Image Processing Toolbox Research Articles

A System for Acquisition, Processing and Visualization of Image Time Series from Multiple Camera Networks

A system for multiple camera networks is proposed for continuous monitoring of ecosystems by processing image time series. The system is built around the Finnish Meteorological Image PROcessing Toolbox (FMIPROT), which includes data acquisition, processing and visualization from multiple camera networks. The toolbox has a user-friendly graphical user interface (GUI) for which only minimal computer knowledge and skills are required to use it. Images from camera networks are acquired and handled automatically according to the common communication protocols, e.g., File Transfer Protocol (FTP). Processing features include GUI based selection of the region of interest (ROI), automatic analysis chain, extraction of ROI based indices such as the green fraction index (GF), red fraction index (RF), blue fraction index (BF), green-red vegetation index (GRVI), and green excess (GEI) index, as well as a custom index defined by a user-provided mathematical formula. Analysis results are visualized on interactive plots both on the GUI and hypertext markup language (HTML) reports. The users can implement their own developed algorithms to extract information from digital image series for any purpose. The toolbox can also be run in non-GUI mode, which allows running series of analyses in servers unattended and scheduled. The system is demonstrated using an environmental camera network in Finland.

Consistency of Multiple Renal Functional MRI Measurements Over 18 Months.

Identification of patients with progressive chronic kidney disease (CKD) and those likely to respond to candidate therapeutics is urgently needed. Functional MRI measurements have shown promise. However, knowledge about the consistency of the measurements is essential to conduct longitudinal studies. To investigate the consistency of repeated functional MRI measurements in healthy subjects. Prospective, longitudinal study. Seventeen healthy subjects were examined on two different occasions, 18 months apart. Multiple gradient-recalled-echo, 2D navigator-gated flow-sensitive alternating inversion recovery True-FISP and spin-echo planar diffusion-weighted sequences were used on a 3T scanner. Images were acquired on two different scanner configurations. Blood oxygenation level-dependent (BOLD) R2*, arterial spin labeling (ASL) perfusion-derived blood flow (BF) and apparent diffusion coefficient (ADC) maps were analyzed using a custom image processing toolbox. Regions of interest (ROIs) were placed on renal cortex, medulla, and whole kidney. Multiple researchers were involved in defining the ROIs. Intra- and intersubject coefficients of variation (CV) and Bland-Altman plots were used to measure consistency and evaluate bias in the measurements. A nonparametric Wilcoxon test was used to compare differences between two timepoints. The intrasubject CV for R2* and ADC were 6.8% and 5.3% with small (-3.8 and 5.3%) bias, respectively, comparing baseline and 18-month data. Intrasubject CV for renal cortex BF was higher (18.7%) compared to R2* and ADC, but comparable to prior literature values over shorter durations. It also exhibited a larger bias (-15.4%) between two timepoints and significantly lower values (P = 0.022) at 18-month data. All three MRI parameters over 18 months, even with a scanner upgrade and involving multiple observers, showed good consistency. These results are useful for the interpretation of longitudinal data and support the use of these methods to monitor progression in patients with CKD. 1 Technical Efficacy: Stage 1 J. MAGN. RESON. IMAGING 2018;48:514-521.

Curvelet transforms and flower pollination algorithm based machine vision system for roughness estimation

Machine vision based systems aided in approximation of the surface roughness in a nondestructive means and relieved the process of automation. The advent of computers and computational tools in manufacturing, assisted in reduction of ideal time by their computational knack to estimate the micron level and uncertain in line values of surface roughness. In the present work, to develop a machine vision based intelligent roughness estimation system; high-resolution surface images of the machine surface are captured. The images captured are processed in MATLAB image processing toolbox for Curvelet Transform texture features. The measured surface roughness values and the texture features are mapped using the advanced computational tool Flower Pollination Algorithm (FPA). The FPA closely estimated the surface roughness with precise percentile of error when compared with another support vector machine model.

