Image Processing Concepts Research Articles

Respiratory Diseases Detection using Machine Learning

Prediction of the Respiratory diseases in the earlier stage can be very useful specially to improve the survival rate of that patient. CT scan images are used to detect various lung diseases .These CT scan reports are sent to pathologists for further process. Pathologists analyze CT scan report and predict the infected tissues which are the main cause of the particular disease. This is lengthy process and to avoid this steps and increase the accuracy of the prediction Machine learning plays an important role . The system proposes to build "Predictive Diagnostic System" of infectious lung by using the concept of image processing in conjunction with machine learning. Proposed system will detect the disease from CT scan images and use preprocessing technique that will remove the noise and disturbance in image. Feature extraction process is applied to extract the useful features of underlying image, and feature selection technique will further optimize the top ranking features. CNN algorithm is then applied to classify the images for detection of Respiratory disease. After detection of disease, report will be generated and submitted to patient.

Optimizing Visualization in Endoscopic Spine Surgery.

Given the inherent limitations of spinal endoscopic surgery, proper lighting and visualization are of tremendous importance. These limitations include a small field of view, significant potential for disorientation, and small working cannulas. While modern endoscopic surgery has evolved in spite of these shortcomings, further progress in improving and enhancing visualization must be made to improve the safety and efficacy of endoscopic surgery. However, in order to understand potential avenues for improvement, a strong basis in the physical principles behind modern endoscopic surgery is first required. Having established these principles, novel techniques for enhanced visualization can be considered. Most compelling are technologies that leverage the concepts of light transformation, tissue manipulation, and image processing. These broad categories of enhanced visualization are well established in other surgical subspecialties and include techniques such as optical chromoendoscopy, fluorescence imaging, and 3-dimensional endoscopy. These techniques have clear applications to spinal endoscopy and represent important avenues for future research.

Face Recognition Based on Artificial Neural Network: A Review

The face recognition/detection is considered as one of the most popular applications in the field of image processing and biometric pattern recognition systems. Although the face recognition approach improves authentication procedure, nevertheless still many challenges appear due to diversities in human facial expression, image huge size, background complexity, variation in illumination, poses, blurry, etc. Therefore, the face detection procedure is classified as one of the most difficult tasks in computer vision. This research paper tends to address the concept of image processing along with the use of the Artificial Neural Network approach and represent it is a potential capability in enhancing the method of extracting face pattern through an adaption of various ANN topologies. Furthermore, it represents fundamental phases associated with the construction of any facial recognition system. Finally, it provides a general overview of different literature survives that related to face recognition based on the use of different ANN approaches and algorithms

Fuzzy Logic Based Perceptual Image Hashing Algorithm in Malaysian Banknotes Detection System for the Visually Impaired

Visually impaired persons have difficulty in business that dealing with banknote. This paper proposed a Malaysian banknotes detection system using image processing technology and fuzzy logic algorithm for the visually impaired. The Malaysian banknote reader will first capture the inserted banknote image, sending it to the cloud server for image processing via Wi-Fi medium. The cloud server is established to receive the banknote image sending from the banknote reader, processing them using perceptual hashing based image searching and fuzzy logic algorithm, then return the detected banknote’s value results back to the banknote reader. The banknote reader will display the results in terms of voice message played on the mini speaker attached on it, to allow visually impaired persons knowing the banknote’s value. This hardware mechanism reduces the size and costs for the banknote reader carried by the visually impaired persons. Experimental results showed that this Malaysian banknotes detection system reached an accuracy beyond 95% by running test on 600 different worn, torn and new Malaysian banknotes. After the banknote image being taken by the banknote reader’s camera, the system able to detect the banknote value in about 480 mili-seconds to 560 mili-seconds for a single sided banknote recognition. The banknotes detection speed was also comparable with human observers reading banknotes, with the response of 1.0908 second per banknote slight difference reading time. The IoT and image processing concepts were successfully blended and it provides an alternative to aid the visually impaired person their daily business transaction activities in a better way.

