Image Processing Operations Research Articles

Super-linear speedup for real-time condition monitoring using image processing and drones

Real-time inspections for the large-scale solar system may take a long time to get the hazard situations for any failures that may take place in the solar panels normal operations, where prior hazards detection is important. Reducing the execution time and improving the system’s performance are the ultimate goals of multiprocessing or multicore systems. Real-time video processing and analysis from two camcorders, thermal and charge-coupling devices (CCD), mounted on a drone compose the embedded system being proposed for solar panels inspection. The inspection method needs more time for capturing and processing the frames and detecting the faulty panels. The system can determine the longitude and latitude of the defect position information in real-time. In this work, we investigate parallel processing for the image processing operations which reduces the processing time for the inspection systems. The results show a super-linear speedup for real-time condition monitoring in large-scale solar systems. Using the multiprocessing module in Python, we execute fault detection algorithms using streamed frames from both video cameras. The experimental results show a super-linear speedup for thermal and CCD video processing, the execution time is efficiently reduced with an average of 3.1 times and 6.3 times using 2 processes and 4 processes respectively.

Automatic Classification of Images with Skin Cancer Using Artificial Intelligence

Skin cancer is the most common malignant neoplasty in the world, it is a public health problem, which has increased in recent years due to environmental changes, different lifestyles, sun exposure, among others. One way to detect skin cancer is by analyzing medical images, analyzing these images can get the detection of any abnormalities. In this paper, several block programming models are implemented with classifiers for the recognition of medical images of skin cancer. Preprocessing, manipulation, and computer vision to extract the relevant characteristics of the images are the starting point for obtaining appropriate classification values. The main objective of this project is to perform the analysis of a set of classification techniques, as well as to verify that combination of image processing operations and classification tools provide better performance compared to the classification values of the original images. Images of three kinds of skin cancer type were used: melanocytic nevi, melanoma, and benign lesions similar to keratosis. Each category contains 200 images. The images were subjected to a set of filters, to later use different classification algorithms. 6 types of filters and 5 different classification techniques were implemented. The results obtained allow us to see the feasibility of the proposed method.

An evolutionary block based network for medical image denoising using Differential Evolution

Image denoising is the key component in several computer vision and image processing operations due to unavoidable noise in the image generation process. For medical image processing, deep convolutional neural networks (CNN) gives a state-of-the-art performance. However, network structures are manually constructed for specific tasks and require several trials to tune a large number of hyperparameters, which can take a long time to construct a network. Additionally, the fittest hyperparameters which may be suitable for source data properties like noisy features cannot be easily found to target data. The realistic noise is generally mixed, complex, and unpredictable in medical images, which makes it difficult to design an efficient denoising network. We developed a Differential Evolution (DE) based automatic network evolution model in this paper to optimize the network architectures and hyperparameters by exploring the fittest parameters. Furthermore, we adopted a transfer learning technique to accelerate the training process. The proposed evolutionary algorithm is flexible and finds optimistic network architectures using well-known methods including residual and dense blocks. Finally, the proposed model was evaluated on four different medical image datasets. The obtained results at different noise levels show the potentiality of the proposed model named DEvoNet for identifying the optimal parameters to develop a high-performance denoising network structure.

Multilevel Thresholding for Image Segmentation Using Mean Gradient

Image binarization and segmentation have been one of the most important operations in digital image processing and related fields. In spite of the enormous number of research studies in this field over the years, huge challenges still exist hampering the usability of some existing algorithms. Some of these challenges include high computational cost, insufficient performance, lack of generalization and flexibility, lack of capacity to capture various image degradations, and many more. These challenges present difficulties in the choice of the algorithm to use, and sometimes, it is practically impossible to implement these algorithms in a low-capacity hardware application where computational power and memory utilization are of great concern. In this study, a simple yet effective and noniterative global and bilevel thresholding technique is proposed. It uses the concept of image gradient vector to binarize or segment the image into three clusters. In addition, a parametric preprocessing approach is also proposed that can be used in image restoration applications. Evidences from the experiments from both visual and standard evaluation metrics show that the proposed methods perform exceptionally well. The proposed global thresholding outperforms the formidable Otsu thresholding technique.