3D marker-controlled watershed for kidney segmentation in clinical CT exams

BackgroundImage segmentation is an essential and non trivial task in computer vision and medical image analysis. Computed tomography (CT) is one of the most accessible medical examination techniques to visualize the interior of a patient’s body. Among different computer-aided diagnostic systems, the applications dedicated to kidney segmentation represent a relatively small group. In addition, literature solutions are verified on relatively small databases. The goal of this research is to develop a novel algorithm for fully automated kidney segmentation. This approach is designed for large database analysis including both physiological and pathological cases.MethodsThis study presents a 3D marker-controlled watershed transform developed and employed for fully automated CT kidney segmentation. The original and the most complex step in the current proposition is an automatic generation of 3D marker images. The final kidney segmentation step is an analysis of the labelled image obtained from marker-controlled watershed transform. It consists of morphological operations and shape analysis. The implementation is conducted in a MATLAB environment, Version 2017a, using i.a. Image Processing Toolbox. 170 clinical CT abdominal studies have been subjected to the analysis. The dataset includes normal as well as various pathological cases (agenesis, renal cysts, tumors, renal cell carcinoma, kidney cirrhosis, partial or radical nephrectomy, hematoma and nephrolithiasis). Manual and semi-automated delineations have been used as a gold standard. Wieclawek Among 67 delineated medical cases, 62 cases are ‘Very good’, whereas only 5 are ‘Good’ according to Cohen’s Kappa interpretation. The segmentation results show that mean values of Sensitivity, Specificity, Dice, Jaccard, Cohen’s Kappa and Accuracy are 90.29, 99.96, 91.68, 85.04, 91.62 and 99.89% respectively. All 170 medical cases (with and without outlines) have been classified by three independent medical experts as ‘Very good’ in 143–148 cases, as ‘Good’ in 15–21 cases and as ‘Moderate’ in 6–8 cases.ConclusionsAn automatic kidney segmentation approach for CT studies to compete with commonly known solutions was developed. The algorithm gives promising results, that were confirmed during validation procedure done on a relatively large database, including 170 CTs with both physiological and pathological cases.

Digital photography provides a fast, reliable, and noninvasive method to estimate anthocyanin pigment concentration in reproductive and vegetative plant tissues.

Anthocyanin pigments have become a model trait for evolutionary ecology as they often provide adaptive benefits for plants. Anthocyanins have been traditionally quantified biochemically or more recently using spectral reflectance. However, both methods require destructive sampling and can be labor intensive and challenging with small samples. Recent advances in digital photography and image processing make it the method of choice for measuring color in the wild. Here, we use digital images as a quick, noninvasive method to estimate relative anthocyanin concentrations in species exhibiting color variation. Using a consumer‐level digital camera and a free image processing toolbox, we extracted RGB values from digital images to generate color indices. We tested petals, stems, pedicels, and calyces of six species, which contain different types of anthocyanin pigments and exhibit different pigmentation patterns. Color indices were assessed by their correlation to biochemically determined anthocyanin concentrations. For comparison, we also calculated color indices from spectral reflectance and tested the correlation with anthocyanin concentration. Indices perform differently depending on the nature of the color variation. For both digital images and spectral reflectance, the most accurate estimates of anthocyanin concentration emerge from anthocyanin content‐chroma ratio, anthocyanin content‐chroma basic, and strength of green indices. Color indices derived from both digital images and spectral reflectance strongly correlate with biochemically determined anthocyanin concentration; however, the estimates from digital images performed better than spectral reflectance in terms of r 2 and normalized root‐mean‐square error. This was particularly noticeable in a species with striped petals, but in the case of striped calyces, both methods showed a comparable relationship with anthocyanin concentration. Using digital images brings new opportunities to accurately quantify the anthocyanin concentrations in both floral and vegetative tissues. This method is efficient, completely noninvasive, applicable to both uniform and patterned color, and works with samples of any size.

