Smallest Univalue Segment Assimilating Nucleus Research Articles

Addressing topology optimization with overhang constraints for structures subjected to self-weight loads

This paper investigates the topology optimization of structures subjected to self-weight loads with self-supporting constraints for additive manufacturing. The integration of topology optimization procedures and additive manufacturing techniques can make the most of their advantages, and there is significant interest today in integrating both approaches. Imposing overhang constraints in topology optimization has been addressed, but primarily for classical topology optimization problems with fixed external loads, not design-dependent loads. This work combines an effective numerical procedure for contour evaluation with a modified version of the power-law model for low densities to eliminate the problems that arise when self-weight loads are considered. The overhang edge detection is based on the Smallest Univalue Segment Assimilating Nucleus (SUSAN) method, and a variable mask size technique is used to avoid eventual dripping problems. The proposed constraint function evaluates the overhang globally and allows control of the formation of unsupported contours for maximum stiffness design problems when self-weight loads are present. Several numerical experiments demonstrate the proposed method's effectiveness and robustness.

Quantum SUSAN edge detection based on double chains quantum genetic algorithm

Edge detection algorithm based on quantum image processing has attracted much attention due to low circuit complexity and small storage capacity. Since the classical smallest univalue segment assimilating nucleus (SUSAN) algorithm is limited in vertical and horizontal directions, a new quantum SUSAN edge detection scheme based on double chains quantum genetic algorithm is designed. First, the linear X-shift and the Y-shift transforms are raised to accelerate the qubit retrieval process and output the quantum feature information. Then, the quantum feature information is fed to quantum comparator and surround suppression circuit exports gradient information. Finally, the quantum SUSAN classifier outputs classification results. The presented algorithm combines the advantages of SUSAN’s accurate positioning and texture edge suppression with the superposition of the quantum genetic algorithm, which avoids the trap of local optimum. In the quantum SUSAN classifier circuit, the double chains quantum genetic coding and the circular SUSAN mask are introduced to improve classification accuracy. Experimental results verify that the proposed scheme has a good edge searchability. Moreover, the edge points obtained by this algorithm are more integral and continuous than other classical algorithms and existing quantum algorithms.

Multimodal Medical Image Fusion Using Nonsubsampled Shearlet Transform and Smallest Uni-Value Segment Assimilating Nucleus

This paper presents a new fusion scheme for medical (CT-MRI) images which is based on the nonsubsampled shearlet transform (NSST). The various image pairs to be fused are obtained from primary and internet sources. Initially, the images are decomposed through NSST into general and detailed features. The smallest uni-value segment assimilating nucleus (SUSAN) and local sum of Gaussian weighted pixel intensities-based activity measures are proposed to fuse the detailed sub-bands and low-frequency sub-band of NSST, respectively, for faster execution of the algorithm. Visual and parametric comparison of the proposed scheme is done through five traditional fusion algorithms using nine fusion performance parameters. In addition, Wilcoxon signed ranks test is also applied to compare different methods scientifically with the proposed fusion scheme. It is observed that the presented method is better in retaining bone, calcification, cerebrospinal fluid (CSF), edema and tumor details of the source images and is faster than other classical fusion schemes. The fused images of the proposed method are suitable for locating the site of biopsy externally or incision location in the bone of the brain skull with minimum diagnostic time.

A hybrid classical techniques and optimal decision model for iris recognition under variable image quality conditions

One of the best biometrics used for human verification and identification is iris recognition. The contrast of its unique characteristics differs from one candidate to another in which the iris pattern has numerous well-known features like uniqueness texture, stability and compactness representation for human identification. Among these facts, several approaches in these areas are localized, but there is still an abundant problems such as the low match rate of the score level and low accuracy. Therefore, a decision model should be essential for iris recognition frameworks. This paper proposes a iris recognition based on a decision model using a unified framework based on the integration of three detection schemes due to variation occurred in shading and position change using Smallest Univalue Segment Assimilating Nucleus (SUSAN), Generalized Hough Transform (GHT) and Viola–Jones (SUSANGHT-VJ) for eye detection, enhancing the dimmer and darker areas using fuzzy retinex method and normalizing the iris boundary using daugman’s Rubber Sheet Model for segmentation. Also, the iris corner points is extracted using Gabor Wavelet Transform (GWT), the vector properties of the blurred texture features are quantized using Local Phase Quantization (LPQ) and the optimal decision model based on Atom Search Optimization (ASO) and Feed Forward Counter propagation Neural Network (FFCNN) for matching score level and classification task. Furthermore, the current framework prevents false matches and inappropriate iris input, thus making the iris match score framework more reliable. The evaluation of the proposed approach is trained and tested with the employed eye template of iris and face datasets. Therefore, the results depict that the proposed technique gives a high recognition rate of 99.9% on different datasets compared to existing methods.

