Top-hat Transform Research Articles

WATER BODIES EXTRACTION USING MATHEMATICAL MORPHOLOGY

The management of water resources is vital for maintaining the world’s ecosystems. Conventional methods of extracting water bodies remain very limited due to the complexity of the implementation. This leads to a reduction in the extraction precision. Our main objec- tive is to improve the detection of water bodies. We tested the accuracy of our method on the Sentinel-2 Dataset that contains images with different complexity levels and heterogeneous structures like shadows, roads, buildings, etc. This article presents an original method that implements the idea of separating the three-component RGB image matrices and then processing only the green matrix because it contains all water bodies with high precision. Our method is based mainly on the mathematical morphology. Firstly, we propose a simple and fast binary algorithm to detect the maximum of water bodies existing in the images. This step was carried out using the Hit-or-Miss Transform. The second step exploits applying the Top-Hat Transform to refine the segmentation result. By comparing our method with several currently used methods, we notice that our method improves the quality of segmentation and gives excellent results, which exceed 95% for all the metrics used to calculate the classification quality in the purview of remote sensing. The error obtained with our method remains less than 1 %. We can affirm that our method is very suitable for detecting bodies of water compared to all current methods.

Advanced enhancement technique for infrared images of wind turbine blades utilizing adaptive difference multi-scale top-hat transformation

Enhancing infrared images is essential for detecting wind turbine blades using infrared technology. This paper introduces an Infrared Image Enhancement Method based on Adaptive Iterative Cutoff Threshold Difference Multi-Scale Top-Hat Transformation (AICT-DMTH) to address the challenge of low image clarity in infrared detection. The method involves performing a black-white difference top-hat transformation by utilizing structural elements of varying scales for dilation and erosion. Additionally, an iterative threshold method is applied to extract more detailed image features, followed by setting a cutoff constant to determine the final scale of the structural element. The effectiveness of the proposed method is evaluated both qualitatively and quantitatively, with infrared images from laboratory and wind farm settings enhanced and compared against existing methods. The experimental results indicate that the proposed method significantly improves the clarity of infrared images, demonstrating robustness in enhancing images from various environments.

Segmentation of retinal microaneurysms in fluorescein fundus angiography images by a novel three-step model.

Microaneurysms serve as early signs of diabetic retinopathy, and their accurate detection is critical for effective treatment. Due to their low contrast and similarity to retinal vessels, distinguishing microaneurysms from background noise and retinal vessels in fluorescein fundus angiography (FFA) images poses a significant challenge. We present a model for automatic detection of microaneurysms. FFA images were pre-processed using Top-hat transformation, Gray-stretching, and Gaussian filter techniques to eliminate noise. The candidate microaneurysms were coarsely segmented using an improved matched filter algorithm. Real microaneurysms were segmented by a morphological strategy. To evaluate the segmentation performance, our proposed model was compared against other models, including Otsu's method, Region Growing, Global Threshold, Matched Filter, Fuzzy c-means, and K-means, using both self-constructed and publicly available datasets. Performance metrics such as accuracy, sensitivity, specificity, positive predictive value, and intersection-over-union were calculated. The proposed model outperforms other models in terms of accuracy, sensitivity, specificity, positive predictive value, and intersection-over-union. The segmentation results obtained with our model closely align with benchmark standard. Our model demonstrates significant advantages for microaneurysm segmentation in FFA images and holds promise for clinical application in the diagnosis of diabetic retinopathy. The proposed model offers a robust and accurate approach to microaneurysm detection, outperforming existing methods and demonstrating potential for clinical application in the effective treatment of diabetic retinopathy.

Maritime Infrared Small Target Detection Based on the Appearance Stable Isotropy Measure in Heavy Sea Clutter Environments.