Computer-aided autism diagnosis based on visual attention models using eye tracking

An advantage of using eye tracking for diagnosis is that it is non-invasive and can be performed in individuals with different functional levels and ages. Computer/aided diagnosis using eye tracking data is commonly based on eye fixation points in some regions of interest (ROI) in an image. However, besides the need for every ROI demarcation in each image or video frame used in the experiment, the diversity of visual features contained in each ROI may compromise the characterization of visual attention in each group (case or control) and consequent diagnosis accuracy. Although some approaches use eye tracking signals for aiding diagnosis, it is still a challenge to identify frames of interest when videos are used as stimuli and to select relevant characteristics extracted from the videos. This is mainly observed in applications for autism spectrum disorder (ASD) diagnosis. To address these issues, the present paper proposes: (1) a computational method, integrating concepts of Visual Attention Model, Image Processing and Artificial Intelligence techniques for learning a model for each group (case and control) using eye tracking data, and (2) a supervised classifier that, using the learned models, performs the diagnosis. Although this approach is not disorder-specific, it was tested in the context of ASD diagnosis, obtaining an average of precision, recall and specificity of 90%, 69% and 93%, respectively.

A Survey on Fruit Ripeness Classification Based On Image Processing with Machine Learning

Agriculture has a major role in the economic development of our country. Productive growth and high yield production of fruits is essential and required for the agricultural industry. Due to the lack of skilled workers, 30–35% of the harvested fruits is wasted. also, because of human perception subjectivity identification, classification and grading of fruits not done precisely. So, it is required to impose the automation system in the fruit industry. The machine learning techniques with adequate concepts of image processing have a great scope to provide intelligence for designing an automation system to differentiate the fruits according to its type, variety, matureness and intactness. Application of image processing has helped agriculture to improve yield estimation, disease detection, fruit sorting, irrigation and maturity grading. Image processing techniques can be used to reduce the time consumption and has made it cost efficient. In this paper, an automatic system is reviewed to identify the ripening stages of fruit from images. Various feature extraction is performed using different algorithm to get the low to high level features automatically and later classification is carried out using various machine learning algorithm to get ripening stages of fruit as predicted output.

IoT based Intelligent Car Security System using IRIS image features

A major crisis for car owners is that they are in persistent fear of having their vehicles stolen from parking area or outside their dwell. Connected to vehicles, cyber security takes on a much progressively imperative job such as frameworks and segments that administer security must be shielded from unsafe assaults, unapproved access and harm. Image processing based real time vehicle theft detection and prohibition system provide an optimum solution for this issue. This project provides a solution for car hacking and theft detection with the help of image processing-based application by using embedded system. All articles must contain an abstract. The IoT based iris door lock and unlock is the optimal method for the security in automative domains. From this work can understand the concepts of digital image processing and iris recognition to a greater extent.

A survey of the identification strategies of brain tumors for MR images

A substantial rise in medical cases associated with brain tumor has been seen in recent years, making it the 10th most common type of tumor Impacting both children and adults. Due to the rising refining of medical picture technologies, Brain Tumor [BT] and their study are of considerable concern Medical image processing concepts have been used successfully in diagnosis of Tumor. For its non-invasive imaging properties, science is more oriented toward MR. Diagnosis or identification mechanisms assisted by computers have become problematic and are still an Open concern due to heterogeneity in tumor shapes, locations, and sizes. Many experts in medical field have carried out notable study work on automated detection of tumor strategies based on segmentation, grouping and variations of automatic brain tumor detection. Different brain tumor identification methods for MR images are analysed in the manuscript, including the assets and challenges found with all techniques to detect different forms of BT. The survey presented here is aimed at supporting the researchers identify the important features of types of brain tumor and identify different segmentation/classification approaches that are effective in identifying a variety of tumor types of disorders of the brain. The manuscript covers the most important approaches, procedures and operating practices. Brain tumor identification rules, priorities, restrictions, and their potential snags on MR picture.

Image processing for frost thickness measurement in fin-and-tube heat exchangers

In studies addressing performance degradations owing to frost formation on heat exchangers, the frost thickness is considered an important parameter. The most commonly used method for measuring frost thickness comprises capturing and analyzing an image. However, relatively few studies have investigated the most reasonable method for deriving frost thickness by analyzing an image. In current measurement techniques, it is difficult to quantitatively determine which methods have less error relative to the true value in a complex shape. Therefore, this study attempted to recommend a more reasonable method, based on analysis of various aspects. First, the fundamental concept of image processing was described in detail. Then, the effects of thresholding algorithms, threshold application algorithms, and the determination of the number of segments on the frost thickness were investigated. Based on the results, an appropriate image processing method for measuring frost thickness was recommended. The frost thickness obtained by this method was well-measured, with an uncertainty of approximately 0.18 mm.