Analysis of controversies in the formulation and evaluation of restoration algorithms for MR Images

There is no reliable guidance available in literature so far for the selection of a suitable technique for denoising Magnetic Resonance (MR) images. The performance of edge-preserving denoising schemes like Nonlocal Means, Bilateral, Total Variation, Anisotropic Diffusion, Kuwahara, wavelet denoising, Linear Minimum Mean Square Error, Smallest Univalue Segment Assimilating Nucleus and Beltrami filters on MR images are evaluated and compared in this paper. Performance evaluation is done on real-time MR Images, Shepp–Logan Phantom images and simulated MR images. Image Quality Analysis indices used for the evaluation are Structural Similarity Index Metric, Noise Quality Measure, Peak Signal to Noise Ratio, Edge Preservation Index, MetricQ, Anisotropic Quality Index, Blind Reference Image Quality Evaluator and computational time. It has been observed that the performance of each filter is completely different on Shepp–Logan, simulated MR and real-time MR images. It is critically sensitive to the strength of noise also. No filter which can offer good performance equally on Phantom, simulated MR image and real-time MR images, is available in the literature. Values of the objective indices are not in concordance with subjective quality ratings. Filter designs optimized on Phantom or simulated MR using maximum PSNR between denoised and ground-truth images as an objective function (minimum error sense in general) do not perform well on real-time MRI.

A new overhang constraint for topology optimization of self-supporting structures in additive manufacturing

This work falls within the scope of computer-aided optimal design, and aims to integrate the topology optimization procedures and recent additive manufacturing technologies (AM). The elimination of scaffold supports at the topology optimization stage has been recognized and pursued by many authors recently. The present paper focuses on implementing a novel and specific overhang constraint that is introduced inside the topology optimization problem formulation along with the regular volume constraint. The proposed procedure joins the design and manufacturing processes into a integrated workflow where any component can directly be manufactured with no requirement of any sacrificial support material right after the topology optimization process. The overhang constraint presented in this work is defined by the maximum allowable inclination angle, where the inclination of any member is computed by the Smallest Univalue Segment Assimilating Nucleus (SUSAN), an edge detection algorithm developed in the field of image analysis and processing. Numerical results on some benchmark examples, along with the numerical performances of the proposed method, are introduced to demonstrate the capacities of the presented approach.

Sparsity-based inverse halftoning via semi-coupled multi-dictionary learning and structural clustering

Inverse halftoning is the restoration of a continuous-tone image from its halftone version, which is a critical process for halftone transform, digital archive management and high precision identification of halftone. In this paper, a novel inverse halftoning method based on semi-coupled multi-dictionary learning is proposed to address the cross-style image restoration from halftone images to continuous-tone images. By using semi-coupled multi-dictionary learning, multiple dictionary pairs and their corresponding mapping functions between continuous-tone image and its halftone version could be simultaneously learned. The learned multiple dictionary pairs can well represent the structure characteristics of halftone images and continuous-tone images, respectively. In addition, the mapping functions learned by semi-coupled manner can bridge the gap between the two different style images of halftone image and continuous-tone image. Unlike the existed methods, the proposed method could effectively relax the assumption of the same sparse coding coefficients in coupled dictionary learning. To obtain more accurate mapping functions, a structural clustering method for cross-style image patches is proposed by using SUSAN (smallest univalue segment assimilating nucleus) filtering and HOG (histogram of oriented gradient) features, which can capture the similar structure features from halftone images and continuous-tone images, and thus improve the classification accurate rate of halftone image patches. The experimental results demonstrate that the proposed method can restore higher quality continuous-tone images than that produced by the state-of-the-art methods, which not only reduce the screen noise in smooth regions, but also provide well fine details and clear edges.

