Blob Detection Research Articles

Atomic force microscopy for quantitative understanding of peptide-induced lipid bilayer remodeling.

A number of peptides are known to bind lipid bilayer membranes and cause these natural barriers to leak in an uncontrolled manner. Though membrane permeabilizing peptides play critical roles in cellular activity and may have promising future applications in the therapeutic arena, significant questions remain about their mechanisms of action. The atomic force microscope (AFM) is a single molecule imaging tool capable of addressing lipid bilayers in near-native fluid conditions. The apparatus complements traditional assays by providing local topographic maps of bilayer remodeling induced by membrane permeabilizing peptides. The information garnered from the AFM includes direct visualization and statistical analyses of distinct bilayer remodeling modes such as highly localized pore-like voids in the bilayer and dispersed thinned membrane regions. Colocalization of distinct remodeling modes can be studied. Here we examine recent work in the field and outline methods used to achieve precise AFM image data. Experimental challenges and common pitfalls are discussed as well as techniques for unbiased analysis including the Hessian blob detection algorithm, bootstrapping, and the Bayesian information criterion. When coupled with robust statistical analyses, high precision AFM data is poised to advance understanding of an important family of peptides that cause poration of membrane bilayers.

Penghitungan Objek Berdasarkan Berdasarkan Jenis Kendaraan Bermotor pada CCTV Lalu Lintas Berbasis Pengolahan Citra Digital Menggunakan Metode Background Subtraction dan Blob Detection

In the road traffic space which is often encountered by passing traffic type of vehicle. To find out the traffic conditions that are needed to calculate vehicle traffic, such as using counting or recording CCTV video. This continues the long and long process that was completed on the error data and the slow pace of traffic engineering decisions. This method is difficult to do in full because of the limited number of counters. This can be done by involving digital processing and CCTV video to be able to classify and transfer vehicle type objects. There are several methods for sharing object imagery, such as SIFT, edge detection and Monte Carlo. This research tries to use the Background Substraction and Blob Detection methods because of its superiority in determining objects and backgrounds and being able to maintain moving objects as well as analyzing screen area calculations. The results of testing with this method obtained the MSE value at the threshold of 100 and 3x3 kernel filter with a pixel area of motorcycle 34-63 pixel-X, 67-155 pixel-Y and cars 73-200 pixel-X, 79-307 pixel-Y and bus / truck 130-128 pixel-X, 305-376 pixel-Y. On evaluation, use the confusion matrix obtained in the morning with an average total of 92% and at night with a total average of 73%. It can be concluded by using CCTV installation parameters and the method used can yields higher accuracy in the morning than at night with the weakness of compiling objects that can make it easier to make objects and test the night to obtain light from vehicle lights generated as vehicle objects the flight.

UAV-BASED THERMAL ANOMALY DETECTION FOR DISTRIBUTED HEATING NETWORKS

Abstract. District Heating Systems (DHS) distribute heat in terms of hot water or steam. Loss of media (water or steam), and thus energy, is expensive and has a negative impact on the environment. It is therefore of great interest to develop techniques to detect and localize potential leakages fast and cost-effectively. To avoid interference with the operating process of a DHS, airborne thermography comes into place. The use of Unmanned Aerial Vehicles (UAV) as a flexible and low-cost platform equipped with a Thermal InfraRed (TIR) camera is a promising alternative to a conventional manned flight.This paper describes a method for automatic thermal anomaly detection of a DHS. Thermal data acquisition using a UAV is followed by photogrammetric processing of the TIR images. In this way, a thermal orthophoto is produced. The next step is an identification of anomalies by means of image analysis. We apply the Laplacian of Gaussian (LoG) blob detector to find high temperature regions in areas of interest of a thermal orthomosaic. This area of interest is defined around the DHS position in the images as defined in a Geographic Information System. Finally, segmentation and classification are employed to reduce false alarms and localize thermal anomalies. An experimental evaluation using real-world data is presented, showing that the developed method deliverers promising results.