New Gen Controlling Variable Using Dragonfly Algorithm in PV Panel

In the present scenario the depletion of conventional sources causes an energy crisis. The energy crisis causes load demand with respect to electricity. The use of renewable energy sources plays a vital role in reducing the energy crisis and in reduction of CO2 emission. The use of solar energy is the major source of power in generation as this is the root cause for the development of wind, tides, etc. However, due to climatic condition the availability of PV sources varies from time to time. Hence it is essential to track the maximum source of energy by implementing different types of MPPT algorithms. However, use of MPPT algorithms has the limitation of using the same during partial shadow conditions. The issue of tracking power under partial shadow conditions can be resolved by implementing an intelligent optimization tracking algorithm which involves a computation process. Though many of nature’s inspired algorithms were present to address real world problems, Mirjalili developed the dragonfly algorithm to provide a better optimization solution to the issues faced in real-time applications. The proposed concept focuses on the implementation of the dragonfly optimization algorithm to track the maximum power from solar and involves the concept of machine learning, image processing, and data computation.

A new auto-replication in systems of attractors with two and three merged basins of attraction via control

Largely recognized as leading concepts in network traffic prediction, machining or image processing, the processes of auto-duplication, self-organization and auto-replication are highly useful and fascinating for chaos and fractal theorists. Those processes appear naturally around us as observed on trees, river deltas, lightning, growth spirals, flowers, romanesco broccoli, frost, etc. Using mathematical notions, concepts and processes to reproduce and control auto-duplication and auto-replication dynamics have attracted the attention of scientists and engineers given their wide range of applications. We use the control technique combined to two different concepts, Julia’s process and fractal-fractional operator, to generate auto-replication in systems of chaotic attractors with two and three merged basins of attraction. The systems used here comprise a controller part, namely the switching-manifold control. Both systems are solved numerically using Julia’s scheme and Legendre wavelets methods. Numerical simulations reveal a fascinating capability for the systems to auto-replicate while conserving the initial properties of the systems, such as symmetry and number of basins of attraction. The merged basins of attraction are shown to be moving away as the result of the fractional dynamics’ impact. Great results that may interest scientists and engineers dealing with fractals and chaos.

Face Mask Detection Using SSDNET and Lightweight Custom CNN

One of the best ways to prevent the spread of the Covid-19 virus is the adoption of the face mask. Just by wearing a face mask can reduce the risk of contracting the virus by almost 70%. Several government agencies are trying to make wearing a face mask mandatory, this process can be aided by using a face mask detecting software based on the concepts of Artificial Intelligence and Image processing. The proposed model is one that has been built using several deep learning concepts and has been trained on a dataset consisting of more than 11,000 images of faces with and without masks. A SSDNET model is being deployed for face detection, the output of which is passed to a custom made Lightweight CNN for mask detection. The model achieves a high accuracy of ~96% and ~99% on two separate testing datasets. The model will help government agencies and health officials fight the global pandemic.

Opportunistic diagnosis of osteoporosis, fragile bone strength and vertebral fractures from routine CT scans; a review of approved technology systems and pathways to implementation.

Osteoporosis causes bones to become weak, porous and fracture more easily. While a vertebral fracture is the archetypal fracture of osteoporosis, it is also the most difficult to diagnose clinically. Patients often suffer further spine or other fractures, deformity, height loss and pain before diagnosis. There were an estimated 520,000 fragility fractures in the United Kingdom (UK) in 2017 (costing £4.5 billion), a figure set to increase 30% by 2030. One way to improve both vertebral fracture identification and the diagnosis of osteoporosis is to assess a patient’s spine or hips during routine computed tomography (CT) scans. Patients attend routine CT for diagnosis and monitoring of various medical conditions, but the skeleton can be overlooked as radiologists concentrate on the primary reason for scanning. More than half a million CT scans done each year in the National Health Service (NHS) could potentially be screened for osteoporosis (increasing 5% annually). If CT-based screening became embedded in practice, then the technique could have a positive clinical impact in the identification of fragility fracture and/or low bone density. Several companies have developed software methods to diagnose osteoporosis/fragile bone strength and/or identify vertebral fractures in CT datasets, using various methods that include image processing, computational modelling, artificial intelligence and biomechanical engineering concepts. Technology to evaluate Hounsfield units is used to calculate bone density, but not necessarily bone strength. In this rapid evidence review, we summarise the current literature underpinning approved technologies for opportunistic screening of routine CT images to identify fractures, bone density or strength information. We highlight how other new software technologies have become embedded in NHS clinical practice (having overcome barriers to implementation) and highlight how the novel osteoporosis technologies could follow suit. We define the key unanswered questions where further research is needed to enable the adoption of these technologies for maximal patient benefit.