Design and development of DrawBot using image processing

Extracting text from an image and reproducing them can often be a laborious task. We took it upon ourselves to solve the problem. Our work is aimed at designing a robot which can perceive an image shown to it and reproduce it on any given area as directed. It does so by first taking an input image and performing image processing operations on the image to improve its readability. Then the text in the image is recognized by the program. Points for each letter are taken, then inverse kinematics is done for each point with MATLAB/Simulink and the angles in which the servo motors should be moved are found out and stored in the Arduino. Using these angles, the control algorithm is generated in the Arduino and the letters are drawn.

A Survey on Applications of Sampling Operators in Image Processing

The objective of this paper is to present a brief study of linear and non-linear cases of univariate and multivariateKantorovich sampling operators and their applications to image processing. This kind of operators are verysuitable to study applications to Signal and Image Processing. Image processing through sampling operatorsplays a crucial part in the diagnosis of Arterial diseases. The visual and empirical assessment of cardiac structureand function is an important challenge faced by medical elds and hospitals.

MSRD-CNN: Multi-Scale Residual Deep CNN for General-Purpose Image Manipulation Detection

The authenticity of digital images is a major concern in multimedia forensics due to the availability of advanced photo editing tools/devices. In the literature, several image forensic methods are available to detect specific image processing or editing operations. However, it remains a challenging task to design a universal forensic method that can detect multiple image editing operations. In this paper, a novel Multi-Scale Residual Deep CNN (MSRD-CNN) is designed to learn the image manipulation features adaptively for multiple image manipulation detection. Our network comprises of three stages: pre-processing, hierarchical high-level feature extraction, and classification. Firstly, a multi-scale residual module is employed in pre-processing stage to extract the prediction error or noise features adaptively. Afterwards, the obtained noise features are processed by feature extraction network having multiple Feature Extraction Blocks (FEBs) for the extraction of high-level image tampering features. Lastly, the resultant feature map is provided to the fully-connected dense layer for classification. The experiment results show that our model surpasses the existing schemes even under anti-forensic attacks, when evaluated on large-scale datasets by considering multiple image processing operations. The proposed network provides overall classification accuracies of 97.07% and 97.48% for BOSSBase and Dresden datasets, respectively.

FPGA-Based Implementation of Ship Detection for Satellite On-Board Processing

At present, the raw echo data captured by spaceborne SAR is usually downlinked to the ground stations for imaging and analysis. If the SAR data can be processed on-board, the processing results could be transmitted to users directly through broadcast distribution, which can greatly reduce the delay time for emergency applications. However, on-board processing implementation faces many challenges due to the space radiation environment and limited resources of the satellite. In this paper, an FPGA-based implementation of ship detection for on-board processing is proposed, which has high efficiency in logic and memory resources. First, the hardware-oriented clustering approach is proposed. Image processing operations with similar regularity of data access can be mapped in one processing engine, which can reduce the employment of logic resources. Second, the concept of the data-buffering cycle (DBC) is proposed. The DBC provides a method to analyze the intermediate data and optimize the memory reuse. Finally, based on the above optimization methods, the FPGA-based implementation for a ship detection algorithm is presented. Compared with the traditional methods, the experimental results show the efficacy of our proposed method with lower consumption in logic and memory resources.