Comparison of edge turbulence characteristics between DIII-D and C-Mod simulations with XGC1

The physical processes taking place at the separatrix and scrape-off layer regions are crucial for the operation of tokamaks as they govern the interaction of hot plasma with the vessel walls. Numerical modeling of the edge with state-of-the-art codes attempts to elucidate the complex interactions between neoclassical drifts, turbulence, poloidal, and parallel flows that control the physical set-up of the SOL region. Here, we present the post-processing analysis of simulation results from the gyrokinetic code XGC1, comparing and contrasting edge turbulence characteristics from a simulation of the DIII-D tokamak against a simulation of the Alcator C-Mod tokamak. We find that the equilibrium E × B flux across the separatrix has a similar poloidal pattern in both discharges, which can be explained by ∇B-drifts and trapped ion excursions. However, collisionality is noted to play a major role in the way that it prevents local charge accumulations from having more global effects in the C-Mod case. In both cases, turbulent electron heat flux is observed to be higher than the ion one and is possibly related to the need of electrons to maintain quasineutrality through the only channel available to them for exiting the confinement. By Fourier analysis, we identify turbulent frequencies and growth rates of the dominant mode in both simulations. In the case of C-Mod, these numbers point to the presence of a drift wave. In the DIII-D case, further linear simulations with the Gene code reveal a trapped electron mode. Furthermore, using a blob detection and tracking tool, we present the amplitude and size distributions of the blobs from both simulations. The amplitude distributions are in qualitative agreement with experimental observations, while the size distributions are consistent with the fact that most of the blobs are not connecting to the divertor plates and suggest that they are generated by the shearing of the turbulent modes.

Efficient Movement Compensation and Detection Algorithm using Blob Detection and Modified Kalman Filter

In various real time applications such as security and surveillance etc., detection of movement from video sequence is commonly used. In such applications, time required to detect the movement and its accuracy is very crucial. In this paper, an efficient motion compensation and detection algorithm using Blob detection and modified Kalman filter techniques is proposed. The method is mainly based on Kalman filtering technique which is modified to compensate and detect the unwanted movement caused by the camera. Also the shadow effect caused by the variation in the intensity of light and object is removed using thresholding technique. Accuracy of movement detection is improved by implementing the blob detection method. The experimental results obtained from the developed algorithm is compared with few methods existing in the literature for validation.

Tracking and visualization of the sensing area for a tethered laparoscopic gamma probe

PurposeIn surgical oncology, complete cancer resection and lymph node identification are challenging due to the lack of reliable intraoperative visualization. Recently, endoscopic radio-guided cancer resection has been introduced where a novel tethered laparoscopic gamma detector can be used to determine the location of tracer activity, which can complement preoperative nuclear imaging data and endoscopic imaging. However, these probes do not clearly indicate where on the tissue surface the activity originates, making localization of pathological sites difficult and increasing the mental workload of the surgeons. Therefore, a robust real-time gamma probe tracking system integrated with augmented reality is proposed.MethodsA dual-pattern marker has been attached to the gamma probe, which combines chessboard vertices and circular dots for higher detection accuracy. Both patterns are detected simultaneously based on blob detection and the pixel intensity-based vertices detector and used to estimate the pose of the probe. Temporal information is incorporated into the framework to reduce tracking failure. Furthermore, we utilized the 3D point cloud generated from structure from motion to find the intersection between the probe axis and the tissue surface. When presented as an augmented image, this can provide visual feedback to the surgeons.ResultsThe method has been validated with ground truth probe pose data generated using the OptiTrack system. When detecting the orientation of the pose using circular dots and chessboard dots alone, the mean error obtained is 0.05^{circ } and 0.06^{circ }, respectively. As for the translation, the mean error for each pattern is 1.78 mm and 1.81 mm. The detection limits for pitch, roll and yaw are 360^{circ }, 360^{circ } and 8^{circ }–82^{circ }cup 188^{circ }–352^{circ } .ConclusionThe performance evaluation results show that this dual-pattern marker can provide high detection rates, as well as more accurate pose estimation and a larger workspace than the previously proposed hybrid markers. The augmented reality will be used to provide visual feedback to the surgeons on the location of the affected lymph nodes or tumor.

