Laplacian Of Gaussian Research Articles

A New Image Quality Metric Using Compressive Sensing And A Filter Set Consisting of Derivative And Gabor Filters

This paper proposes an image quality metric (IQM) using compressive sensing (CS) and a filter set consisting of derivative and Gabor filters. In this paper, compressive sensing that is used for acquiring a sparse or compressible signal with a small number of measurements is used for measuring the quality between the reference and distorted images. However, an image is generally neither sparse nor compressible, so a CS technique cannot be directly used for image quality assessment. Thus, for converting an image into a sparse or compressible signal, the image is convolved with filters such as the gradient, Laplacian of Gaussian, and Gabor filters, since the filter outputs are generally compressible. A small number of measurements obtained by a CS technique are used for evaluating the image quality. Experimental results with various test images show the effectiveness of the proposed algorithm in terms of the Pearson correlation coefficient (CC), root mean squared error, Spearman rank order CC, and Kendall CC.

Comparative Study of Edge Detection using Renyi Entropy and Differential Evolution

Edge detection is an important task in image processing. Edge is defined as the boundary between two regions separated by two relatively distinct gray level properties. Traditional edge detection methods give rise to the exponential increment of computational time. In this paper, edge detection in gray level images is done by using Renyi entropy and differential evolution algorithm. The Renyi entropy is a one- parameter generalization of the Shannon entropy. Here Renyi entropy was calculated for the1dimensional histogram of the images. Differential evolution (DE) is an efficient and powerful population-based stochastic search technique for solving optimization problems, and this has been widely applicable in many scientific and engineering fields. The selection of the initial population in a population-based heuristic optimization method is most important, as it affects the search for a number of iterations and has an influence on the final solution. If the prior information about the optima is not available, then initial population is selected randomly using a pseudorandom numbers. The main advantage of DE algorithm is its simple in structure, easy to use, speed and robustness. I.INTRODUCTION Edge detection is a method which identifies the points in a digital image at which the brightness of the image changes clearly. Edge detection is the boundary between two regions separated by two relatively distinct grey level properties. The applications of edge detection such as image enhancement, water marking, compression, restoration etc. The traditional edge detection algorithms have been developed based on computation of the intensity gradient vector and it is very sensitive to noise in the image. For decreasing the noise some spatial averaging may be combined with differentiation that is known as LOG (laplacian of Gaussian operators). But this method used a 2D linear filter which is similar to second order derivatives and that also sensitive to noise. And the magnitude of the images produces double edges and gives the undesirable effect due to incomplete segmentation. For this reason laplacian combined with smoothing and find the edges via zero crossing and it also time taking. But the proposed a technique which is based on the information theory known as Renyi entropy. Renyi entropy decreases the computation time. To compare the result of Renyi entropy we proposed a new method which is based on optimization algorithm i.e. differential evolution algorithm which is a optimization algorithm. DE is an evolutionary algorithm and it is use to find out the near optimal solutions. For minimizing the total cost and maximize the possible reliability most of the optimization algorithm is used.

Loss of Calculation in Nature Disaster by using Laplacian of Gaussian

In last few years, the nature Disaster was occur in many counties that cause on building, Hospital, university etc. in such that cases it can’t calculate the loss of economy. For that it will take a survey on that disaster place, so then it can calculate the loss of economy. In this paper, the loss of calculation in nature disaster is calculated by using Laplacian of Gaussian algorithm.

Remote Sensing Image Automatic Registration on Multi-scale Harris-Laplacian

In order to overcome the difficulty of automatic image registration in image preprocessing, this paper presents an automatic registration algorithm for remote sensing images with different spatial resolutions. The algorithm is studied based on Harris-Laplacian corner detection, which can determine the affine transformation (zoom, rotation, translation) between images of different scales. The corners in the reference and registration images are firstly detected and located by a multi-scale Harris-Laplacian (H-L) corner detector. Secondly, the algorithm chooses SURF (Speeded Up Robust Feature) descriptor to calculate the detected corners descriptors. Then, the multi-resolution corner matching is achieved based on Euclid distance. Finally, according to the LoG (Laplacian Of Gaussian), the scale factor is automatically determined between reference and registration images. A number of remote sensing images are tested, and the experiments show that the studied algorithm can register two remote sensing images of different sizes and resolutions automatically. It also verifies that the algorithm has the lower time cost comparing with the other existing algorithms (e.g. SIFT) within certain detecting accuracy level. This algorithm is also useful for resolving the problem of potential errors due to parallax effects when establishing geometric affine transformation on corners for detecting on buildings with different unknown elevations.

