Hybrid Image Processing Research Articles

Enhancing deep learning pre-trained networks on diabetic retinopathy fundus photographs with SLIC-G.

Diabetic retinopathy disease contains lesions (e.g., exudates, hemorrhages, and microaneurysms) that are minute to the naked eye. Determining the lesions at pixel level poses a challenge as each pixel does not reflect any semantic entities. Furthermore, the computational cost of inspecting each pixel is expensive because the number of pixels is high even at low resolution. In this work, we propose a hybrid image processing method. Simple Linear Iterative Clustering with Gaussian Filter(SLIC-G) for the purpose of overcoming pixel constraints. The SLIC-G image processing method is divided into two stages: (1) simple linear iterative clustering superpixel segmentation and (2) Gaussian smoothing operation. In such a way, a large number of new transformed datasets are generated and then used for model training. Finally, two performance evaluation metrics that are suitable for imbalanced diabetic retinopathy datasets were used to validate the effectiveness of the proposed SLIC-G. The results indicate that, in comparison to prior published works' results, the proposed SLIC-G shows better performance on image classification of class imbalanced diabetic retinopathy datasets. This research reveals the importance of image processing and how it influences the performance of deep learning networks. The proposed SLIC-G enhances pre-trained network performance by eliminating the local redundancy of an image, which preserves local structures, but avoids over-segmented, noisy clips. It closes the research gap by introducing the use of superpixel segmentation and Gaussian smoothing operation as image processing methods in diabetic retinopathy-related tasks.

Application of Hybrid Image Processing Based on Artificial Intelligence in Interactive English Teaching

Primary school English teaching resources play an important role in primary school English teaching. The information age requires that primary school English teaching should strengthen the use of multimedia resources and gradually realize the diversification of teaching content. Expanded reality innovation is a sort of mixture picture handling innovation, which is one of the significant innovations that would influence the improvement of fundamental schooling in the following five years. It can seamlessly output virtual objects to the real environment, which is convenient for this paper to obtain and absorb information. It can also help students to participate in exploration and cultivate their creativity and imagination. It can strengthen the cooperation between students and teachers and create various learning environments. It has an immeasurable prospect of development in the field of education. The primary school English teaching resources based on augmented reality create a realistic learning situation from two-dimensional plane to three-dimensional three-dimensional display, and enrich the presentation of primary school English teaching content. It can stimulate students’ interest in learning English and promote the transformation of English teaching methods. It is a useful attempt in the field of education. This paper made statistics on the test results of the experimental class and the control class. Most of the scores of the experimental group were between 71 and 100, a total of 27, accounting for 67.5%. The score distribution of the control class was relatively balanced, with the highest number between 61-70, and the number was 10, accounting for 25%. Therefore, it can be seen that hybrid image processing technology is important for interactive English teaching.

Deep-learning empowered unique and rapid optimization of meta-absorbers for solar thermophotovoltaics

Optical nano-structure designs usually employ computationally expensive and time-intensive electromagnetic (EM) simulations that call for resorting to modern-day data-oriented methods, making design robust and quicker. A unique dataset and hybrid image processing model combining a CNN with gated recurrent units is presented to foresee the EM absorption response of photonic nano-structures. An inverse model is also discussed to predict the optimum geometry and dimensions of meta-absorbers. Mean-squared error of the order of 10−3 and an accuracy of 99% is achieved for trained models, and the average prediction time for the DL models is around 98% faster than that of simulations. This idea strengthens the proposition that efficient DL-based solutions can substitute the traditional methods for designing nano-optical structures.

Automated Brain Tumor Detection and Classification in MRI Images: A Hybrid Image Processing Techniques

Due to the complex structure of brain images, accurately detecting and segmenting brain tumors with Magnetic Resonance Imaging (MRI) is a difficult process. This paper suggests an automated brain tumor identification and segmentation approach employing hybrid salient segmentation with K-Means clustering and hybrid CLEACH-median filter algorithm on MRI images. The proposed method enhances the contrast and detail of MRI images using a hybrid CLEACH-median filter algorithm, and segments the most important features of the images using a hybrid salient segmentation method with K-Means clustering. The proposed method includes a stages classification step to determine the stage of the brain tumor. The findings show that the suggested approach outperformed existing methods in terms of efficiency and accuracy for both detecting and segmenting brain tumors. The suggested technique can be a useful tool for automating the detection and segmentation of brain tumors, which will help radiologists and physicians make quicker and more accurate diagnosis.