Assessment of the feasibility of detecting concrete cracks in images acquired by unmanned aerial vehicles

An 8-rotor unmanned aerial vehicle is used as a working platform. Its motion characteristics in a hovering state are obtained using a non-contact measurement instrument, which, along with the modulation transfer function of its airborne images, indicates the reliability of the airborne images of unmanned aerial vehicles in a hovering state. By installing a laser range finder on the cradle synchronized with the camera shutter to measure the object distance, the pixel resolution of the object distance is obtained. The airborne images are then processed using the MATLAB image processing toolbox, from which the pixels of concrete cracks are extracted. Compared to a static image and direct manual measurements, the airborne image of the unmanned aerial vehicle has higher precision, indicating its wide potential applications as an alternative of the conventional inspection methods of bridge-inspection vehicle and working platforms.

Real-time eye blink and wink detection for object selection in HCI systems

This paper presents an approach for real-time detection of three types of eye blinks: eye blink (blinking both eyes simultaneously), left and right winks. The process of blink detection has been divided into four parts viz. face localization in facial images acquired through a video camera, eye pair localization, pixels’ motion analysis using optical flow technique, and classification of eye blinks. Blink detection has been performed using a video camera and MATLAB software with image processing and computer vision toolbox. The algorithm takes about 60 ms time for processing a frame and 250 ms time for confirmation and classification of the detected blink. An experiment was conducted to evaluate the performance of the proposed approach in which 10 users voluntarily participated. The performance of the proposed method has been tested under two lighting conditions: natural lighting conditions and controlled lighting conditions. Also, the performance has been tested by varying the distance of the user from the camera. Here, it is observed that the system gives best performance when used under controlled lighting conditions and the user sitting at a distance of about 0.5 m. Accuracy of the proposed approach has been found to be 96, 92 and 88% for detection of eye blink, left wink and right wink, respectively. The proposed method has also been tested on ZJU dataset where it has given precision, detection accuracy and false alarm rate of values 94.11, 91.2 and 1.54%, respectively. The proposed system has been used and evaluated for performing various mouse analogous functions using eye blinks and winks. It has given an accuracy of 90, 80 and 90% in performing left click, double click, and right click operations, respectively.

Calorie Measurement: Predicting the Nutrient Content of Food using image Analysis

People have started giving preference to their health, type of food, workouts in order to keep them away from health problems. Nowadays Obesity has a serious health issue in adults. Obesity is mainly caused due to improper consumption of food. They can be reduced by measuring the intake of food of an individual. This paper gives a brief description of measuring the calorie value of a food which is consumed by the individual. The system first takes the image of the food. From the given food image the feature like color, shape and texture are extracted by using different algorithms. The Bag of features method is used to extract the features and recognize the type of food. The calorie value is measured using the nutrient table. Our system uses the image processing toolbox in mat lab.

Lung Cancer Detection using Image Processing Techniques

Lung cancer is one of the hazardous disease which leads to high death rates in the world. A cancer is an irregular growth of cells that can be characteristically derived from a single irregular cell and that may spread to whole part of the lung. So, it is necessary to find it at the earlier stages and take basic steps to cure. CT scan is one of the sensitive method used in the medical field for treating the patients. The quality of the image is very important for detection of lung cancer. Pre-processing of an image is a necessary process, as there is a difficulty in detecting cancer cells in an image due to the presence of noise and low-quality of images. To reduce the volume of these problems, diagnosis of lung cancer steps like image enhancement, image segmentation, feature extraction methods can be used. For processing and implementation of these methods Matlab tool has been used. This paper focuses on improving the quality of image and to optimise the work. Implementation is done using image processing toolbox that is available in Matlab tool. The whole idea of this research is to show the improved work in the existing system and to get more agreeable results.

