Image Processing Toolbox Research Articles

Unsupervised Learning Based on Multiple Descriptors for WSIs Diagnosis.

An automatic pathological diagnosis is a challenging task because histopathological images with different cellular heterogeneity representations are sometimes limited. To overcome this, we investigated how the holistic and local appearance features with limited information can be fused to enhance the analysis performance. We propose an unsupervised deep learning model for whole-slide image diagnosis, which uses stacked autoencoders simultaneously feeding multiple-image descriptors such as the histogram of oriented gradients and local binary patterns along with the original image to fuse the heterogeneous features. The pre-trained latent vectors are extracted from each autoencoder, and these fused feature representations are utilized for classification. We observed that training with additional descriptors helps the model to overcome the limitations of multiple variants and the intricate cellular structure of histopathology data by various experiments. Our model outperforms existing state-of-the-art approaches by achieving the highest accuracies of 87.2 for ICIAR2018, 94.6 for Dartmouth, and other significant metrics for public benchmark datasets. Our model does not rely on a specific set of pre-trained features based on classifiers to achieve high performance. Unsupervised spaces are learned from the number of independent multiple descriptors and can be used with different variants of classifiers to classify cancer diseases from whole-slide images. Furthermore, we found that the proposed model classifies the types of breast and lung cancer similar to the viewpoint of pathologists by visualization. We also designed our whole-slide image processing toolbox to extract and process the patches from whole-slide images.

ENHANCING THE SECURITY AND INTEGRITY OF MEDICAL INFORMATION THROUGH WATER MARKING

Ongoing headways in another period of e- wellbeing and telemedicine advancements present more current open doors for sharing clinical information when an open correspondence station is utilized. Notwithstanding, this trade is confronting basic difficulties of copyright insurance, content validation, and respectability check. Hence, because of the popularity for safe control of patient's clinical data, computerized watermarking is expected, as a worth added instrument, for secure clinical information the executives. In this review, another reversible watermarking method for the security of clinical recordings is proposed. The patient personality is inserted, as a watermark, into the host clinical recordings. A calculation is embraced for choosing the ideal casings in every video shot. This approach incorporates the utilization of polynomial change strategies, to recognize the best watermark implanting regions in the ideal casings. Exploratory outcomes exhibit high subtlety of the watermark and solid vigor against various assaults. Thus, our calculation approves the safety efforts that guarantee a successful control of clinical recordings. Software Tools: Image processing Toolbox of MATLAB version 2016a Key Words: Watermarking, Biomedical imaging, Discrete wavelet transform,,PSNR

Recognition of human Iris for biometric identification using Daugman’s method

Iris identification is a well-known technology used to detect striking biometric identification procedures for recognizing human beings based on physical behaviour. The texture of the iris is unique and its anatomy varies from individual to individual. As we know, the physical features of human beings are unique, and they never change; this has led to a significant development in the field of iris recognition. Iris recognition tends to be a reliable domain of technology as it inherits the random variation of the data. In the proposed study of approach, we have designed and implemented a framework using various subsystems, where each phase relates to the other iris recognition system, and these stages are discussed as segmentation, normalisation, and feature encoding. The study is implemented using MATLAB where the results are outcast using the rapid application development (RAD) approach. We have applied the RAD domain, as it has an excellent computing power to generate expeditious results using complex coding, image processing toolbox, and high-level programing methodology. Further, the performance of the technology is tested on two informational groups of eye images MMU Iris database, CASIA V1, CASIA V2, MICHE I, MICHE II iris database, and images captured by iPhone camera and Android phone. The emphasis on the current study of approach is to apply the proposed algorithm to achieve high performance with less ideal conditions.

Surface Analysis in Additive Manufacturing Using Image Processing

Fused Deposition Modeling (FDM) is a type of additive manufacturing process where prototypes are developed by depositing layers on previously deposited layer of material. Surface roughness is an important factor in determining quality of produced parts. This work proposes a methodology to calculate the surface roughness of part manufactured using FDM process. The surface roughness values to be measured using conventional stylus instrument and Digital image processing technique. Stylus comes in direct contact with surface so it destroys the surface topography. Image processing is a non-contact method hence it overcomes this problem. A camera and directional lightings will be used to capture images of surface of specimens. These images will be analyzed and processed using various image processing techniques available in MATLAB image processing toolbox. Experimental results will be validated by comparing the results obtained by using image processing technique with conventional stylus system. The system is also proposed to inspect surface irregularities. Key Words: Surface roughness, image processing, MATLAB, FDM.