COVID-19 infection segmentation using hybrid deep learning and image processing techniques

The coronavirus disease 2019 (COVID-19) epidemic has become a worldwide problem that continues to affect people’s lives daily, and the early diagnosis of COVID-19 has a critical importance on the treatment of infected patients for medical and healthcare organizations. To detect COVID-19 infections, medical imaging techniques, including computed tomography (CT) scan images and X-ray images, are considered some of the helpful medical tests that healthcare providers carry out. However, in addition to the difficulty of segmenting contaminated areas from CT scan images, these approaches also offer limited accuracy for identifying the virus. Accordingly, this paper addresses the effectiveness of using deep learning (DL) and image processing techniques, which serve to expand the dataset without the need for any augmentation strategies, and it also presents a novel approach for detecting COVID-19 virus infections in lung images, particularly the infection prediction issue. In our proposed method, to reveal the infection, the input images are first preprocessed using a threshold then resized to 128 × 128. After that, a density heat map tool is used for coloring the resized lung images. The three channels (red, green, and blue) are then separated from the colored image and are further preprocessed through image inverse and histogram equalization, and are subsequently fed, in independent directions, into three separate U-Nets with the same architecture for segmentation. Finally, the segmentation results are combined and run through a convolution layer one by one to get the detection. Several evaluation metrics using the CT scan dataset were used to measure the performance of the proposed approach in comparison with other state-of-the-art techniques in terms of accuracy, sensitivity, precision, and the dice coefficient. The experimental results of the proposed approach reached 99.71%, 0.83, 0.87, and 0.85, respectively. These results show that coloring the CT scan images dataset and then dividing each image into its RGB image channels can enhance the COVID-19 detection, and it also increases the U-Net power in the segmentation when merging the channel segmentation results. In comparison to other existing segmentation techniques employing bigger 512 × 512 images, this study is one of the few that can rapidly and correctly detect the COVID-19 virus with high accuracy on smaller 128 × 128 images using the metrics of accuracy, sensitivity, precision, and dice coefficient.

Time Effective Logistics of Hybrid Image Processing Course and Laboratory

In “pre-COVID 19” time, Braude Academic College of Engineering students enrolled in the course “Image Processing”, visited frontal lectures, and, additionally, participated in the laboratories provided in the class equipped with computers. During the laboratories, students (organized in small groups – preferably by pairs) were asked to implement several image-processing algorithms explained during frontal lectures. In the frames of this course, C, C++, and C# languages are used to write code. Specifically, to write the code, students used computers with Windows 10 and Visual Studio installed. Additionally, students were asked to prepare a PowerPoint presentation, in which they were asked to analyze the results obtained. During the in-campus laboratory, students were free to ask for help, and, in case of need, the educator provided relevant explanations. When the report was ready, students demonstrated the presentation and the working code to the educator. The grading policy was that if the presentation was good enough, and if students reasonably answered the questions, they got a high grade. As a backup, students E-Mailed a presentation and the code by using a special format developed specifically for that course. Because of COVID-19 limitations, during three semesters logistics of the lectures and laboratories were changed, and, as lectures, as laboratories were provided online by using cloud services like ZOOM and Gmail. It so happens, that semester 2021-10 – 2022-03 was started as an online semester, but after three weeks, it became a hydride semester: lectures and laboratories were provided in-campus, but students had the right to stay at home and continue to use cloud services including ZOOM and Email. This change created a number of logistics problems, and, thus, some modifications were provided in an attempt to ensure fair and non-biased grading as for the students who were physically present during the lectures and laboratories, as for the students who participated remotely. In the frames of this course, each group of students prepared a set of assignment reports and two micro-project presentations. Additionally, students physically present in the class, participated in the short nonobligatory micro-exams. This paper discusses logistics decisions and their effect on the quality of the students’ micro exams, assignments reports, and presentations. Keywords: hybrid laboratory, STEM, image processing

Hybrid image processing model: a base for smart emergency applications

Hybrid image processing model: a base for smart emergency applications

Deep learning based river surface ice quantification using a distant and oblique-viewed public camera