Blind Image Quality Assessment Using the Joint Statistics of Generalized Local Binary Pattern

Multimedia, including audio, image, and video, etc., is a ubiquitous part of modern life. Quality evaluation, both objective and subjective, is of fundamental importance for various multimedia applications. In this letter, a novel quality-aware feature is proposed for blind/no-reference (NR) image quality assessment (IQA). The new quality-aware feature is generated from the proposed joint generalized local binary pattern (GLBP) statistics. In this method, using the Laplacian of Gaussian (LOG) filters, the images are first decomposed into multi-scale subband images. Then, the subband images are encoded with the proposed GLBP operator and the quality-aware features are formed from the joint GLBP histograms from the encoding maps of each subband image. Finally, using support vector regression (SVR), the quality-aware features are mapped to the image's subjective quality score for NR-IQA. The experimental results for two representative databases show that the proposed method is strongly correlated to subjective quality evaluations and competitive to the state-of-the-art NR-IQA methods.

A Low Complexity Interest Point Detector

Interest point detection is a fundamental approach to feature extraction in computer vision tasks. To handle the scale invariance, interest points usually work on the scale-space representation of an image. In this letter, we propose a novel block-wise scale-space representation to significantly reduce the computational complexity of an interest point detector. Laplacian of Gaussian (LoG) filtering is applied to implement the block-wise scale-space representation. Extensive comparison experiments have shown the block-wise scale-space representation enables the efficient and effective implementation of an interest point detector in terms of memory and time complexity reduction, as well as promising performance in visual search.

Face Mole Detection, Classification and Application

Do you have moles on face? Are the moles good or bad? We could treat this problem from medical, cosmetic, or even fortune applications viewpoint. Here, image processing techniques are investigated to detect and verify the goodness of face mole from fortune telling point of view. The process includes Voronoi diagram setup for sample moles, face mole detection, and mole recognition. In the first part, Voronoi diagram is used to partition the given sample mole-face into regions. In the second part, face detection and Laplacian of Gaussian is used to get the prominent features on face. Aspect ratio and area are two features for mole verification. At last, an algorithm is developed to warp the detected user moles to the sample mole-face by Thin-plate Spline Analysis for mole recognition. By using Voronoi diagram, the mole recognition spends only O(logn), where n is the number of given sample moles. The goodness of the recognized mole could be retrieved according to the stored information for fortune telling. The system was tested with 20 people and the mole recognition rate reached 91.25% which demonstrated the feasibility of the proposed system.

Methods of Image Edge Detection: A Review

The first step in an image recognition system is the edges sensibility in a digital image. Edge detection for object observation in image processing is the important part. This will give us a good understanding of edge detection algorithms. An edge is useful because it marks the boundaries and divides of plane, object or appearance from other places things. For pattern recognition it is also an intermediate step in the digital images. An edge consists of pixels with the intensity variations of gray tones which are different from their neighbour pixels. This paper introduces the standard edge detection methods which are widely used in image processing such as Prewitt, Laplacian of Gaussian, Canny, Sobel, Robert and also the new approach are discussed in this known as Fuzzy logic.

Image segmentation based on Frequency domain operation (FFT) and plugin implementation for ImageJ