Smallest Univalue Segment Assimilating Nucleus approach to Brain MRI Image Segmentation using Fuzzy C-Means and Fuzzy K-Means Algorithms

Image segmentation still remains an important task in image processing and analysis. Sequel to any segmentation process, preprocessing activities carried out on the images have a great effect on the accuracy of the segmentation task. This paper therefore laid emphasis on the preprocessing stage of brain Magnetic Resonance Imaging (MRI) images Smallest Univalue Segment Assimilating Nucleus (SUSAN) and bias field correction algorithms. Subsequently, brain tissue extraction tool was employed in extracting non-brain tissues from the brain image. Afterwards, Fuzzy K-Means (FKM) and Fuzzy C-Means (FCM) segmentation algorithms were employed for segmenting brain MRI images acquired from four different MRI databases into their White Matter (WM), Gray Matter (GM) and Cerebrospinal Fluid (CSF) constituents. Evaluation metrics such as cluster validity functions using partition coefficients and partition entropy; area error metrics such as false positive, true positive, true negative and false negative (FN); similarity index, sensitivity and specificity were used to evaluate the performance of both techniques. A comparative analysis of the experimental results revealed that in most instances, FKM segmentation technique is preferable to FCM segmentation technique for brain MRI segmentation task.

A visual navigation algorithm for paddy field weeding robot based on image understanding

Navigation system and its navigation algorithm are the crucial parts for intelligent paddy field weeding robot. The environments of paddy fields are complicated in South China. The colors of weed, duckweed and cyanobacteria, which grow in paddy fields, are very similar with rice seedlings. Moreover, the rice seedlings present various morphological features during the growth progress. Therefore, how to extract the guidance lines for navigation system and weeding robot presents various challenges. In order to deal with the above mentioned problems, a navigation method for weeding robot based on SUSAN (smallest univalue segment assimilating nucleus) corner and improved sequential clustering algorithm is proposed in this paper. Firstly, gray feature in paddy field image is extracted by using the adaptive graying algorithm. Secondly, the SUSAN corners are extracted as characteristic points. Thirdly, the seedling navigation line is detected by applying the improved sequential clustering algorithm and Hough Transform. Finally, the position error and angle error are calculated, and a fuzzy controller is designed to control the robot. Experimental results show desirable performances of the proposed method. The proposed segmentation method is effective in complicated environment.

Volume visualization based on the intensity and SUSAN transfer function spaces

Designing transfer functions is a challenging task for medical volume data visualization, especially when an arch of the same boundary disperses seriously and adjacent arches are intersected in the intensity and gradient magnitude (IGM) transfer function space. In this paper, a novel transfer function space is proposed to better highlight and differentiate different materials in realistic volume datasets. The proposed method combines the intensity values and three-dimensional (3D) SUSAN (Smallest Univalue Segment Assimilating Nucleus) edge responses of the original data to define the intensity and SUSAN (IS) transfer function space. The results of various datasets in volume rendering show that boundary of different materials exhibits a trapezoidal shape in the proposed IS space, and boundary information is much better brought out in comparison to the IGM space. Thus the IS space provides much more intuitive clues than the IGM space in order that transfer functions can be more easily designed. Meanwhile, more details of materials of interest are visible in the rendering images.

Vehicle License Plate Detection and Tilt Correction Based on HSI Color Model and SUSAN Corner Detector

Detection and tilt correction of vehicle license plates are inevitable problems to be solved before developing Intelligent Transportation Systems. This paper describes a method of extraction of the vehicle license plate region from a vehicle image with tilt correction. The method consists of five distinct phases: segmenting color, labeling and filtering, correcting tilt, verifying candidate region, and segmenting license plate characters. Initially, an adaptive technique with labeling and filtering capability is utilized to select a statistical threshold value in the HSI color space for detecting candidate vehicle license plate regions. In this way the proposed method can overcome the limitation of the failure to detect a license plate when the vehicle body and license plate are similar colors. The slopes and tilt angles in both the horizontal and vertical directions of the skewed vehicle license plate are determined using the candidate corner points detected by the Smallest Univalue Segment Assimilating Nucleus corner detector, and the license plate region is rotated accordingly. Finally, a horizontal and vertical position histogram is employed to segment the candidate region into rows and constituent characters. The proposed tilt correction method is compared with the least square fitting with perpendicular offsets method and found to outperform results when the tilt angle gradually increases. 145 vehicle images were used for testing with different conditions and the results are presented to prove its efficiency and effectiveness.