Selecting Promising Junior Swimmers in Egypt Using Automated Biometric Algorithms of Image Processing and Fuzzy Concepts

Modern sports need a great physical and psychological effort from young athletes to reach high performance levels. Stature length, leg length, foot length, arm length, hand length, shoulder width, hip width, chest width and weight are the anthropometric characteristics that affect swimmers' performances. This paper introduces new techniques to select promising junior swimmers in Egypt. It develops two automated algorithms to select junior swimmer depending on their anthropometric measurement. The first technique uses Canny filter to develop the first algorithm, while the second one uses the Fuzzy concepts. The proposed algorithms make use of the image processing technique to handle the anthropometric measurements, by detecting the human body feature points automatically from the front and side images. The 101 feature points extract automatically from 36 human body measurements, while swimming games needs only 8 body dimensions from these 36 human body measurements. Therefore, the proposed system is not limited to swimming sports but can also be applied to other sports. Moreover, the experimental results and the corresponding statistical analysis show the high accuracy and advantages of the proposed algorithms. The first algorithm improved the results that could have obtained using the well-known fully vision-based automatic human body method by 22.23%, 15.9%,29.41%, and 27.5%, for stature length, arm length, leg length, and shoulder width, respectively. Also, it gave the best results for Leg Length, and Shoulder width, while the second one yielded the best result for Stature Length.

CUBATURE FORMULA FOR APPROXIMATE CALCULATION INTEGRAL OF HIGHLY OSCILLATING FUNCTION OF TREE VARIABLES (IRREGULAR CASE)

Context. The integrals of highly oscillating functions of many variables are one of the central concepts of digital signal and image processing. The object of research is a digital processing of signals and images using new information operators. Objective. The work aims to construct a cubature formula for the approximate calculation of the triple integral of a rapidly oscillating function of a general form.Method. Modern methods of digital signal processing are characterized by new approaches to obtaining, processing and analyzing information. There is a need to build mathematical models in which information can be given not only by the values of the function at points, but also as a set of traces of the function on the planes and as a set of traces of the function on the lines. There are algorithms which are optimal by accuracy for calculating the integrals of highly oscillating functions of many variables (regular case), which involve different types of information in their construction. As a solution of a broader problem for the irregular case, the work presents the cubature formula for the approximate calculation of the triple integral of the highly oscillating function in a general case. The presented algorithm for approximate calculation of the integral is based on the application of operators that restore the function of three variables using a set of traces of functions on the mutually perpendicular planes. Operators use piece-wise splines as auxiliary functions. The cubature formula correlates with a formula of the Filon type. An error estimation of the approximation of the integral from the highly oscillating function by the cubature formula on the class of differential functions is obtained.Results. The cubature formula of the approximate calculation of the triple integral from the highly oscillating function of a general form is researched.Conclusions. The experiments confirm the obtained theoretical results on the error estimation of the approximation triple integral from the highly oscillating function in a general form by the cubature formula. The prospect of further research is to obtain an estimation of the approximation error on wider classes of functions and to prove that the proposed cubature formula is optimal by the order of accuracy.