Infrared small target detection plays a crucial role in maritime security. However, detecting small targets within heavy sea clutter environments remains challenging. Existing methods often fail to deliver satisfactory performance in the presence of substantial clutter interference. This paper analyzes the spatial-temporal appearance characteristics of small targets and sea clutter. Based on this analysis, we propose a novel detection method based on the appearance stable isotropy measure (ASIM). First, the original images are processed using the Top-Hat transformation to obtain the salient regions. Next, a preliminary threshold operation is employed to extract the candidate targets from these salient regions, forming a candidate target array image. Third, to distinguish between small targets and sea clutter, we introduce two characteristics: the gradient histogram equalization measure (GHEM) and the local optical flow consistency measure (LOFCM). GHEM evaluates the isotropy of the candidate targets by examining their gradient histogram equalization, while LOFCM assesses their appearance stability based on local optical flow consistency. To effectively combine the complementary information provided by GHEM and LOFCM, we propose ASIM as a fusion characteristic, which can effectively enhance the real target. Finally, a threshold operation is applied to determine the final targets. Experimental results demonstrate that our proposed method exhibits superior comprehensive performance compared to baseline methods.

Robust small infrared target detection using weighted adaptive ring top-hat transformation

Complex background in infrared images often challenges the accurate detection of small targets. To address this problem, we propose a weighted adaptive ring top-hat transformation (WARTH) for extracting infrared small targets in complex backgrounds. The method utilizes an adaptive ring-shaped structural element (SE) and a target awareness indicator to effectively measure local and global feature information to detect small targets while minimizing false alarms accurately. Firstly, the difference-of-structure tensors (DoST) is designed, and the positive smallest eigenvalue of DoST (PSEDoST) is computed to construct the adaptive ring-shaped SE that captures local feature information for background estimation. Secondly, the image is converted into the Fourier phase spectrum, and a two-stage sliding window filtering technique is designed to generate the target awareness indicator that perceives global feature information of small targets. Finally, the WARTH is defined by fusing the above two measurements, which can further eliminate false alarms and improve the robustness of target detection. The experimental results demonstrate that the WARTH is superior to several advanced methods in terms of false alarm reduction and small target detection in complex backgrounds.

An Improved Method for Reconstruction and Enhancing Dark Images based on CLAHE

The obtained images are frequently flawed because of a variety of environmen- tal issues, particularly at night, such as inside illumination, cloudy weather, etc. The dark image has a compressed dynamic range that can be improved in order to see the finer details. This research effort proposes an improved lighting reflection model-based technique for improving extremely dim images. This improved method relies on reconstruction carried out via morphological processing with Top-hat transformation and Contrast Limited Adaptive His- togram Equalization (CLAHE). The HSV colour scheme is used to perceive the image, and the V component is estimated. The inverse of the intensity component (V) is calculated after normalising the intensity component. The negative image is then subjected to the CLAHE algorithm. The final step is to apply multiscale image enhancement to the obtained image. The brightness component of an image is adaptively adjusted via gamma enhancement. The outcomes of two gamma-enhanced photographs with various gamma values are produced after gamma enhancement. The significant information that can be used for image fusion is extracted from these images using principal com- ponent analysis. The weight value is adaptively determined during the PCA- based image fusion employing morphological Top-hat modification to enhance the image quality and highlight the erratic background pixels. The suggested technique emphasises edge and structural preservation while enhancing detail in extremely dim photos. Results from experimental validations demonstrate that the suggested strategy outperforms the current method in terms of both qualitative and quantitative measures.

FRCNN-Based Reinforcement Learning for Real-Time Vehicle Detection, Tracking and Geolocation from UAS