Quantity estimation modeling of the Rice Plant-hopper infestation area on rice stems based on a 2-Dimensional Wavelet Packet Transform and corner detection algorithm

BackgroundOutbreaks of Rice Plant-hoppers (RPH) (Nilaparvata lugens, Sogatella furcifera, and Laodelphax striatellus) appear in Asia almost every year and have had significant impacts on rice yields. To implement timely, targeted pesticide applications, reduce input costs and benefit the environment, the accurate early detection and quantity estimation of RPH infestation is a critical part of integrated pest management (IPM) for rice production. To use visible images to detect and estimate RPH infestation areas on rice stems, related experiments and studies were performed to determine the feasibility of using a 2-Dimensional Wavelet Packet Transform (2DWPT) and a corner detection algorithm. Visible images of the rice stems were collected using a handheld camera. First, a series of pretreatments to these visible images were applied, including smoothing, denoising, image color space transformation and 2-Dimensional Wavelet Packet transformation. Second, the related image corner eigenvalues (i.e. the number of the corners) were extracted using a Smallest Univalue Segment Assimilating Nucleus (SUSAN) algorithm. Finally, a linear regression model was developed based on the corner eigenvalues. ResultsThe results show that the SUSAN corner detection algorithm used to extract the corner eigenvalues can also be used to distinguish the I (infestation) and N (non-infestation) areas with high accuracy. Most of the corner eigenvalues based on different image forms had a high correlation coefficient with the RPH quantity, and B-P10 (i.e., the corner eigenvalue of the RGB color space B component that was transformed via 2DWPT at node P10) had the highest correlation coefficient of 0.8277. ConclusionsIt is possible to detect and quantify the estimated RPH infestation area on rice stems by applying a 2DWPT and corner detection algorithm to visible images. Along with the micro-sensor mobile monitoring platform, the visible-image-based method is expected to be used as a redundant method in remote sensing to measure the stress induced by RPH.

Nonlocal-means-based smallest univalue segment assimilating nucleus edge detector

To improve the antinoise performance of the smallest univalue segment assimilating nucleus (SUSAN) edge detector, a nonlocal means-based SUSAN edge detector is proposed. The proposed method first determines the initial SUSAN edge response based on the image patch convolved with an adaptive kernel instead of the single pixel. Then it computes the final edge response using the weighted sum of the initial edge responses of the pixels with their structures similar to the considered pixel. Extensive simulations on natural and real images demonstrate that compared with state-of-the-art detectors, the proposed method performs much better in terms of robustness to noise and edge detection and it provides significantly higher values of Pratt’s figure of merit and performance measure.

Analysis and improvement of SUSAN algorithm

A modified Smallest Univalue Segment Assimilating Nucleus (SUSAN) algorithm based on the local gray value character of an image is presented here. Beginning with an explanation of the principle of edge detection and noise reduction, we find SUSAN algorithm is immune to all noise points but the isolated noise points. To improve this, an original edge response formulation is optimized by imposing constraint conditions. Then a set of anti-noise tests were run to compare our scheme with the original algorithm and other popular edge detectors. The results show that for Gaussian noise and salt-and-pepper noise, the improved SUSAN algorithm performs much better than the original one in view of sensitivity to noise and detection of edges, and especially for salt-and-pepper noise the improved SUSAN algorithm works best among the all detectors tested here.

Segmentation of the High Spatial Resolution Remotely Sensed Imagery Based on SUSAN

The SUSAN(Smallest Univalue Segment Assimilating Nucleus) method is used to detect gradient features from QuickBird imagery,and then the imagery is segmented using marker-controlled WT(Watershed Transform),and the segmentation result is satisfactory.The SUSAN method detects gradients well.It is not sensitive to noise and the values of the gradients are in a definite range and do not change with images,which offers convenience in selecting parameters in the later processes.The method is flexible because it is easy to choose the illumination threshold and the size of SUSAN matrix is not fixed.Based on the marker derived from both SUSAN gradients and NDVI,the gradients are modified using morphological grayscale reconstruction method,which efficiently constrains much local minima of the gradients and improves the segmentation precision.