A Versatile Machine Vision Algorithm for Real-Time Counting Manually Assembled Pieces.

The Industry 4.0 paradigm is based on transparency and co-operation and, hence, on monitoring and pervasive data collection. In highly standardized contexts, it is usually easy to gather data using available technologies, while, in complex environments, only very advanced and customizable technologies, such as Computer Vision, are intelligent enough to perform such monitoring tasks well. By the term “complex environment”, we especially refer to those contexts where human activity which cannot be fully standardized prevails. In this work, we present a Machine Vision algorithm which is able to effectively deal with human interactions inside a framed area. By exploiting inter-frame analysis, image pre-processing, binarization, morphological operations, and blob detection, our solution is able to count the pieces assembled by an operator using a real-time video input. The solution is compared with a more advanced Machine Learning-based custom object detector, which is taken as reference. The proposed solution demonstrates a very good performance in terms of Sensitivity, Specificity, and Accuracy when tested on a real situation in an Italian manufacturing firm. The value of our solution, compared with the reference object detector, is that it requires no training and is therefore extremely flexible, requiring only minor changes to the working parameters to translate to other objects, making it appropriate for plant-wide implementation.

Analysis of the Selection Impact of 2D Detectors on the Accuracy of Image-Based TLS Data Registration of Objects of Cultural Heritage and Interiors of Public Utilities

The aim of this article is to present the influence of detector selection for the image-based Terrestrial Laser Scanning (TLS) registration method. The presented results are the extended continuation of investigations presented in the article, ‘The Influence of the Cartographic Transformation of TLS Data on the Quality of the Automatic Registration’. In order to obtain the correct results of the TLS registration process, it is necessary to detect and match the correct tie points, which are evenly distributed across the entire area. Commonly, for TLS data registration manually or semi-manually corresponding points are detected. However, when large, complicated cultural heritage objects are investigated, it is sometimes impossible to place marked control points. The only possibility of resolving this problem is the use of image-based TLS data registration. One of the most important factors that influences the quality and ability to use it correctly, is accurate selection. For this purpose, the authors decided to test three blob detectors ASIFT, SURF, CenSurE, and two point detectors FAST and BRISK. The results indicated that selection depends on two factors: if the time required for data processing is not important, the ASIFT algorithm should be used, which allows for full registration, but if not, a combination of other algorithms with results supervision should be considered.

A study on the condition based maintenance evaluation system of smart plant device using convolutional neural network

There are two main causes of plant accidents: poor maintenance management and human error. In this study, we implemented a smart plant maintenance system that can reduce human errors based on the conditional based maintenance (CBM) concept. Unlike smart plant technology, which focuses on existing technology, we interviewed actual engineers and implemented a system reflecting their needs. First, we implemented three methods for learning defective images using convolutional neural network (CNN) and found that blob detection processing improves learning accuracy. Second, the fitness for service API (FFS API) methodology used in the actual pitting corrosion maintenance evaluation method was used to implement the CBM system. Finally, we verified the reliability of this system by conducting validation through actual case study.

A Low-Resolution IR-Array as a Doorway Occupancy Counter in a Smart Building

A doorway counter, which detects a person underpass at a room entry/exit, may be the most accurate type of occupancy counters used in buildings. An occupancy counter, which uses a low-resolution IR-imager and Raspberry Pi board has been constructed. The imager provides only 8 x 8 pixels initial resolution, but it has been enhanced using two-dimensional interpolation. Due to the low absolute accuracy in temperature measurements, the imager is set to measure temperature difference between a target and background. Signal-to-noise ratio is also increased using discrete two-dimensional convolution filtering. The blob detection and tracking algorithm deduces the direction of an occupant and finally increments or decrements the counter. A heat signature varies between people and depends on person’s clothing. An on-board server on Raspberry Pi distributes the data via Wi-Fi to any client device in the net. The complete system includes also wireless PIR-sensors. The low-resolution IR occupancy counter has been compared with counters based on different technologies. The benefits of a low-resolution IR-imager are privacy preservation, operation capability in total darkness, energy-efficient passive operation and a low price.

Cathodoluminescent screen imaging system for seeded blob detection in toroidal plasma experiment.