In the last few years, uncrewed aerial systems (UASs) have been broadly employed for many applications including urban traffic monitoring. However, in the detection, tracking, and geolocation of moving vehicles using UAVs there are problems to be encountered such as low-accuracy sensors, complex scenes, small object sizes, and motion-induced noises. To address these problems, this study presents an intelligent, self-optimised, real-time framework for automated vehicle detection, tracking, and geolocation in UAV-acquired images which enlist detection, location, and tracking features to improve the final decision. The noise is initially reduced by applying the proposed adaptive filtering, which makes the detection algorithm more versatile. Thereafter, in the detection step, top-hat and bottom-hat transformations are used, assisted by the Overlapped Segmentation-Based Morphological Operation (OSBMO). Following the detection phase, the background regions are obliterated through an analysis of the motion feature points of the obtained object regions using a method that is a conjugation between the Kanade–Lucas–Tomasi (KLT) trackers and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering. The procured object features are clustered into separate objects on the basis of their motion characteristics. Finally, the vehicle labels are designated to their corresponding cluster trajectories by employing an efficient reinforcement connecting algorithm. The policy-making possibilities of the reinforcement connecting algorithm are evaluated. The Fast Regional Convolutional Neural Network (Fast-RCNN) is designed and trained on a small collection of samples, then utilised for removing the wrong targets. The proposed framework was tested on videos acquired through various scenarios. The methodology illustrates its capacity through the automatic supervision of target vehicles in real-world trials, which demonstrates its potential applications in intelligent transport systems and other surveillance applications.

Spatiotemporal distribution of seamount volume along the Kyushu-Palau Ridge: Implications for rejuvenated volcanism

• Accurate quantification of seamount volcanism reveals multiphase volcanism along the Kyushu–Palau Ridge. • The proximity of Pre-Oligocene lithospheric weak zones to high concentrations of seamount volume indicate tectonic inheritance facilitated magma migration. • Rejuvenated volcanism related to the propagated back-arc spreading during Oligocene contributed to the development of the Kyushu-Palau Ridge. The Kyushu-Palau Ridge (KPR) is a remnant arc that initially formed with the subduction of the Pacific plate beneath the West Philippine Sea. The KPR split from the proto-Izu-Bonin-Mariana (IBM) arc with the back-arc spreading at ∼ 30 Ma. Even though most of the seamounts have been dated, the factors that drive the volcanic arc evolution along the KPR remain unknown. In this study, we quantify the spatiotemporal distribution of the seamount volume along the KPR, representing a quantitative indicator of erupted volcanism. A spatial filtering method based on the White Top-Hat Transform is used to identify seamounts from the bathymetry. Combining seismic data interpretation and gravity data inversion, we estimate the seamount volume distribution along the KPR. Results show that high concentrations of the seamount volume are in proximity to pre-Oligocene lithospheric weak zones, indicating that tectonic inheritance has facilitated magma migration during the early-stage volcanic arc generation. Subsequently, the younger than 30 Ma age of the majority of the seamounts suggests a late-stage rejuvenated volcanism in the Oligocene. In addition, the spatiotemporal variations of the seamount volume in the northern and central segments are synchronous with the propagated spreading of the Perce Vela and Shikoku basins, further indicating that the rejuvenated volcanism was driven by the propagated back-arc spreading. Rejuvenated volcanism can thus be an important contributive factor to remnant volcanic arc formation.

Comparison of Vehicle License Plate Detection Algorithms and LP Character Segmentation and Recognition using Image Processing

In the last couple of decades, the number of vehicles has increased drastically, consequently, it is becoming difficult to keep track of each vehicle for purpose of law enforcement and traffic management. License Plate Detection is used increasingly nowadays for the same. The system performing the task of License Plate detection is known as the LPR system which generally consists of three steps: Detection of the License plate, Segmentation of License plate characters, and Recognition of the characters of the License Plate (LP). But in real-world scenarios, the various lighting conditions, camera angle, and rotation degrades the accuracy of License Plate region detection, which in turn causes inaccurate segmentation and recognition of the license plate characters hence leading to low accuracy of the LPR systems. Therefore, it is vital to consider the most promising algorithm or technique for LP detection. In this paper, we will be analyzing and comparing five different methods for license plate detection: Morphological reconstruction, Sobel Operator, Top Hat Transform, Histogram processing, and Canny Edge detection. We will be experimentally applying these techniques on real-time captured vehicle images, using the Bounding Box algorithm for character segmentation, performing license plate character recognition using Template matching, and subsequentially evaluating and demonstrating the LPR system that promises the most accurate and efficient results.