Application of a compressed air jet for cleaning of wheel surface in grinding nickel-based super alloy Inconel 718

Grinding plays an important role in the production of fine finishing surfaces. However, generation of substantial amount of energy through rubbing, plowing and cutting actions in the grinding zone would result in the creation of micro cracks, surface damage, subsurface damage, surface burning as well as residual stress on the ground surface. Nickel-based super alloy Inconel 718 is widely utilized for the fabrication of workpiece, especially in aerospace industry and gas turbines according to their excellent oxidation resistance, fatigue resistance, thermal stability and superior corrosion. However, difficult-to-grind feature and tendency to adhere the wheel pores are considered as the main difficulties encountered in the production of workpiece with this material. Regarding the tendency to clog on the pores of wheel surface, the wheel would be dulled easily and immediately after shorter period of time. To avoid this problem as well as removing chips from the grinding zone and reducing the loading of the wheel, it is proposed to employ a compressed air jet nozzle under the incident angle of 30˚. The various parameters of surface roughness, tangential force, normal force, specific force, surface topography using Scanning Electron Microscopy (SEM) and profilometer, besides the evaluation of wheel loading using image processing toolbox by MATLAB are considered in this investigation. The obtained results reveal the best output parameters with the use of conventional cutting fluids along with a compressed air jet.

Simplified, open‐source analysis of DNA‐binding proteins

The structure, regulation, and maintenance of DNA is critical to cellular function. Errors in these underlying mechanisms play a major role in diseases such as cancer. As a result, insights into the molecular details are needed to further our understanding, improve biological models, and develop novel therapeutics. Single‐molecule techniques have emerged as useful tools for uncovering the activity and function of DNA‐binding proteins in real time. Furthermore, the data from single‐molecule techniques allows for an accurate quantification of many molecular properties, such as binding location, kinetics, etc. For many researchers, however, developing an analysis pipeline to quantify single‐molecule data is challenging due to the required time, resources, and expertise. To address these obstacles, we developed an automated, open‐source image processing and data quantification toolbox. We show that our toolbox allows for easy, rapid, and intuitive processing of single‐molecule data. Using systems like the gene editing CRISPR/Cas9 system, we demonstrate that our toolbox 1) reports DNA binding specificity at the base‐pair level, 2) measures binding constants (kon/koff) from the direct visualization of individual complexes interacting with DNA, and 3) allows for the accurate quantification of enzymatic processivity and protein diffusion. Overall, we show that our simplified, open‐source data analysis platform allows for automated processing of single‐molecule data and rapid characterization of virtually any DNA‐binding protein or polymerase. This toolbox is accessible to all researchers and will enhance efforts to understand a wide range of normal and pathological DNA processes.

Assessing the Homogeneity of Forage Mixtures Using an RGB Camera as Exemplified by Cattle Rations

The article examines existing methods for assessing the homogeneity of feed mixes in the feed industry and agriculture. As an alternative to existing approaches, the authors offer a low-cost online technology to assess the homogeneity of feed. The feedstuff under study includes feed mixes for cattle or compound feed consisting of naturally-grown feed (green mass of freshly cut grass, haylage, corn silage, etc.) and concentrated components (grain milling, sunflower, and soybean meal). The proposed method based on an RGB camera, a diode lamp, filters, and software is approved by a preliminary study of the physical properties of feed mix components by Specim IQ hyperspectral camera and revealing characteristics of light absorption of each type of components (concentrated/natural origin). The article presents a method of processing a feed mix image fixed by an RGB camera through light filters using Matlab Image Processing Toolbox tools, namely, a Color Thresholder app and Image Region Analyzer app.

Computing Color Transforms with Applications to Image Editing

This paper deals with the implementation of various MATLAB functions present in image processing toolbox of MATLAB and using the same to create a basic image processor having different features like, viewing the red, green and blue components of a color image separately, color detection and various other features (noise addition and removal, edge detection, cropping, resizing, rotation, histogram adjust, brightness control, etc.) that is used in a basic image editor along with object detection and tracking.

The characteristics of alkali-activated slag mortar containing multi-walled carbon nanotubes at elevated temperature

The effect of the addition of different concentrations (0, 0.05, 0.10 and 0.15 wt%) of multi-walled carbon nanotubes (MWCNTs) on the mechanical properties and microstructure of alkali-activated slag (AAS) mortars at temperatures of 23, 200, 400, 600 and 800°C was investigated. To investigate the strength parameters of the specimens, the mechanical strength and mass loss of the specimens at ambient temperatures and after exposure to elevated temperatures were determined. Petrographic image analysis was also conducted to analyse the microstructures of the specimens. The Matlab image processing toolbox was used to calculate the pore area of the samples at room temperature. The results showed that the addition of MWCNTs improved the mechanical properties of the AAS mortars at both ambient and elevated temperatures: the compressive and flexural strengths of the mortars were improved by up to 69% and 85%, respectively. At 400°C, the compressive strength increase of the specimens compensated for the deterioration rate of about 3% mass loss. This temperature should be considered the maximum tolerable degree for AAS mortars.