We designed and built a diagnostic based on a cathodoluminescent screen for the detection of turbulent plasma structures with high spatial resolution. The screen is coated with a low threshold energy cathodoluminescent powder that emits light when exposed to a plasma. The emitted light is imaged with a fast frame camera combined with an image intensifier and an optical bandpass filter. The diagnostic is used to study turbulent structures and seeded blobs. The results are analyzed with pattern recognition algorithms to track the turbulent structures and study their evolution in time.

A Novel Keypoint Detector Combining Corners and Blobs for Remote Sensing Image Registration

Keypoint detection is a crucial step for feature-based image registration. The traditional detectors only extract one type of keypoint such as a corner or a blob, which is not quite beneficial to image registration. Accordingly, this letter presents a novel keypoint detector that aims to simultaneously extract corners and blobs. The proposed detector is named as Harris-Difference of Gaussian (DoG), which combines the advantages of the Harris-Laplace corner detector and the DoG blob detector. In the definition of Harris-DoG, we first build an image scale space and extract the corners by using the multiscale Harris detector. Then, these corners are screened by an automatic scale selection technique based on their DoG responses. This can make the corners robust to scale changes. Meanwhile, DoG also is used to detect the blobs in the image scale space by a nonmaxima suppression scheme. Finally, the scale invariant feature transform (SIFT) descriptors are computed for the detected corners and blobs, and they are applied together for image registration. The proposed Harris-DoG has been tested by using three pairs of multisensor remote sensing images. The experimental results show that Harris-DoG can effectively increase the number of correct matches and improve the registration accuracy compared with the state-of-the-art keypoint detectors.

Volcano video data characterized and classified using computer vision and machine learning algorithms

Video cameras are common at volcano observatories, but their utility is often limited during periods of crisis due to the large data volume from continuous acquisition and time requirements for manual analysis. For cameras to serve as effective monitoring tools, video frames must be synthesized into relevant time series signals and further analyzed to classify and characterize observable activity. In this study, we use computer vision and machine learning algorithms to identify periods of volcanic activity and quantify plume rise velocities from video observations. Data were collected at Villarrica Volcano, Chile from two visible band cameras located ~17 ​km from the vent that recorded at 0.1 and 30 frames per second between February and April 2015. Over these two months, Villarrica exhibited a diverse range of eruptive activity, including a paroxysmal eruption on 3 March. Prior to and after the eruption, activity included nighttime incandescence, dark and light emissions, inactivity, and periods of cloud cover. We quantify the color and spatial extent of plume emissions using a blob detection algorithm, whose outputs are fed into a trained artificial neural network that categorizes the observable activity into five classes. Activity shifts from primarily nighttime incandescence to ash emissions following the 3 March paroxysm, which likely relates to the reemergence of the buried lava lake. Time periods exhibiting plume emissions are further analyzed using a row and column projection algorithm that identifies plume onsets and calculates apparent plume horizontal and vertical rise velocities. Plume onsets are episodic, occurring with an average period of ~50 ​s and suggests a puffing style of degassing, which is commonly observed at Villarrica. However, the lack of clear acoustic transients in the accompanying infrasound record suggests puffing may be controlled by atmospheric effects rather than a degassing regime at the vent. Methods presented here offer a generalized toolset for volcano monitors to classify and track emission statistics at a variety of volcanoes to better monitor periods of unrest and ultimately forecast major eruptions.

RETRACTED ARTICLE: Enhanced histogram equalization based nodule enhancement and neural network based detection for chest x-ray radiographs

Lung cancer is the malignant tumors, which maximizes the speed of incidence and death rate and it will in the shape of spherical nodules in a conventional radiograph. Moreover, few lung nodules can’t be identified, since it overlaps with the normal anatomic structures like ribs and clavicles. Earlier, Rib suppression is executed to rectify this issue, which works according to the Linear Discriminant Analysis (LDA) and it is brought-into maximize the visibility of lung nodules. With this motivation, initially, it is constructed through LDA; then, the pixel intensity of lung nodule is measure through the usage of the Enhanced Histogram Equalization and it is included to the subtracted image of original image and rib model to improve the original brightness; at last, the border of ribs is recognized and smoothed, is done through mean function is measure through the use of pixel intensity. The white nodule-likeness extraction is the second step. Texture feature extraction is done for Continuous Wavelet Transform and the multi-scale Convergence-index filter. In order to create the white nodule-likeness map (WNLM), Neural Network classifier is utilized. Candidate extraction on WNLM using Laplace of Gaussian blob detection method is the third step. To estimate the rib suppression method, the JSRT database and dual-energy images were employed. The experiment represents when the method is enforced on the test images, the ribs can be suppressed significantly.