Designing a Diagnostic System of Patients Suspected with Glaucoma Using Retinal Fundus Images

Introduction: Glaucoma is one of eye diseases and is a group of disorders that cause damages to optic nerve. If it does not cure; it can lead to permanent vision loss. There is no sign and pain for this disease and it appears in form of blindness in very advanced phase of its progression. Digital imaging is a useful tool for non-invasive measurements in medical field. By using image processing techniques, many medical images could be processed and analyzed, helping experts to detect diseases, decreasing cost and time of tests and helping to do screening significantly. The main purpose of this study was to suggest an algorithm in order to detect glaucoma suspects in retinal fundus images.Material and Methods: This study was an original applied study and its algorithm was developed in MATLAB environment using image processing toolbox. It was evaluated by using existed images obtained from RIM-ONE database. In the present paper, Otsu multi-level thresholding algorithm was used along with MICO algorithm to segment the optic cup and disc and estimate their vertical diameter.Results: The algorithm was run on 124 images containing 57 images of glaucoma suspects and 67 images of healthy retina. The sensitivity and specificity were 0.93 and 0.90 respectively.Conclusion: Suggested algorithm worked fast because light pre-processing has been done. However, there is no system with 100% correct diagnosis, the results obtained from suggested system was acceptable. Thus using such systems could be helpful for practitioners.

Fusion of WorldView2 images using Contourlet, Curvelet and Ridgelet transforms for edge enhancement

ABSTRACT: This article discusses the implementation of three transforms, namely Contourlet, Curvelet and Ridgelet, which are intended for image edge enhancement. These transforms were applied to fused Worldview 2 satellite images. The fusion was performed over the WorldView 2 satellite images applying various types of wavelet transforms, such as Daubechies, Bior, rbior, Coiflet and Symlet 5, with different levels of decomposition. The best results were obtained for the case of Symlet 5, level 5. Wavelet fused images and the generated images (using Contourlet, Curvelet and transformed Ridgelet) were evaluated and analyzed quantitatively. Quantitative methods in the present analysis include ERGAS, RASE, Universal Quality (Qu) and correlation coefficient (CC). Image merging and the implementation of transforms were performed with MatLab®, which supplies the following tools: Wavelet toolbox, Image processing toolbox, Contourlet toolbox, and Curvelet and Ridgelet source code. The results show that the Curvelet and Ridgelet transforms yield better results in terms of edge enhancement for both the merged image and the original image.

Indian Fake Currency Detection using Image Processing: A Review

Paper currency identification is one of the image processing techniques i.e. clothed to recognize currency of different countries. The paper currencies of different countries are collectively rises ever more. However, the main intention of most of the standard currency recognition systems and machines is on recognizing fake currencies. The features are extracted by using image processing toolbox in MATLAB and preprocessed by reducing the data size in captured image. The expose pluck out is discharged by considering HSV (Hue Saturation Value). The chief is neural network classifier and the next step is recognition. MATLAB is used to evolve this program. The new source of paper currency recognition is pattern recognition. But for currency recognition, converter system is an image processing method which is used to identify currency and transfer it into the other currencies as the users need. The need of currency recognition and converters is accurately to recognize the currencies and transfer the currency immediately into the other currency. This application uses the computing energy in differentiation among different kinds of currencies are differentiated with their suitable class using power computing. Fake note at present plays a key topic for the researchers. The recognition system is composed of two parts. First is the captured image and the second is recognition. Forged currencies recognition is the main aim of the standard paper currency identification system. The most mandatory system is currency identification system and it should be very accurate. The performance of different methods are surveyed to refine the exactness of currency recognition system.

Feature Matching in Iris Recognition System using MATLAB

Iris recognition system is a secure human authentication in biometric technology. Iris recognition system consists of five stages. They are Feature matching, Feature encoding, Iris Normalization, Iris Segmentation and Image acquisition. In Image acquisition, the eye Image is captured from the CASIA database, the Image must have good quality with high resolution to process next steps. In Iris Segmentation, the Iris part is detected by using Hough transform technique and Canny Edge detection technique. Iris from an eye Image segmented. In normalization, the Iris region is converted from the circular region into a rectangular region by using polar transform technique. In feature encoding, the normalized Iris can be encoded in the form of binary bit format by using Gabor filter techniques. In feature matching, the encoded Iris template is compared with database eye Image of Iris template and generated the matching score by using Hamming distance technique and Euclidean distance technique. Based on the matching score, we get the result. This project is developed using Image processing toolbox of Matlab software.