A graph-based top-down visual attention model for lockwire detection via multiscale top-hat transformation

As a locking device, lockwire is widely used in industrial fields that produces high levels of vibration. Lockwire detection is vital for ensuring mechanical stability. However, the existing methods are inapplicable to detect all types of small-size lockwires in complex backgrounds. In this paper, we construct a graph-based top-down visual attention model via the multiscale top-hat transformation to pick out lockwires from various complex backgrounds. Since lockwires typically exhibit separated bright spot-like structures at different scales in images, we firstly construct multiscale anisotropic Gaussian structuring elements to obtain the top-hat feature map. Based on a novel connectivity function, an undirected graph is then constructed. Afterwards, we propose an improved shortest path algorithm to remove prominent complex background components and extract lockwire candidates by minimizing the redefined cost function. Taking full advantages of imaging characteristics of lockwires, we design three saliency metrics to strengthen the saliency of lockwires while weakening backgrounds. Finally, a global top-down saliency map is produced to detect lockwires from complex backgrounds by combining three saliency maps. The experimental results show that our proposed method achieves superior performance compared to state-of-the-art methods.

Intelligent Robotic Welding Based on a Computer Vision Technology Approach

Robots have become an essential part of modern industries in welding departments to increase the accuracy and rate of production. The intelligent detection of welding line edges to start the weld in a proper position is very important. This work introduces a new approach using image processing to detect welding lines by tracking the edges of plates according to the required speed by three degrees of a freedom robotic arm. The two different algorithms achieved in the developed approach are the edge detection and top-hat transformation. An adaptive neuro-fuzzy inference system ANFIS was used to choose the best forward and inverse kinematics of the robot. MIG welding at the end-effector was applied as a tool in this system, and the weld was completed according to the required working conditions and performance. The parts of the system work with compatible and consistent performances, with acceptable accuracy for tracking the line of the welding path.

Infrared bi-polar small target detection via novel ring morphological transformation

Despite the progress of the infrared small target detection algorithms in recent years, there are two unresolved challenges in small target detection remain. (1) fast and robust infrared small target detection is still a challenge, and (2) existing algorithms are less effective in detecting bi-polar targets. To solve these problems, we propose a small target detection algorithm based on a novel ring morphological transformation. In the proposed algorithm, we reconstruct the structural elements in four directions based on the ring top-hat transformation and the relationship between the target and circularity. Then, we organically combine the open and closed operations in the four directions to make the algorithm capable of detecting bi-polar targets. The final results are obtained by fusing the results of the open and closed operations in the four directions. Extensive experiments on six datasets demonstrate the effectiveness and robustness of the proposed algorithm. Moreover, the low complexity makes the proposed algorithm satisfy the purpose of real-time detection.

Automatic microseismic events detection using morphological multiscale top-hat transformation

The occurrence of microseismic is not random but is related to the physical properties of the underground medium. Due to the low intensity and the influence of noise, microseismic eventually lead to poor signal-to-noise ratio. We proposed a method for automatic detection of microseismic events by adoption of multiscale top-hat transformation. The method is based on the difference between the signal and noise in the multiscale top-hat transform section and achieves the detection on a specific section. The microseismic data are decomposed into different scales by multiscale morphology top-hat transformation firstly. Then the potential microseismic events could be detected by picking up the peak value in the multiscale top-hat section, and the characteristic profile obtains the start point with a specific threshold value. Finally, the synthetic data experiences demonstrate the advantages of this method under strong and weak noisy conditions, and the filed data example also shows its reliability and adaptability.

A Combined Approach to Infrared Small-Target Detection with the Alternating Direction Method of Multipliers and an Improved Top-Hat Transformation.