Structural monitoring of a breakwater using UAVs and photogrammetry

The present project addresses a problem related to the erosion effects on a breakwater barrier due to waves which leads to its degradation and that may eventually lead to lack of functionality of the structure. In the present case, the breakwater acts as a physical barrier between the Atlantic Ocean and the cargo Harbour of Leixões, in Matosinhos, Portugal, justifying the needs of health monitoring of the barrier.To monitor this structure, with a length of roughly 700 m, the need of a fast data acquisition system led to the choice of imaging techniques which allow for a fast acquisition of a diversified data set. The images were acquired using a high-resolution camera attached to an unmanned aerial vehicle (UAV), enabling a faster and more automated procedure that leads to the systematization of the process, while being compatible with the difficult accessibility of the structure, which is surrounded by sea waves. Point clouds corresponding to the breakwater’s geometry were then obtained from the set of the UAV aerial images using photogrammetry.Two image acquisition and processing operations were performed three months apart in order to compare the point clouds acquired in the different instances and identify possible changes in the geometric configuration of the breakwater. By registering the two point clouds and computing the distance between them, it was possible to show that some movement within the structure occurred between the two points in time.

Online Monitoring System for Macro-Fatigue Characteristics of Glass Fiber Composite Materials Based on Machine Vision

Glass fiber-based composites are widely used in various fields due to the excellent properties of glass fiber. Although glass fiber has the advantages of high strength and corrosion resistance, it also has the weakness of brittleness and low toughness. When glass fiber-based materials are loaded under alternating stresses for a long time, there is a high risk of fatigue-induced deformation damage. The accidents caused by fatigue damage (FD) are all over the field and have caused serious accidents. Most of the existing methods for fatigue deformation monitoring rely on high-precision sensors, which are expensive and poorly robust, and do not have the ability to be extended to industrial production. In this article, we first proposed an <i>in situ</i> online monitoring system purely based on machine vision, which identifies the key frames at the same position in different periods in the experimental video stream and extracts the changing regions through a series of image processing operations to judge whether fatigue deformation occurs. The proposed monitoring method can be applied to the task of monitoring fatigue deformation tests of rigid materials before service. After on-site testing and evaluation by professionals, the proposed monitoring system can completely capture the deformation characteristics of the material during the entire test cycle with a deformation accuracy of 0.07 mm and an average false alarm rate of 2.14&#x0025;. The complete deformation video data are provided by the monitoring system that can be used for material deformation characteristics modeling.

Effects of Image Processing Operations on Adversarial Noise and Their Use in Detecting and Correcting Adversarial Images

Effects of Image Processing Operations on Adversarial Noise and Their Use in Detecting and Correcting Adversarial Images

Development of methods for generation of digital watermarks resistant to distortion

Active attacks and natural impacts can lead to two types of image-container distortions: noise-like and geometric. There are also image processing operations, e.g. scaling, rotation, truncation, pixel permutation which are much more detrimental to digital watermarks (DWM). While ensuring resistance to removal and geometric attacks is a more or less resolved problem, the provision of resistance to local image changes and partial image deletion is still poorly understood. The methods discussed in this paper are aimed at ensuring resistance to attacks resulting in partial image loss or local changes in the image. This study's objective is to develop methods for generating a distortion-resistant digital watermark using the chaos theory. This will improve the resistance of methods of embedding the digital watermark to a particular class of attacks which in turn will allow developers of DWM embedding methods to focus on ensuring the method resistance to other types of attacks. An experimental study of proposed methods was conducted. Histograms of DWMs have shown that the proposed methods provide for the generation of DWM of a random obscure form. However, the method based on a combination of Arnold’s cat maps and Henon maps has noticeable peaks unlike the method based on shuffling the pixels and their bits only with Arnold’s cat maps. This suggests that the method based only on Arnold’s cat maps is more chaotic. This is also evidenced by the value of the coefficient of correlation between adjacent pixels close to zero (0.0109) for color DWMs and 0.030 for black and white images.