Flow visualization by Matlab® based image analysis of high-speed polymer melt extrusion film casting process for determining necking defect and quantifying surface velocity profiles

Abstract The primary objective of this research paper is to detect and quantify the necking defect and surface velocity profiles in high-speed polymer melt extrusion film casting (EFC) process using Matlab® based image processing techniques. Extrusion film casting is an industrially important manufacturing process and is used on an industrial scale to produce thousands of kilograms of polymer films/sheets and coated products. In this research, the necking defect in an EFC process has been studied experimentally and the effects of macromolecular architecture such as long chain branching (LCB) on the extent of necking have been determined using image processing methodology. The methodology is based on the analysis of a sequence of image frames taken with the help of a commercial CCD camera over a specific target area of the EFC process. The image sequence is then analyzed using Matlab® based image processing toolbox wherein a customized algorithm is written and executed to determine the edges of the extruded molten polymeric film to quantify the necking defect. Alongwith the necking defect, particle tracking velocimetry (PTV) technique is also used in conjunction with the Matlab® software to determine the centerline and transverse velocity profiles in the extruded molten film. It is concluded from this study that image processing techniques provide valuable insights into quantifying both the necking defect and the associated velocity profiles in the molten extruded film.

MatGel: A MATLAB program for quantitative analysis of 2D polyacrylamide electrophoresis (2D-PAGE) protein gel images

Two-dimensional polyacrylamide gel electrophoresis (2D-PAGE) is widely used in proteomics studies. Hundreds of proteins extracted from a biological sample can be separated and visualized on a 2D-PAGE gel. The interpretation of protein expression levels relies on the comparison of areas and intensities of the corresponding protein spots in 2D-PAGE gel images. However, determination of protein spot areas by the manual selection method is time-consuming and error-prone. The purpose of this research is to develop a highly automated program for the simultaneous detection and quantification of protein spots across a large number of 2D-PAGE protein gel images by using MATLAB image processing toolbox. This program will enhance the potential of using 2D-PAGE technique as a high throughput quantitative protein expression study tool. We developed MatGel, a simple and efficient program for protein spot area detection and intensity quantification from 2D-PAGE protein gel images. MatGel can detect and output the areas and mean intensities of corresponding protein spots across a large number of 2D-PAGE gel images simultaneously. Users also have options to adjust preferences at each step of image analysis. Basic knowledge with MATLAB programming language is required to run the program.•We developed MATLAB program MatGel to automate the determination of protein spots on 2D-PAGE protein gel images.•MatGel can analyze a large number of 2D-PAGE gel images simultaneously to minimize human errors.•MatGel is flexible and easy to use.

Performance Evaluation of Digital Image Processing by Using Scilab

Scilab is an open-source, cross-platform computational environment software available for academic and research purposes as a free of charge alternative to the matured computational copyrighted software such as MATLAB. One of important library available for Scilab is image processing toolbox dedicated solely for image and video processing. There are three major toolboxes for this purpose: Scilab image processing toolbox (SIP), Scilab image and video processing toolbox (SIVP) and recently image processing design toolbox (IPD). The target discussion in this paper is SIVP due to its vast use out there and its capability to handle streaming video file as well (note that IPD also supports video processing). Highlight on the difference between SIVP and IPD will also be discussed. From testing, it is found that in term of looping test, Octave and FreeMat are faster than Scilab. However, when converting RGB image to grayscale image, Scilab outperform Octave and FreeMat.

ANALYSIS OF A STEGANOGRAPHIC METHOD FOR HIDING ONE IMAGE IN ANOTHER IMAGE USING MATLAB AND IMAGE PROCESSING TOOLBOX

Analysis of a Steganographic Method for Hiding an Image into a Cover Image Using MATLAB and Image Processing Toolbox: The paper presents an algorithm for hiding a 24-bit color image in bmp format in another 24-bit color image also in bmp format. The algorithm is based on the least-significant bit method and is implemented using MATLAB and Image Processing Toolbox. This algorithm can be applied for 100% reconstruction of the hidden image when four cover images are used.

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.

An image processing toolbox based on MATLAB GUI

Our research realizes the basic processing of images based on MATLAB GUI. The functions include image reading, storage, display, adding noise, denoising, image enhancement, edge detection, image segmentation, discrete Fourier transform, wavelet transform, feature extraction, target recognition, color image processing, etc. At the same time, the image can be stylized and different filter processing can be carried out on the image.

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.

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.

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.

Image Processing for the Identification of Persistent Stress from Retina

Chronic stress is a prolonged pressure that an individual faces over a long period. Chronic stress accounts for 80% of all health problems in the United States, and many other countries like the UK, Germany, India, etc. This can be challenging because it disturbs the immune system, eye vision, digestive system, sleep, and reproductive system. From the retinal images, few parameters are calculated for each disease. To detect glaucoma cup to disk ratio is calculated whereas for CSR area around the macula region is measured and to know whether a person is suffering from hypertension an AV ratio is calculated. The objective of this research is to identify whether a patient is under persistent depression. The retinal images of the patient are the inputs. They are then checked for three main diseases - glaucoma, central serous retinopathy, hypertension that are related to chronic stress. All the parameters are compared with a normal eye. If a person suffers from two or more of these diseases, he or she is evident to suffer from persistent stress. This entire experiment is simulated on MATLAB R2020a software. All the images are from Kaggle dataset and processed using image processing toolbox in MATLAB. The results are validated by ophthalmologist manually.

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.
 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.
 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.
 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.
 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.