In infrared small target detection, the infrared patch image (IPI)-model-based methods produce better results than other popular approaches (such as max-mean, top-hat, and human visual system) but in some extreme cases it suffers from long processing times and inconsistent performance. In order to overcome these issues, we propose a novel approach of dividing the traditional target detection process into two steps: suppression of background noise and elimination of clutter. The workflow consists of four steps: after importing the images, the second step applies the alternating direction multiplier method to preliminarily remove the background. Comparatively to the IPI model, this step does not require sliding patches, resulting in a significant reduction in processing time. To eliminate residual noise and clutter, the interim results from morphological filtering are then processed in step 3 through an improved new top-hat transformation, using a threefold structuring element. The final step is thresholding segmentation, which uses an adaptive threshold algorithm. Compared with IPI and the new top-hat methods, as well as some other widely used methods, our approach was able to detect infrared targets more efficiently (90% less computational time) and consistently (no sudden performance drop).

Improved one-dimensional dilation-based top-hat algorithm for star segmentation under complicated background conditions.

The white top-hat transformation has been widely used in small bright target extraction. It usually applies an erosion operation to remove the target and then a dilation operation to recover the intensity of the processed image. A bright target will be extracted by subtracting the opening operation (erosion followed by dilation) from the raw image. The drawback of this method is that its denoising ability is poor because the estimated background threshold by an opening operation is smaller than the raw image. This study puts forward the viewpoint that by use of a proposed one-dimensional (1D) symmetrical line-shaped structuring element a bright target can also be removed by the dilation operation. Consequently, the white top-hat transformation can be implemented by subtracting only the dilation operation from the raw image. To the best knowledge of the authors, it is the first time to use this method to achieve the top-hat transformation. The simulation experiment shows that the proposed 1D top-hat algorithm has excellent performance in denoising ability and detection ability. Moreover, real night experiments demonstrate that our proposed algorithm can work reliably under both complicated background conditions and good weather conditions. It is noticeable that the performance of computational efficiency and resource consumption have been considerably improved because a 1D structuring element is employed and the erosion operation is not included.

When Infrared Small Target Detection Meets Tensor Ring Decomposition: A Multiscale Morphological Framework

Detecting the small targets from a heterogeneous background in an infrared image is a challenging problem, which has received extensive attention. In this article, we propose a method in terms of tensor ring (TR) decomposition and nonlinear multiscale morphological top-hat transformation for infrared small target detection (ISTD). First, a tensor model with prior knowledge is constructed for extracting the structural features of multiple infrared images. Then, the problem of small target detection is converted into a problem of minimizing the tensor rank with TR. Based on the TR decomposition model, we introduce the top-hat regularization into our model with multiple structural elements of different size to perform morphological operations. The corresponding morphological model exploits a more accurate ring top-hat regularization expression through adaptive nonlinear combination for the ISTD problem. Finally, the optimization of the model is realized by the closed solution given by the alternating direction method of multipliers algorithm. In order to verify the superior performance of our method, our method is compared with a number of advanced detection models. By analyzing the results of comparison experiments, the detection accuracy and precision of our model in the detection of small infrared targets have been improved. Even in complex background conditions, our model also maintain a good robustness.

Contrast enhancement for improved blood vessels retinal segmentation using top-hat transformation and otsu thresholding

Diabetic Retinopathy is a effect of diabetes. It results abnormalities in the retinal blood vessels. The abnormalities can cause blurry vision and blindness. Automatic retinal blood vessels segmentation on retinal image can detect abnormalities in these blood vessels, actually resulting in faster and more accurate segmentation results. The paper proposed an automatic blood vessel segmentation method that combined Otsu Thresholding with image enhancement techniques. In image enhancement, it combined CLAHE with Top-hat transformation to improve image quality. The study used DRIVE dataset that provided retinal image data. The image data in dataset was generated by the fundus camera. The CLAHE and Top-hat transformation methods were applied to rise the contrast and reduce noise on the image. The images that had good quality could help the segmentation process to find blood vessels in retinal images appropriately by a computer. It improved the performance of the segmentation method for detecting blood vessels in retinal image. Otsu Thresholding was used to segment blood vessel pixels and other pixels as background by local threshold. To evaluation performance of the proposed method, the study has been measured accuracy, sensitivity, and specificity. The DRIVE dataset's study results showed that the averages of accuracy, sensitivity, and specificity values were 94.7%, 72.28%, and 96.87%, respectively. It indicated that the proposed method was successful and well to work on blood vessels segmentation retinal images especially for thick blood vessels.