An Unsupervised Learning of Hyperspectral Images using Fuzzy C-means (FCM) Clustering Method with Glowworm Swarm Optimization (GSO)

The unsupervised learning method is one of the formidable operations in Hyper-Spectral Image (HSI) processing. Fuzzy C-Means (FCM) clustering is an optimistic and strategic method for selecting the unsupervised bands. There are some limits and standards in fuzzy clustering technique. The Glowworm Swarm Optimization (GSO) is proposed with combining fuzzy clustering and GSO. The GSO is introduced to enhance the performance of fuzzy clustering to optimize the characteristics of hyperspectral images. The main objective of the proposed method is to improve the accuracy of the hyperspectral datasets and to achieve it through better computational time. The experimental results are achieved through MATLAB toolbox and the proposed method has the capability to perform with the high quality hyperspectral image classification. Copyright © VBRI Press.

Classification of Initial Stages of Alzheimer’s Disease through Pet Neuroimaging Modality and Deep Learning: Quantifying the Impact of Image Filtering Approaches

Alzheimer’s disease (AD) is a leading health concern affecting the elderly population worldwide. It is defined by amyloid plaques, neurofibrillary tangles, and neuronal loss. Neuroimaging modalities such as positron emission tomography (PET) and magnetic resonance imaging are routinely used in clinical settings to monitor the alterations in the brain during the course of progression of AD. Deep learning techniques such as convolutional neural networks (CNNs) have found numerous applications in healthcare and other technologies. Together with neuroimaging modalities, they can be deployed in clinical settings to learn effective representations of data for different tasks such as classification, segmentation, detection, etc. Image filtering methods are instrumental in making images viable for image processing operations and have found numerous applications in image-processing-related tasks. In this work, we deployed 3D-CNNs to learn effective representations of PET modality data to quantify the impact of different image filtering approaches. We used box filtering, median filtering, Gaussian filtering, and modified Gaussian filtering approaches to preprocess the images and use them for classification using 3D-CNN architecture. Our findings suggest that these approaches are nearly equivalent and have no distinct advantage over one another. For the multiclass classification task between normal control (NC), mild cognitive impairment (MCI), and AD classes, the 3D-CNN architecture trained using Gaussian-filtered data performed the best. For binary classification between NC and MCI classes, the 3D-CNN architecture trained using median-filtered data performed the best, while, for binary classification between AD and MCI classes, the 3D-CNN architecture trained using modified Gaussian-filtered data performed the best. Finally, for binary classification between AD and NC classes, the 3D-CNN architecture trained using box-filtered data performed the best.

Deep generative neural networks for spectral image processing

An artificial intelligence approach based on deep generative neural networks for spectral imaging processing was proposed. The key idea was to treat different spectral image processing operations such as segmentation, regression, and classification as image-to-image translation tasks. For the image-to-image translation, the conditional generative adversarial networks were used. As a baseline comparison, the traditional chemometric approach based on pixels wise modelling was demonstrated. The analysis was presented with two real data sets related to fruit property prediction and kernel and shell classification of walnuts. The presented artificial intelligence approach for spectral image processing can provide benefits for any field of science where spectral imaging and processing is widely performed.

Zero-bit fragile watermarking for medical image tamper detection and recovery using RS code and lifting wavelet transform

ABSTRACT Medical images are habitually composed of Regions of Interest (ROI) and Region of Non-interest (RONI). ROI means the area containing the crucial information for diagnosis. To achieve the fidelity and integrity of the ROI, we propose a novel watermarking approach based on two great concepts zero-watermarking and Error Correcting Code (ECC). Tamper detection and recovery information are stored in RONI which accepts some visual quality degradation. Experimental results prove that our proposed approach produces a good performance in terms of imperceptibility and the ability to resist several hard attacks. The proposed scheme can recover 100% of the ROI until 15% of distortion is caused by salt and pepper noise. For multiplicative and Gaussian noise, the scheme has also a good capability of recovery (between 70% and 100%). With close to 20% of distortion, the system can recover 50% of the ROI. The proposed method has also a good capability of recovery against cropping and image processing operations.