Long-term monitoring of surface ice concentration and ice pan properties are of great importance for understanding river freeze-up processes but current data are limited due to challenging winter environments. This study investigated the use of oblique images of river surfaces captured at long focus distances for long-term monitoring of surface ice conditions. Image data from a public camera mounted on a building roof top captured during five freeze-up seasons was used. A deep learning based hybrid image processing algorithm consisting of image classification, rectification, segmentation and extraction of river ice properties was developed to compute surface ice concentrations as well as ice pan size and shape properties. The validity and accuracy of the image data and processing algorithms were evaluated. Time series of multi-year surface ice concentrations as well as size distributions and shape properties of ice pans during freeze-up on the North Saskatchewan River are presented. A lognormal distribution was found to fit the ice pan size distributions for all years. Overall the size and shape of ice pans were relatively stable from year to year. The diameter of ice pans ranged from 0.55 m ∼ 15.03 m with a mean size of 1.82 m. The ice pans are generally elliptical shaped. The daily mean ice pan diameter varied from ∼1 m to ∼3 m. Properties of slushy and crusty ice pans were also estimated by visually separating image periods with dominant ice pan types and it was found that slushy ice pans were generally smaller and slightly less irregular compared to crusty ice pans. This study demonstrates that accurate long-term monitoring of river ice conditions as well as statistical properties of ice pans can be obtained using images captured by a distant and oblique-viewed camera that was not intentionally set up for ice research.

Automatic crack classification and segmentation on concrete bridge images using convolutional neural networks and hybrid image processing

Abstract Cracks are an indicator for a bridge’s structural health and functional failures. Crack detection is one of the major tasks needed to maintain the structural health and serviceability of a bridge. At present, the most commonly used crack detection technology is manual inspection, which has the disadvantages of being highly labor-intensive and time-consuming. In this paper, a crack detection method based on a convolutional neural network (CNN) is proposed. To automate quantitative measurements of an identified crack, hybrid image processing is proposed, as well. First, a dataset is compiled, including 12,000 cropped crack images and 19,500 cropped background images. Second, preprocessed images with the proposed method of Bilateral-Graying-Contrast (BGC) are fed into ResNet and a Visual Geometry Group Network (VGG) for training and testing. Finally, an automatic measurement system for bridge crack is developed which is not prone to weakened shooting conditions. The results demonstrate that ResNet achieves an accuracy of crack detection up to 97.44%, which is higher than VGG. Our crack measurement system significantly reduces the measurement error to 9.86% and can be assumed as a reliable method in the analysis of concrete bridge images.

Automated brain tumor detection of MRI image based on hybrid image processing techniques

Primary challenges are the identification, segmentation, and extraction of the afflicted area from the scanning of magnetic resonance. However, it is a time-consuming and tiresome for clinical specialists. In this paper, an automated brain tumor system is proposed. The proposed system employs hybrid image processing techniques such as contrast correction, histogram normalization, thresholding techniques, arithmetic, and morphological operations to quarantine nearby organs and other tissue from the brain for improving the localization of the affected region. At first, the skull stripping process is proposed to segregate the non-designated regions to extract the designated brain regions. Those resultant brain region images are further subjected to discover the brain tumor. The planned scheme is studied on the magnetic resonance (MR) images with the use of T1, T2, T1c, and fluid-attenuated inversion recovery (FLAIR). The proposed hybrid method employed. The results reveal that the proposed method is quite efficient to extract the tumor region. The accuracy rate for segmentation and separation of area of interest in brain tumor reached to 95%. Finally, the significance of the proposed procedure is confirmed using the real image clinical dataset got from ten patients were diagnosed as begin, malignant, and metastatic brain tumors in Al-Yarmouk and Baghdad teaching hospital in Baghdad, Iraq.

Automated Characterization of Catalytically Active Inclusion Body Production in Biotechnological Screening Systems.

We here propose an automated pipeline for the microscopy image-based characterization of catalytically active inclusion bodies (CatIBs), which includes a fully automatic experimental high-throughput workflow combined with a hybrid approach for multi-object microbial cell segmentation. For automated microscopy, a CatIB producer strain was cultivated in a microbioreactor from which samples were injected into a flow chamber. The flow chamber was fixed under a microscope and an integrated camera took a series of images per sample. To explore heterogeneity of CatIB development during the cultivation and track the size and quantity of CatIBs over time, a hybrid image processing pipeline approach was developed, which combines an ML-based detection of in-focus cells with model-based segmentation. The experimental setup in combination with an automated image analysis unlocks high-throughput screening of CatIB production, saving time and resources. Biotechnological relevance- CatIBs have wide application in synthetic chemistry and biocatalysis, but also could have future biomedical applications such as therapeutics. The proposed hybrid automatic image processing pipeline can be adjusted to treat comparable biological microorganisms, where fully data-driven ML-based segmentation approaches are not feasible due to the lack of training data. Our work is the first step towards image- based bioprocess control.