Entropy-Driven Morphological Top-Hat Transformation for Infrared Small Target Detection

Infrared small target detection is a key technique in an infrared system. In the past decade, many methods have concentrated on traditional top-hat transformation, which relies on the hand-crafted shape and value of structural elements. However, these methods are inevitably challenged by the following two aspects: first, the structural elements cannot suppress heavy clutter because the construction of structural elements is always according to the prior information of the target and unable to consider the feature of clutter. Second, adaptively extracting sufficient local feature information for background suppression is hard for the structural element. In this article, we propose an entropy-driven top-hat transformation with guided filter kernel for considering the features of both the clutters and background. First, we propose an entropy-driven top-hat transformation method with our proposed local mean entropy, which can be used to suppress clutter according to the local complex degree of clutter. Then, an adaptive structural element based on a guided filter kernel is further exploited to capture the local feature information of image for background suppression. Finally, an adaptive threshold is combined with our algorithm to achieve target detection in image sequences. The experimental results show that the proposed algorithm is not only robust for suppressing different kinds of backgrounds but can also obtain a higher value of the signal-to-clutter ratio gain and detection accuracy compared with some popular traditional baseline methods and related top-hat methods.

Image Pre-processing techniques comparison : COVID-19 detection through Chest X-Rays via Deep Learning

The COVID-19 pandemic had a particularly devastating effect, spreading rapidly over the world and infecting about 36 million individuals. Chest radiography is a critical component that aids in the early detection of a variety of diseases. With the spread of the pandemic, training Convolutional Neural Networks (CNN) to detect and identify COVID-19 from chest X-rays is becoming more popular. However, there are few publicly available and medically validated datasets for COVID-19 infected chest X-Rays, resulting in the model failing to generalize successfully. It is critical to pre-process and enrich the data used to train the model in order to achieve this aim. Global Histogram Equalization (GHE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Top Bottom Hat Transform are some of the pre-processing techniques available. In this study, we examine and compare all of these pre-processing methods in order to determine which is best for building a CNN model that can accurately classify an image as infected with COVID-19 or Viral Pneumonia.

Automated Segmentation of Mass Regions in DBT Images Using a Dilated DCNN Approach.

To overcome the limitations of conventional breast screening methods based on digital mammography, a quasi-3D imaging technique, digital breast tomosynthesis (DBT) has been developed in the field of breast cancer screening in recent years. In this work, a computer-aided architecture for mass regions segmentation in DBT images using a dilated deep convolutional neural network (DCNN) is developed. First, to improve the low contrast of breast tumour candidate regions and depress the background tissue noise in the DBT image effectively, the constraint matrix is established after top-hat transformation and multiplied with the DBT image. Second, input image patches are generated, and the data augmentation technique is performed to create the training data set for training a dilated DCNN architecture. Then the mass regions in DBT images are preliminarily segmented; each pixel is divided into two different kinds of labels. Finally, the postprocessing procedure removes all false-positives regions with less than 50 voxels. The final segmentation results are obtained by smoothing the boundaries of the mass regions with a median filter. The testing accuracy (ACC), sensitivity (SEN), and the area under the receiver operating curve (AUC) are adopted as the evaluation metrics, and the ACC, SEN, as well as AUC are 86.3%, 85.6%, and 0.852 for segmenting the mass regions in DBT images on the entire data set, respectively. The experimental results indicate that our proposed approach achieves promising results compared with other classical CAD-based frameworks.