Braille2Alpha: Braille Dots Recognition with Alphanumeric Conversion

The Braille system is a tactile language where each element is represented by a cell with six dot positions, arranged in three rows and two columns. Each dot position can be raised or otherwise allowing different configurations which can be felt by trained fingers. For caregivers with normal sights, training their fingers is not naturally easy. This paper presents an image processing approach to Braille dots recognition with alphanumeric conversion, whereby a person with normal eyesight is able to translate a raw Braille image captured by a mobile camera into the corresponding alphanumeric texts. Image pre-processing relies heavily on various segmentation algorithms in the MATLAB image processing Toolbox. This application is hoped to help the blind and the visually impaired community as well as their caregivers to translate Braille texts digitally, hence enhancing the communication and collaboration possibilities.

A Biometric Fusion Based on Face and Fingerprint Recognition using ANN

Biometric systems are used for identifying and recognizing individual characteristics on the basis of biological or behavioral features. In the research work, a biometric fusion system based on fingerprint and face using the artificial intelligence technique is proposed. To achieve better accuracy of the biometric fusion system, the uniqueness of feature is significant. To find out the unique feature set from the data, we have used different feature extraction algorithm in the proposed biometric fusion system. Initially, pre-processing has been applied on the test images which is used to remove the unwanted data from the uploaded image and return an appropriate data for further process. In the fingerprint part, minutia extraction is used as a feature of fingerprint whereas Extended Local Binary pattern (ELBP) is used for extracting features of face and creates a pattern of face features. To create a unique feature set, optimization algorithm is needed and we have used genetic algorithm as a feature optimization technique. In the proposed fusion system, ANN is used to classify the test data according to the trained ANN structure with optimized feature data of fingerprint and face. To check the efficiency of proposed fusion system, we have calculated the performance parameters like FAR, FRR and Accuracy. From the analysis of proposed fusion system, we have observed that the accuracy of the proposed work is better than the previous ones and it is more than the 94%. To design a proposed biometric fusion system, image processing toolbox is used under the MATLAB environment.

Image processing in detection of knee joints injuries based on MRI images

This paper presents image processing methods for visualization and classification of medial meniscus tears. The first method uses watershed with a threshold segmentation approach. The algorithm was tested on a number of images of the knee obtained with a use of the magnetic resonance imaging technique (MR). Images of the knee were collected from healthy subjects and patients with a clinically diagnosed meniscal pathology. Then, watershed technique was compared with other popular methods of image segmentation, i.e. simple thresholding and region growing. For this purpose, the execution speed and the efficiency of the methods were analyzed. Additionally, an automatic detection of the meniscus based on MRI of the knee joint was developed. The solutions were implemented using classical image processing methods in the MATLAB environment with an application of the Image Processing Toolbox and MVtec Halcon vision libraries. The presented methods will have a practical value for the referring physicians and the diagnostic imaging specialists.

A multi-objective simulation-optimization model for in situ bioremediation of groundwater contamination: Application of bargaining theory