Event Abstract Back to Event Image segmentation based on Frequency domain operation (FFT) and plugin implementation for ImageJ Víctor J. García Fernández1* and Dimiter Prodanov2 1 IMEC, Belgium 2 IMEC, EHS, Belgium In order to better measure cell’s response to different chemical or mechanical stimuli robust quantification of the cell spatio-temporal organization is required. Accurate identification of individual cellular phenotypes can be obtained by combining automated microscopic acquisition with extensive morphological feature extraction and data mining strategies. The aim of the present work is to implement filter banks allowing for measurement of scale-invariant features which will be used for downstream image classification operations. A generic way of segmenting images is by using multi-scale approaches, such as wavelet filter banks or scale spaces. Fourier domain filtering encodes image information in a distributed manner that allows manipulation of the global information content of the image scaling the performance of such filtering operations. The poster and the software demo will present a generic framework for Fourier domain filtering made available as a plugin to the popular public domain image processing software ImageJ. Filter implementations include Gaussian, Laplacian of Gaussian and Fractional Laplacian operators. We could successfully apply this plugin for example in segmentation of histological images. Acknowledgements The work has been supported in part by a grant from Research Fund - Flanders (FWO), contract number 0880.212.840. References Prodanov D (2013). Open source image analysis software toolboxes for microscopic applications. Front. Neuroinform. Conference Abstract: Imaging the brain at different scales: How to integrate multi-scale structural information?. doi: 10.3389/conf.fninf.2013.10.00005 Lindeberg, T. (1994). Scale-space theory: A basic tool for analysing structures at different scales. J App Stat. 21 (2): 224–270. Mols K, Prodanov D and Bonin V (2013). Scale-space based segmentation of cells in functional two-photon in vivo images. Front. Neuroinform. Conference Abstract: Imaging the brain at different scales: How to integrate multi-scale structural information?. doi: 10.3389/conf.fninf.2013.10.00033 Keywords: Image Processing, Computer-Assisted, FFT, filtering, Cell segmentation, ImageJ Conference: Second Belgian Neuroinformatics Congress, Leuven, Belgium, 4 Dec - 4 Dec, 2015. Presentation Type: Poster Presentation Topic: Brain Imaging Citation: García Fernández VJ and Prodanov D (2015). Image segmentation based on Frequency domain operation (FFT) and plugin implementation for ImageJ. Front. Neuroinform. Conference Abstract: Second Belgian Neuroinformatics Congress. doi: 10.3389/conf.fninf.2015.19.00010 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 31 Oct 2015; Published Online: 17 Nov 2015. * Correspondence: Mr. Víctor J García Fernández, IMEC, Leuven, Belgium, victorjgf@gmail.com Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Víctor J García Fernández Dimiter Prodanov Google Víctor J García Fernández Dimiter Prodanov Google Scholar Víctor J García Fernández Dimiter Prodanov PubMed Víctor J García Fernández Dimiter Prodanov Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

A Novel Approach for Interest Point Detection via Laplacian-of-Bilateral Filter

Scale-invariant feature transform (SIFT) algorithm, one of the most famous and popular interest point detectors, detects extrema by using difference-of-Gaussian (DoG) filter which is an approximation to the Laplacian-of-Gaussian (LoG) for improving speed. However, DoG filter has a strong response along edge, even if the location along the edge is poorly determined and therefore is unstable to small amounts of noise. In this paper, we propose a novel interest point detection algorithm, which detects scale space extrema by using a Laplacian-of-Bilateral (LoB) filter. The LoB filter, which is produced by Bilateral and Laplacian filter, can preserve edge characteristic by fully utilizing the information of intensity variety. Compared with the SIFT algorithm, our algorithm substantially improves the repeatability of detected interest points on a very challenging benchmark dataset, in which images were generated under different imaging conditions. Extensive experimental results show that the proposed approach is more robust to challenging problems such as illumination and viewpoint changes, especially when encountering large illumination change.

Coarse-to-fine dot array marker detection with accurate edge localization for stereo visual tracking

We present a coarse-to-fine dot array marker detection algorithm which can extract dot features with high accuracy and low uncertainty. The contribution of this paper is twofold: one is a configurable dot array marker detection framework which enables real-time multi-marker tracking with compact marker size (coarse detection); the other is a closed-form sub-pixel edge localization method including the formulation and the implementation (fine localization). The marker pattern together with the dot contours is detected in a fast but coarse way for efficiency consideration, using simple thresholding and hierarchical contour analysis. If the marker pattern matches with one of predefined marker descriptors, sub-pixel edge point localization of the dot contour is performed within the detected marker region by searching the zero-crossing in the convolution of the marker image with a Laplacian-of-Gaussian (LoG) kernel. A closed-form solution is proposed to localize the “true” edge point in a 3×3 neighborhood of a candidate pixel by solving a quartic equation. The dot center is finally extracted by ellipse fitting and re-ordered according to an orientation indicator. The algorithm was evaluated against both synthetic and real image data, and also in real applications where stereo visual trackers were implemented using the proposed marker detection algorithm. Experimental results show that (1) the marker detection algorithm yielded a feature detection error of less than 0.1 pixel with real-time performance; (2) the uncertainties in both localizing static 2-D dot features and 3-D pose tracking were obviously reduced by performing the sub-pixel localization; and (3) the feasibility of the marker tracking under stereo laparoscopic views was confirmed in an in vivo animal experiment.