Subpixel blob localization and shape estimation by gradient search in parameter space of anisotropic Gaussian kernels

In this paper, a novel blob localization and shape estimation method is proposed, which can implement subpixel precise localization and precise shape estimation. The method consists of blob detection and filtration, and gradient search based localization and shape estimation. In detection and filtration of blobs, the scale range of the Laplacian of Gaussian detector is determined by the particular scales, then the size priority and area-overlap rate criteria are given to filtrate the redundancy of detection results. In the subpixel localization and shape estimation, a new affine-invariant blob measure is proposed based on anisotropic Gaussian kernels, which possesses five-parameter shape description of blobs. Then the gradient search method in the five-dimensional parameter space is developed to realize a fast subpixel localization and high-precision shape estimation that is not restricted by the parameter grid. Moreover, a blob discrimination based upon the convergence of the gradient search is used to automatically remove blobs of low quality. The proposed method is compared with several methods on fluorescence-light microscopy cell images and multiple typical images with various blobs. The results show that the proposed method obtains higher localization precision, more precise shape estimation, and higher repeatability rate under affine transformations of digital images.

Improved small blob detection in 3D images using jointly constrained deep learning and Hessian analysis

Imaging biomarkers are being rapidly developed for early diagnosis and staging of disease. The development of these biomarkers requires advances in both image acquisition and analysis. Detecting and segmenting objects from images are often the first steps in quantitative measurement of these biomarkers. The challenges of detecting objects in images, particularly small objects known as blobs, include low image resolution, image noise and overlap between the blobs. The Difference of Gaussian (DoG) detector has been used to overcome these challenges in blob detection. However, the DoG detector is susceptible to over-detection and must be refined for robust, reproducible detection in a wide range of medical images. In this research, we propose a joint constraint blob detector from U-Net, a deep learning model, and Hessian analysis, to overcome these problems and identify true blobs from noisy medical images. We evaluate this approach, UH-DoG, using a public 2D fluorescent dataset for cell nucleus detection and a 3D kidney magnetic resonance imaging dataset for glomerulus detection. We then compare this approach to methods in the literature. While comparable to the other four comparing methods on recall, the UH-DoG outperforms them on both precision and F-score.

Comparison of edge turbulence characteristics between DIII-D and C-Mod simulations with XGC1

The physical processes taking place at the separatrix and scrape-off layer regions are crucial for the operation of tokamaks as they govern the interaction of hot plasma with the vessel walls. Numerical modeling of the edge with state-of-the-art codes attempts to elucidate the complex interactions between neoclassical drifts, turbulence, poloidal, and parallel flows that control the physical set-up of the SOL region. Here, we present the post-processing analysis of simulation results from the gyrokinetic code XGC1, comparing and contrasting edge turbulence characteristics from a simulation of the DIII-D tokamak against a simulation of the Alcator C-Mod tokamak. We find that the equilibrium E × B flux across the separatrix has a similar poloidal pattern in both discharges, which can be explained by ∇ B-drifts and trapped ion excursions. However, collisionality is noted to play a major role in the way that it prevents local charge accumulations from having more global effects in the C-Mod case. In both cases, turbulent electron heat flux is observed to be higher than the ion one and is possibly related to the need of electrons to maintain quasineutrality through the only channel available to them for exiting the confinement. By Fourier analysis, we identify turbulent frequencies and growth rates of the dominant mode in both simulations. In the case of C-Mod, these numbers point to the presence of a drift wave. In the DIII-D case, further linear simulations with the Gene code reveal a trapped electron mode. Furthermore, using a blob detection and tracking tool, we present the amplitude and size distributions of the blobs from both simulations. The amplitude distributions are in qualitative agreement with experimental observations, while the size distributions are consistent with the fact that most of the blobs are not connecting to the divertor plates and suggest that they are generated by the shearing of the turbulent modes.