In the present study, a BIOPLUME III simulation model is coupled with a non-dominating sorting genetic algorithm (NSGA-II)-based model for optimal design of in situ groundwater bioremediation system, considering preferences of stakeholders. Ministry of Energy (MOE), Department of Environment (DOE), and National Disaster Management Organization (NDMO) are three stakeholders in the groundwater bioremediation problem in Iran. Based on the preferences of these stakeholders, the multi-objective optimization model tries to minimize: (1) cost; (2) sum of contaminant concentrations that violate standard; (3) contaminant plume fragmentation. The NSGA-II multi-objective optimization method gives Pareto-optimal solutions. A compromised solution is determined using fallback bargaining with impasse to achieve a consensus among the stakeholders. In this study, two different approaches are investigated and compared based on two different domains for locations of injection and extraction wells. At the first approach, a limited number of predefined locations is considered according to previous similar studies. At the second approach, all possible points in study area are investigated to find optimal locations, arrangement, and flow rate of injection and extraction wells. Involvement of the stakeholders, investigating all possible points instead of a limited number of locations for wells, and minimizing the contaminant plume fragmentation during bioremediation are new innovations in this research. Besides, the simulation period is divided into smaller time intervals for more efficient optimization. Image processing toolbox in MATLAB® software is utilized for calculation of the third objective function. In comparison with previous studies, cost is reduced using the proposed methodology. Dispersion of the contaminant plume is reduced in both presented approaches using the third objective function. Considering all possible points in the study area for determining the optimal locations of the wells in the second approach leads to more desirable results, i.e. decreasing the contaminant concentrations to a standard level and 20% to 40% cost reduction.

Software toolbox for analysis of the endometrial myometrial junction - a pilot study

To develop and evaluate an algorithm for computerized evaluation and measurement of the endometrial-myometrial junction (EMJ). The advanced image processing toolbox of the Matlab software package was used for identificiation and quantitative analysis of the EMJ area on three-dimensional (3D) rendered coronal plane uterine images, with clear-cut borders of the EMJ. The algorithm was used to process the images and calculate the geometric parameters characterizing the identified EM The manual measurements of the maximum thickness of the EMJ were compared to automated measurements performed by the algorithm on the same images. For all three interfaces, the mean maximum manual measurement was less than the mean maximui computed measurement. The differences between the two measurements were not statistically significant (p = 0.275, 0.608 and 0.41 for the right wall, left wall, and fundus, respectively). The mean systematic and random errors ranged from 5.4% tol9.3% and 20.4 to 48.6%, respectively. Pearson correlations for the right wall, left wall and fundus (r = 0.642, p = 0.001; r = 0.730, p < 0.001, and r 0.694, p < 0.001, respectively) were good. Maximum EMJ thickness measurements performed by the innovative Matla software algorithm are as accurate as manual measurements, and have the potential to reduce inter-observer variability.

Aplikasi MATLAB untuk Mengenali Karakter Tulisan Tangan

&lt;p&gt;Handwriting recognition is one of the very interesting research object in the field of image processing, artificial intelligence and computer vision. This is due to the handwritten characters is varied in every individual. The style, size and orientation of handwriting characters has made every body’s is different, hence handwriting recognition is a very interesting research object. Handwriting recognition application has been used in quite many applications, such as reading the bank deposits, reading the postal code in letters, and helping peolple in managing documents.&lt;/p&gt;&lt;p&gt;This paper presents a handwriting recognition application using Matlab. Matlab toolbox that is used in this research are Image Processing and Neural Network Toolbox.&lt;/p&gt;&lt;p&gt; &lt;/p&gt;

Generating Road Network Graph with Vision-Based Unmanned Vehicle

With the advancement of technology and its cheapness, robotic vehicles have gained a large number of applications. The spread of their use is growing also because they are getting smaller, lighter and easier to build. In this paper we present a simple and effective way to map a road network with the help of a driverless vehicle. Our approach consists of only three parts: vision-segmentation, angle variation and travelled distance. A video camera attached to a Lego^® NXT Mindstorm vehicle guides it by image segmentation using Matlab^® Image processing toolbox, along a road network, in which is represented by black tape over a white floor. The algorithm makes the vehicle travel all over the road memorizing main coordinates to identify all crossroads by keeping track of the travelled distance and the current angle. The crossroads and road’s end are the nodes of the graph. After several simulations have been performed, the modelling proved to be successful in that small scale approach. Consequently, there are good chances that driverless cars and UAVs also make use of the strategies to map route networks accordingly. The algorithm presented in this paper is useful when there is no localization signal such as GPS, for example, navigation on water, tunnels, inside buildings, among others. <strong>Faculty Sponsor</strong>: Francisco de Assis Zampirolli