy of the highest sphere kernel was 85.2%. Test results of the hardware show the reliability, flexibility, and system protection of the automatic system to provide accurate movements in two degrees of freedom.

Design and Implementation of Humanoid Robotic Arm

Robotics has been acknowledged process of main stream in the industrial automation domain for decades. It is gradually making its headway into the domain of military, medical and vehicle application domain. But only problem we might face is in controlling, the aim of this project is to enhance the interactivity. In Activities we have shown all the activities going around in the places where the basic activities are eating and cooking. In Environment we have shown the surroundings or environment where the activities are taking place. In Interaction we have shown the interaction between the person/object by which the activities are done. In Object section we have put the objects/tools connected to activities. In User we have shown the user that are involved in the activities in the given environment. For a controlling robotic arm in open source by adding a virtual world input by enabling the user to interact with the real world and making the entire process Eco friendly. Besides the research, humanoid robots are being developed to perform human tasks like personal assistance, through which they should be able to assist the sick and elderly, and dirty or dangerous jobs. Humanoids are also suitable for some procedurally-based vocations, such as reception-desk administrators and automotive manufacturing line workers. In essence, since they can use tools and operate equipment and vehicles designed for the human form, humanoids could theoretically perform any task a human being can, so long as they have the proper software. Ultrasonic actuators are designed to produce movements in a micrometer order at ultrasonic frequencies (over 20 kHz). They are useful for controlling vibration, positioning applications and quick switching. However, the complexity of doing so is immense.In our project we are designing humanoid robot. Which are activated through gesture. For gesture recognized we use MATLAB image processing technique. For wireless data transmission we use cc2500RF module as well as Bluetooth module. Here servo motor is used for arm controlling. DC motor used for platform movement. All this hardware control by ATmega328 microcontroller.

Visualization of Arc Energy Distribution Based on CCD Image Sensor

With the advancement of computer and sensor technology, visualization research has been more and more widely used in the industrial field, especially for arc plasma research of high energy fields. During the electrical breaking process, the DC arc energy distribution directly affects the working performance of the switchgear. A single voltage and current monitoring method is difficult to characterize the complex energy evolution process of the arc. Therefore, the visualization of the arc energy distribution is particularly important. In this paper, the arc energy distribution of the arc combustion process is visualized as the main research content. The arc characteristic detection platform is built, and the voltage, current, contact displacement value and arc image between the contacts are synchronously collected. According to the spectral characteristics of the color CCD image sensor, the colorimetric temperature measurement formula with calibration coefficient is derived to establish the relationship between the pixel and the arc temperature. The acquired arc image is processed by matlab image processing technology to visualize the two-dimensional energy distribution characteristics of the arc in the horizontal projection direction during the breaking process.

Identification of impurity in wheat mass based on video processing using artificial neural network and PSO algorithm

The presence of weed seeds and other impurities in the wheat grains affect the identification quality of the wheat grains. This study explores the possibility of identifying the wheat in the wheat grain mass and estimates the amount of impurities in the wheat mass based on the video processing combined with the artificial neural network (ANN) integrated by particle swarm optimization (PSO) algorithm. After pre-processing the video of the mass movement on the conveyor belt, 35 shapes, color, and textural features were extracted from each grain sample in the image in the presence of the MATLAB software and image processing (IP) toolbox. The data obtained from the IP section were categorized into two approaches. The first one, purposes the identification of the wheat grains in the grain mass, and the other one, identifies each components in the wheat mass. Both of them employs the hybrid ANN-PSO algorithm to achieve the highest classification accuracy and the lowest error value. According to the results, ANN with the architecture of 36-10-10-5 and ANN with the architecture of 36-8-8-5 overtakes the other architectures with the highest accuracy and performance values for training (100 and 100%) and testing phases (100 and 86.66%), respectively for the first and second approaches. Accordingly, based on the results of the hybrid ANN-PSO algorithm, the highest classification accuracy was 98.62% and 97.77% (for training and testing phases, respectively) and 76.08% and 73.1% (for training and testing phases, respectively) related to the first and the second approaches, respectively. Finally, the video processing using ANN can be considered as a powerful approach for identifying the impurities in the wheat grain mass. Practical applications One of the major problems in wheat and similar mass products is the presence of impurities inside the total mass, which drastically reduces the quality and the marketability of the product. Conventional methods of detecting the amount of impurities in the grain mass are always accompanied by difficulties such as lack of precision, time consuming, and tedious. The use of new technologies such as machine vision and artificial intelligence have been considered as the important tools in this regard. One of the practical applications of this study is to detect the amount of impurities in wheat grain mass at the inlet of silos and in pricing on grain masses. The system proposed in this study can accurately detect and report impurities in wheat grain mass.