Edge Detection Operators: Peak Signal to Noise Ratio Based Comparison

Edge detection is the vital task in digital image processing. It makes the image segmentation and pattern recognition more comfort. It also helps for object detection. There are many edge detectors available for pre-processing in computer vision. But, Canny, Sobel, Laplacian of Gaussian (LoG), Robert's and Prewitt are most applied algorithms. This paper compares each of these operators by the manner of checking Peak signal to Noise Ratio (PSNR) and Mean Squared Error (MSE) of resultant image. It evaluates the performance of each algorithm with Matlab and Java. The set of four universally standardized test images are used for the experimentation. The PSNR and MSE results are numeric values, based on that, performance of algorithms identified. The time required for each algorithm to detect edges is also documented. After the Experimentation, Canny operator found as the best among others in edge detection accuracy. Index Terms—Canny operator, Edge Detectors, Laplacian of Gaussian, MSE, PSNR, Sobel operator.

Blind image quality assessment using joint statistics of gradient magnitude and Laplacian features.

Blind image quality assessment (BIQA) aims to evaluate the perceptual quality of a distorted image without information regarding its reference image. Existing BIQA models usually predict the image quality by analyzing the image statistics in some transformed domain, e.g., in the discrete cosine transform domain or wavelet domain. Though great progress has been made in recent years, BIQA is still a very challenging task due to the lack of a reference image. Considering that image local contrast features convey important structural information that is closely related to image perceptual quality, we propose a novel BIQA model that utilizes the joint statistics of two types of commonly used local contrast features: 1) the gradient magnitude (GM) map and 2) the Laplacian of Gaussian (LOG) response. We employ an adaptive procedure to jointly normalize the GM and LOG features, and show that the joint statistics of normalized GM and LOG features have desirable properties for the BIQA task. The proposed model is extensively evaluated on three large-scale benchmark databases, and shown to deliver highly competitive performance with state-of-the-art BIQA models, as well as with some well-known full reference image quality assessment models.

Salt & Pepper 잡음 환경에서 에지 검출 알고리즘에 관한 연구

영상, 차선, 물체 인식 등을 위한 에지 검출은 중요한 영상 처리 방법이며, 이를 위한 기존의 방법에는 Sobel, Prewitt, Roberts, Laplacian, LoG(Laplacian of Gaussian) 등이 있다. 이러한 방법들은 salt & pepper 잡음에 훼손된 영상에서 특성이 미흡하다. 이와 같은 문제점을 개선하기 위하여 본 논문에서는 중심 화소의 인접 화소를 중심으로 국부 마스크를 설정하여, 그것의 중심 화소가 비잡음인 경우 그대로 처리하고 잡음인 경우 추정 마스크를 구한 후, 가중치 마스크를 적용하여 에지를 검출하는 알고리즘을 제안하였다. Edge detection for such as image, lane and object recognition is important image processing method. And some traditional method for this, there are Sobel, Prewitt, Roberts, Laplacian, LoG(Laplacian of Gaussian) and so on. Characteristics of these methods are insufficient in the salt & pepper noise added image. In order to improve such a problem of conventional methods, in this paper, we proposed an algorithm applying the weighted mask for detecting an edge by setting the local mask centered on the adjacent of the central pixel if central pixel of the mask is non-noise, it is intactly set by element of estimated mask, after calculating estimated mask if it is noise.

A Blur Metric Method Based on Edge Width for the Blurred Image

Aiming at the inaccurate locating problem of the boundary while retrieving edge width by the edge extension and inaccurate blur measure problem of a blurred image due to the dependence on the gradient direction, this paper presents a novel blur measure method, which applies the edge width obtained by a multi-scale filtering to model the blurriness of Gaussian-blurred image. The proposed method first construct the gradient line of Gaussian-blurred image according to its gradient magnitude edge and models the relationship between the edge and the gradient line, and then using LOG (Laplace of Gaussian)filter detects the edge to determine the edge width. The experimental results show that the average width determined by the proposed method can measure the blurriness of Gaussian-blurred images and the blur measure based on the edge width is stable for images with different content.