Efficient Tumor Detection in MRI Brain Images

<span>Detection of brain of tumor is a laborious task as it involves identification, segmentation followed by detection of the tumor. It is a very challenging task to envisage uncommon structures in the image of human brain[15]. An Image processing concept called MRI can be used to visualize different structures of human body. The Magnetic Resonance images (MRI) are used to detect the uncommon portions of human brain. This paper explores different noise removal methods accompanied by Balance-contrast enhancement technique (BCET) which results in increased accuracy. Segmentation followed by canny edge detection is performed on the improved images to detect the fine edges of the abnormalities present. The model attained an accuracy of at most 98% in detecting the tumor or the abnormality in a human brain which determines the effectiveness of the proposed model.</span>

Quantum Image Histogram Statistics

Image histogram is a simple but important concept in digital image processing. It is not changed with image translation, rotation, scale, and etc., which makes it be widely used in image feature extraction, image segmentation, image matching, image classification, contrast enhancement and so on. With the development of quantum image processing, it is also necessary to perform the histogram statistics of images on quantum computers. However, since all pixels in a quantum image are stored superposedly, it is difficult to solve the problem of counting the number of pixels with a certain color. This paper proposes a method for calculating the quantum image histogram, based on the quantum adder for superposition states. It uses control qubits to determine whether the color information of a quantum image and the index information of the quantum histogram are equal to a particular value. If this is the case, the quantum adder for superposition states counts the number of pixels with that color. This scheme not only solves the problem of histogram statistics in quantum image processing, but also reduces the complexity of classical histogram statistics from O(22n) to O(2q), where n is related to the image size and q is related to color numbers.

Brain Tumor Detection Using Image Segmentation and Classification

Image processing has an important factor called image Segmentation which is very important and initial step in medical image processing. In this process, image is partition according to distinct region. Processing of MRI scan image is the part of medical field. In this project, we use the patient’s MRI scan image to detect the Brain tumor using GUI in MATLAB. Before detection, we remove noise by removal functions and apply some basic concept of image processing including segmentation and morphological operations. This project is implemented in MATLAB software. This proposed method detects exact location of tumor from MRI image. This algorithm could be applied on different MRI scan images. In our purposed model, segmentation algorithm which detect the tumor region. After features are extracted through DWT followed by PCA for reducing features dimensions. Finally, SVM, CNN, Lazy IBK classifiers are applied on it to detect tumor type with high degree of accuracy.

Image Processing Concepts for Brain Tumor MRI Image Classification

The current generation is witnessing a radical change in technology with the rise of artificial intelligence. The application of artificial intelligence on different domain indicates the widespread involvement of this technology in the years to come. One such application is on medical image classification such as brain tumor classification. The process of medical image classification involves techniques from the image processing domain to process set of MRI image data in order to extract prominent feature that eases the classification process. The classifier model learns the MRI image data to predict the occurrence of the tumor cells. The objective of this paper is to provide knowledge pertaining to various approaches implemented in the field of machine learning applied to medical image classification as preparation of the MRI dataset to a standard form is the key for developing classifier model. the paper focus to analyses different types of preprocessing methods, image segmentation, and feature extraction methodologies and inscribes to points out the astute observation for each of techniques present in image processing methodologies. As predicting tumor cells is a challenging task because of its unpredictable shape. Hence emulating an appropriate methodology to improve the accuracy and efficiency is important as it aids in constructing a classifier model that can accelerate the process of prediction and classification for the brain tumor MRI imagery.

Brain Tumor Identification and Classification of MRI images using deep learning techniques

The detection, segmentation, and extraction from Magnetic Resonance Imaging (MRI) images of contaminated tumor areas are significant concerns; however, a repetitive and extensive task executed by radiologists or clinical experts relies on their expertise. Image processing concepts can imagine the various anatomical structure of the human organ. Detection of human brain abnormal structures by basic imaging techniques is challenging. In this paper, a Fully Automatic Heterogeneous Segmentation using Support Vector Machine (FAHS-SVM) has been proposed for brain tumor segmentation based on deep learning techniques. The present work proposes the separation of the whole cerebral venous system into MRI imaging with the addition of a new, fully automatic algorithm based on structural, morphological, and relaxometry details. The segmenting function is distinguished by a high level of uniformity between anatomy and the neighboring brain tissue. ELM is a type of learning algorithm consisting of one or more layers of hidden nodes. Such networks are used in various areas, including regression and classification. In brain MRI images, the probabilistic neural network classification system has been utilized for training and checking the accuracy of tumor detection in images. The numerical results show almost 98.51% accuracy in detecting abnormal and normal tissue from brain Magnetic Resonance images that demonstrate the efficiency of the system suggested.