Determining Planetary Boundary Layer Height by Micro-pulse Lidar with Validation by UAV Measurements

ABSTRACT Planetary boundary layer height (PBLH) is often used to characterize the structure of the lower atmosphere. Aerosol lidar, a ground-based remote sensing method, provides the vertical distribution of aerosol at a high temporal resolution observation data, from which, the PBL structure and the position of the PBL top can be comprehensively studied. PBLH determination with lidar data depends primarily on the characteristic turbulent motions in the atmosphere and the geophysical location. However, lidar determination of PBLH over densely populated subtropical locations has rarely been discussed; thus, developing retrieval techniques suitable to these areas is necessary. In this study, four PBLH determination methods (Gradient, δ–threshold, Haar wavelet transform, and hybrid image processing) are applied to estimate the PBLH from lidar observations over an urban area in East Asia, and one—the Gradient method—relied on potential temperature measurements from an unmanned aerial vehicle (UAV) flights to validate our results. Our results indicate that a combination of the gradient method and δ-threshold method can provide better results, in terms of diurnal pattern, than using either method individually. Furthermore, the Haar wavelet and the Hybrid image processing can detect the PBL development comparably well, but both methods are dependent on their initial conditions and optimized algorithm settings. In addition, the accompanying UAV observations are conclusively shown to have a high degree of efficacy for validating the lidar data. This research highlights that a combination of PBLH determination methods can better describe the PBLH evolution throughout a day in some cases, while in others less common determination methods are proving useful, and a suite of retrieval methods should still be explored for precisely mapping the PBL in densely populated subtropical areas.

Local Features-Based Watermarking for Image Security in Social Media

The last decade shows an explosion of using social media, which raises several challenges related to the security of personal files including images. These challenges include modifying, illegal copying, identity fraud, copyright protection and ownership of images. Traditional digital watermarking techniques embed digital information inside another digital information without affecting the visual quality for security purposes. In this paper, we propose a hybrid digital watermarking and image processing approach to improve the image security level. Specifically, variants of the widely used Least-Significant Bit (LSB) watermarking technique are merged with a blob detection algorithm to embed information into the boundary pixels of the largest blob of a digital image. The proposed algorithms are tested using several experiments and techniques, which are followed by uploading the watermarked images into a social media site to evaluate the probability of extracting the embedding watermarks. The results show that the proposed approaches outperform the traditional LSB algorithm in terms of time, evaluation criteria and the percentage of pixels that have changed.

High-resolution 3D light-field imaging.

.Significance: High-speed 3D imaging methods have been playing crucial roles in many biological discoveries.Aim: We present a hybrid light-field imaging system and image processing algorithm that can visualize high-speed biological events.Approach: The hybrid light-field imaging system uses the selective plane optical illumination, which simultaneously records a high-resolution 2D image and a low-resolution 4D light-field image. The high-resolution 4D light-field image is obtained by applying the hybrid algorithm derived from the deconvolution and phase retrieval methods.Results: High-resolution 3D imaging at a speed of 100-s volumes per second over an imaging field of in the , , and axis, respectively, is achieved with a 2.5 times enhancement in lateral resolution over the entire imaging field compared with standard light-field systems. In comparison to the deconvolution algorithm, the hybrid algorithm addresses the artifact issue at the focal plane and reduces the computation time by a factor of 4.Conclusions: The new hybrid light-field imaging method realizes high-resolution and ultrafast 3D imaging with a compact setup and simple algorithm, which may help discover important applications in biophotonics to visualize high-speed biological events.

Automated hemangioma detection using Otsu based binarized Kaze features

This study aims to detect liver hemangioma on CT images by using hybrid image processing methods as well as binarized histogram of gradients based Kaze feature extraction. Using hybrid strategies, automatic hemangioma detector design is the state of art of this study. Our study helps doctors to detect the solid liver masses. Proposed algorithm includes detection of hemangioma using Otsu auto-threshold based Histogram of Gradients (HOG) and Kaze feature extraction implementation. 48 liver CT images, 28 of which are hemangiomas and 20 of which are healthy liver images, are used as the dataset. CT images are obtained by the Department of the Radiology at Firat University. Presented work was implemented to 48-CT images and 91,66% accuracy was achieved for different shaped and sized hemangiomas. These results show that the developed algorithm could ease the process of detecting liver masses for radiologist and doctors could evaluate their findings easily.