Comparison of Crack Extraction Performance According to Different Edge Detectors

Edges of images contain important information such as form, size, and location of objects. Thus, edge detection is an extremely important factor in image processing. In order to detect such edges, much research has been carried out, and edge detectors such as Sobel, Prewitt, Robert, Canny, and Laplacian of Gaussian (“LoG”) are universally used. This Research compares and analyzes the crack extraction function of each edge detector to automatically detect cracks occurring in concrete structures. In order to do this, simulated crack samples of various widths and contrasts were produced and attached to concrete walls, and crack images were taken from different distances. Cracks were extracted from the images taken using edge detectors like Sobel, Prewitt, Robert, Canny, and LoG, and the crack extraction performance of the edge detectors used were compared and analyzed based on the photographed distance.

A Robotic Crack Inspection and Mapping System for Bridge Deck Maintenance

One of the important tasks for bridge maintenance is bridge deck crack inspection. Traditionally, a human inspector detects cracks using his/her eyes and marks the location of cracks manually. However, the accuracy of the inspection result is low due to the subjective nature of human judgement. We propose a crack inspection system that uses a camera-equipped mobile robot to collect images on the bridge deck. In this method, the Laplacian of Gaussian (LoG) algorithm is used to detect cracks and a global crack map is obtained through camera calibration and robot localization. To ensure that the robot collects all the images on the bridge deck, a path planning algorithm based on the genetic algorithm is developed. The path planning algorithm finds a solution which minimizes the number of turns and the traveling distance. We validate our proposed system through both simulations and experiments.

변형된 가중치 마스크를 이용한 에지검출 알고리즘에 관한 연구

에지는 영상에서 화소 간의 명암 차이가 큰 경우에 나타나며, 대상의 크기, 위치, 방향 등의 정보를 포함한다. 에지검출 방법에는 Sobel, Roberts, Laplacian, LoG(Laplacian of Gaussian) 등이 있으며, 이러한 방법들은 AWGN(additive white Gaussian noise)이 첨가된 영상에서 그 특성이 미흡하다. 따라서 이러한 특성을 개선하기 위하여 본 논문에서는 거리에 따른 가중치와 주변 화소의 평균에 의한 추정 마스크를 적용하는 알고리즘을 제안하였다. 그리고 제안한 방법의 성능을 확인하기 위하여 평가 척도는 처리 영상 및 PFOM(Pratt's figure of merit)을 사용하여 기존의 방법들과 비교하였다. Edge in images appears when a great difference shows up in light and shade between pixels and includes data of the subject's size, location direction and etc. The edge is generally detected by the methods such as Sobel, Roberts, Laplacian, LoG(Laplacian of Gaussian) and etc. However, in AWGN(additive white Gaussian noise) added images, quality of the edge becomes slightly uncertain. Therefore, this paper proposed edge detection algorithm using modified mask of weighting to improve the quality of the existing methods. And in order to verify the performance efficiency of the proposed method, processed image and PFOM(Pratt's figure of merit) has been used as valuation standard for a comparison with the existing methods.

Breast cancer detection using combined curvelet based enhancement and a novel segmentation methods

This paper describes the digital implementation of a mathematical transform namely 2D Fast Discrete Curvelet Transform (FDCT) via UnequiSpaced Fast Fourier Transform (USFFT) in combination with the novel segmentation method for effective detection of breast cancer. USFFT performs exact reconstructions with high image clarity. Radon, ridgelet and Cartesian filters are included in this method. Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR) were calculated for the image and the resulting value showed that the proposed method performs well on mammogram image in reducing noise with good extraction of edges. This work includes a novel segmentation method, which combines Modified Local Range Modification (MLRM) and Laplacian of Gaussian (LoG) edge detection method to segment the textured features in the mammogram image. The result was analyzed using a Receiver Operating Characteristics (ROC) plot and the detection accuracy found was 99% which is good compared to existing methods.

Noise robust face hallucination employing Gaussian–Laplacian mixture model

Because of the excellent ability to characterize the sparsity of natural images, ℓ1-norm sparse representation (SR) is widely used to formulate the linear combination relationship in dictionary-learning-based face hallucination. However, due to inherently less sparse nature of noisy images, Laplacian prior assumed for ℓ1-norm seems aggressive in terms of sparsity, which ultimately leads to significant degradation of hallucination performance in the presence of noise. To this end, we suggest a moderately sparse prior model referred to as a Gaussian–Laplacian mixture (GLM) distribution and employ it to infer the optimal solution under the Bayesian framework. The resulting regularization method known elastic net (EN) not only maintains same hallucination performance as SR under noise free scenarios but also outperforms the latter remarkably in the presence of noise. The experimental results on simulation and real-world noisy images show its superiority over some state-of-the-art methods.