Detection of Plant Disease on Leaves using Blobs Detection and Statistical Analysis

Plant is exposed to many attacks from various micro-organism, bacterial disease and pests. The symptoms of the attacks are usually distinguished through the leaves, stem or fruit inspection. Disease that are commonly attack plants are Powdery Mildew and Leaf Blight and it may cause severe damaged if not controlled in early stages. Image processing has widely being used for identification, detection, grading and quality inspection in the agriculture field. Detection and identification disease of a plant is very important especially, in producing a high-quality fruit. Leaves of a plant can be used to determine the health status of that plant. The objective of this work is to develop a system that capable to detect and identify the type of disease based on Blobs Detection and Statistical Analysis. A total 45 sample leaves images from different colour and type were used and the accuracy is analysed. The Blobs Detection technique are used to detect the healthiness of plant leaves. While Statistical Analysis is used by calculating the Standard Deviation and Mean value to identify the type disease. Result is compared with manual inspection and it is found that the system has 86% in accuracy compared to manual detection process.

Deep Image Sensing and Retrieval Using Suppression, Scale Spacing and Division, Interpolation and Spatial Color Coordinates With Bag of Words for Large and Complex Datasets

Intelligent and efficient image retrieval from versatile image datasets is an inevitable requirement of the current era. Primitive image signatures are vital to reflect the visual attributes for content based image retrieval (CBIR). Algorithmically descriptive and well identified visual contents form the image signatures to correctly index and retrieve similar results. Hence feature vectors should contain ample image information with color, shape, objects, spatial information perspectives to distinguish image category as a qualifying candidate. This contribution presents a novel features detector by locating the interest points by applying non-maximum suppression to productive sum of derivative of pixels computed from differential of corner scores. The interest points are described by applying scale space interpolation to scale space division produced from Hessian blob detector resulted after Gaussian smoothing. The computed shape and object information is fused with color features extracted from the spatially arranged L2 normalized coefficients. High variance coefficients are selected for object based feature vectors to reduce the massive data which in fuse form transformed to bag-of-words (BoW) for efficient retrieval and ranking. To check the competitiveness of the presented approach it is experimented on nine well-known image datasets Caltech-101, ImageNet, Corel-10000, 17-Flowers, Columbia object image library (COIL), Corel-1000, Caltech-256, tropical fruits and Amsterdam library of textures (ALOT) belong to shape, color, texture, and spatial & complex objects categories. Extensive experimentation is conducted for seven benchmark descriptors including maximally stable extremal region (MSER), speeded up robust features (SURF), difference of Gaussian (DoG), red green blue local binary pattern (RGBLBP), histogram of oriented gradients (HOG), scale invariant feature transform (SIFT), and local binary pattern (LBP). Remarkable outcomes reported that the presented technique has significant precision rates, recall rates, average retrieval precision & recall, mean average precision & recall rates for many image semantic groups of the challenging datasets. Results comparison is presented with research techniques and reported improved results.

High-ISO Long-Exposure Image Denoising Based on Quantitative Blob Characterization.

Blob detection and image denoising are fundamental, sometimes related tasks in computer vision. In this paper, we present a computational method to quantitatively measure blob characteristics using normalized unilateral second-order Gaussian kernels. This method suppresses non-blob structures while yielding a quantitative measurement of the position, prominence and scale of blobs, which can facilitate the tasks of blob reconstruction and blob reduction. Subsequently, we propose a denoising scheme to address high-ISO long-exposure noise, which sometimes spatially shows a blob appearance, employing a blob reduction procedure as a cheap preprocessing for conventional denoising methods. We apply the proposed denoising methods to real-world noisy images as well as standard images that are corrupted by real noise. The experimental results demonstrate the superiority of the proposed methods over state-of-the-art denoising methods.