Convolution based hybrid image processing technique for microscopic images of etch-pits in Nuclear Track Detectors

A novel image processing technique based on convolution is developed for analyzing the etch-pit images in Nuclear Track Detectors (NTDs). The outcomes of the application of the proposed method on the different types of NTDs (e.g., CR-39, PET) containing etch-pit openings of different sizes and shapes (circular and elliptical) is presented. Promising results have been obtained for both identifying and counting the etch-pits in NTDs.

A hybrid image processing method for measuring 3D bubble distribution using digital inline holography

The paper presents a hybrid bubble hologram processing approach for measuring the size and 3D distribution of bubbles over a wide range of size and shape. The proposed method consists of five major steps, including image enhancement, digital reconstruction, small bubble segmentation, large bubble/cluster segmentation, and post-processing. Two different segmentation approaches are proposed to extract the size and the location of bubbles in different size ranges from the 3D reconstructed optical field. Specifically, a small bubble is segmented based on the presence of the prominent intensity minimum in its longitudinal intensity profile, and its depth is determined by the location of the minimum. In contrast, a large bubble/cluster is segmented using a modified watershed segmentation algorithm and its depth is measured through a wavelet-based focus metric. Our processing approach also determines the inclination angle of a large bubble with respect to the hologram recording plane based on the depth variation along its edge on the plane. The accuracy of our processing approach on the measurements of object size and 3D distributions are assessed through synthetic bubble holograms and oil droplet holograms from an experiment separately. In addition, we evaluate the ability of this algorithm to estimate the bubble inclination with respect to the hologram recording plane through measuring a 3D-printed physical target of pillars with different inclination angles. The holographic measurement technique is further implemented to capture the fluctuation of instantaneous gas leakage rate from a ventilated supercavity generated in a water tunnel experiment. Overall, our paper introduces an inexpensive and compact solution for high resolution characterization of bubbles and other particles in multiphase flows from a broad range of applications.

A soft-computing based hybrid tool to extract the tumour section from brain MRI

In recent days, examination of medical images had been carried out using a number of image processing tools, specifically implemented for such purposes. This proposed work is based on a hybrid image processing technique focuses on extracting the tumour section from the brain Magnetic-Resonance-Image (MRI) recorded with various MR sequences. The proposed technique aims to identify the best possible image processing methodology for brain MRI investigation and subsequently to extract the tumour section for clinical setting. For exploring the proposed technique, most popular Radiopedia database, BraTS 2015 dataset is primarily considered for the assessment and later, real time clinical brain MRI slices are investigated. The proposed work implements Shannon Entropy (SE) objective function assisted with Social Group Optimization (SGO) algorithm to enhance the image. The results produced by SGO are compared with the other heuristic approaches like the Firefly-Algorithm (FA), Bat-Algorithm (BA) and Differential-Evolution (DE). Then Distance-Regularized-Level-Set (DRLS) segmentation technique is performed for extracting the tumour part from the enhanced slices. Further, the segmentation comparison of DRLS against traditional Active-Contour (AC) is also adopted for the evaluation. This integrated approach offers better picture-similarity-measures (PSM) compared with the alternatives.

Hybrid image processing approach for autonomous crack area detection and tracking using local digital image correlation results applied to single-fiber interfacial debonding

Local digital image correlation is a popular method for accurate full field displacement measurements. However, the technique struggles at autonomously tracking emerging and propagating cracks. We proposed a hybrid approach which utilizes image processing techniques in combination with local digital image correlation to autonomously monitor cracks in a mechanically loaded specimen. Our approach can extract and track crack surfaces and provide a volume-based visualization of the crack growth. This approach was applied to single-fiber composite experimental results with interfacial debonding from the literature. Results quantitatively show that strong interfacial fiber/matrix bonding leads to slower interfacial crack growth, delays interfacial crack growth in the matrix, requires higher loadings for crack growth and shows a specific crack path distinct from the one obtained for weak interfaces. The approach was also validated against a manual approach where a domain scientist extracts a crack using a polygon extraction tool. The method can be used on any local digital image correlation results involving damage observations.

Hybrid image processing approach for autonomous crack area detection and tracking using local digital image correlation results applied to single-fiber interfacial debonding

Hybrid image processing approach for autonomous crack area detection and tracking using local digital image correlation results applied to single-fiber interfacial debonding