Image-based processing simulation of shock wave propagation through the area of ionization instability

A partially automatic method of digital processing images (photographs, shadow and Schlieren pictures) for the analysis of experimental data is proposed. The method is utilized to investigate the effect of the region of ionization instability created by a glow gas discharge on the front of an initially flat shock wave. The proposed method is based on a composition of simple image processing operations and makes it possible to perform simulations taking into account the real geometry of the ionization strata and the shape of the front of a shock wave based on the obtained experimental images. First, as a result of digital processing the geometry of experimental objects is extracted from the images. This information is then embedded in the Navier-Stokes code for conducting simulations. New results for the real geometry of ionization strata of different scales are presented which confirmed the previous ones obtained for the density homogeneously stratified source model.

ENCRYPTION AND DATA INSERTION TECHNIQUE USING REGION DIVISION AND HISTOGRAM MANIPULATION

Traditionally, encryption is applied to mask the semantic of a content, while data insertion adds data to a content for management purpose. In this work, a joint encryption and data insertion method is proposed. The input image is divided into 2 parts, where the first part is manipulated to mask the perceptual semantics, while the second part is processed to hide data. The binary image, which is the data to be inserted, further divides the second part of the input image into 2 regions, one being the ‘zero’ region and the other being the ‘one’ region. Pixels of the original image at position coinciding with the ‘zero’ region are darken, while those coinciding with the ‘one’ region are brightened. The darkening and brightening processes are performed by using histogram matching technique. Furthermore, two techniques are introduced to improve robustness of the inserted binary image against basic image processing operations. The proposed joint method allows the inserted binary image to be extracted directly from the masked image or from the reconstructed image. The proposed method is also commutative because the same result is achieved irregardless of the order of processing in encrypting and inserting data.

RT-SPeeDet: Real-Time IP–CNN-Based Small Pit Defect Detection for Automatic Film Manufacturing Inspection

Pits are defects that occur during the film manufacturing process; they appear in the micrometer scale, which makes distinguishing them with the human eye difficult. Existing defect detectors have poor recognition rates for small objects or require a considerable amount of time. To resolve these problems, we propose a real-time small pit defect detector (RT-SPeeDet), a two-stage detection model based on an image processing and convolutional neural network (IP–CNN) approach. The proposed method predicts boundary boxes using a lightweight image-processing algorithm optimized for pit defects, and applies binary classification to the predicted regions; thus, simultaneously simplifying the problem and achieving real-time processing speed, unlike existing detection methods that rely on CNN-based detectors for both boundary box prediction and classification. RT-SPeeDet uses lightweight image processing operations to extract pit defect candidate region image patches from high-resolution images. These patches are then passed through a CNN-based binary classifier to detect small pit defects at a real-time processing speed of less than 0.5 s. In addition, we propose a multiple feature map synthesis method that enhances the features of pit defects, enabling efficient detection of faint pit defects, which are particularly difficult to detect.

Image processing system using MATLAB-based analytics

Owing to recent technological advancement, computers and other devices running several image editing applications can be further exploited for digital image processing operations. This paper evaluates various image processing techniques using matrix laboratory (MATLAB-based analytics). Compared to the conventional techniques, MATLAB gives several advantages for image processing. MATLAB-based technique provides easy debugging with extensive data analysis and visualization, easy implementation and algorithmic-testing without recompilation. Besides, MATLAB's computational codes can be enhanced and exploited to process and create simulations of both still and video images. Moreover, MATLAB codes are much concise compared to C++, thus making it easier for perusing and troubleshooting. MATLAB can handle errors prior to execution by proposing various ways to make the codes faster. The proposed technique enables advanced image processing operations such as image cropping/resizing, image denoising, blur removal, and image sharpening. The study aims at providing readers with the most recent MATLAB-based image processing application-tools. We also provide an empirical-based method using two-dimensional discrete cosine transform (2D-DCT) derived from its coefficients. Using the most recent algorithms running on MATLAB toolbox, we performed simulations to evaluate the performance of our proposed technique. The results largely present MATLAB as a veritable approach for image processing operations.