Ultrasound speckle reduction by a SUSAN-controlled anisotropic diffusion method

An ultrasound speckle reduction method is proposed in this paper. The filter, which enhances the power of anisotropic diffusion with the Smallest Univalue Segment Assimilating Nucleus (SUSAN) edge detector, is referred to as the SUSAN-controlled anisotropic diffusion (SUSAN_AD). The SUSAN edge detector finds image features by using local information from a pseudo-global perspective. Thanks to the noise insensitivity and structure preservation properties of SUSAN, a better control can be provided to the subsequent diffusion process. To enhance the adaptability of the SUSAN_AD, the parameters of the SUSAN edge detector are calculated based on the statistics of a fully formed speckle (FFS) region. Different FFS estimation schemes are proposed for envelope-detected speckle images and log-compressed ultrasonic images. Adaptive diffusion threshold estimation and automatic diffusion termination criterion are employed to enhance the robustness of the method. Both synthetic and real ultrasound images are used to evaluate the proposed method. The performance of the SUSAN_AD is compared with four other existing speckle reduction methods. It is shown that the proposed method is superior to other methods in both noise reduction and detail preservation.

Feature list object matching based on oriented SUSAN features

For the machine vision object matching,the feature list correlation algorithm can be adopted in the calculation of the matching similarity measurement.As a result,the processing time is able to be decreased considerably,and the objects can also be clearly recognized due to the high values of the coefficients and the high values of the Peak Signal-to-Noise Ratio(PSNR).A feature list object matching method based on the oriented Smallest Univalue Segment Assimilating Nucleus(SUSAN)features was proposed.The feature pixels with oriented SUSAN features were added to the feature lists and the similarity was based on the normalized absolute error of feature pixel points.The supposed algorithm is verified by the experiments.

Combining block and corner features for content-based trademark retrieval

In order to retrieve a similarly look trademark from a large trademark database, an automatic content based trademark retrieval method using block hit statistic and corner Delaunay Triangulation features was proposed. The block features are derived from the hit statistic on a series of concentric ellipse. The corners are detected based on an enhanced SUSAN (Smallest Univalue Segment Assimilating Nucleus) algorithm and the Delaunay Triangulation of corner points are used as the corner features. Experiments have been conducted on the MPEG-7 Core Experiment CE-Shape-1 database of 1 400 images and a trademark database of 2 000 images. The retrieval results are very encouraging.

Training-Based Descreening

Conventional halftoning methods employed in electrophotographic printers tend to produce Moiré artifacts when used for printing images scanned from printed material, such as books and magazines. We present a novel approach for descreening color scanned documents aimed at providing an efficient solution to the Moiré problem in practical imaging devices, including copiers and multifunction printers. The algorithm works by combining two nonlinear image-processing techniques, resolution synthesis-based denoising (RSD), and modified smallest univalue segment assimilating nucleus (SUSAN) filtering. The RSD predictor is based on a stochastic image model whose parameters are optimized beforehand in a separate training procedure. Using the optimized parameters, RSD classifies the local window around the current pixel in the scanned image and applies filters optimized for the selected classes. The output of the RSD predictor is treated as a first-order estimate to the descreened image. The modified SUSAN filter uses the output of RSD for performing an edge-preserving smoothing on the raw scanned data and produces the final output of the descreening algorithm. Our method does not require any knowledge of the screening method, such as the screen frequency or dither matrix coefficients, that produced the printed original. The proposed scheme not only suppresses the Moiré artifacts, but, in addition, can be trained with intrinsic sharpening for deblurring scanned documents. Finally, once optimized for a periodic clustered-dot halftoning method, the same algorithm can be used to inverse halftone scanned images containing stochastic error diffusion halftone noise.

항공영상으로부터 에지 맵의 체인코드 추적에 의한 선소추출

고해상도의 항공영상으로부터 3차원 와이어프레임(wire-frame) 구성을 위한 새로운 선소 추출 알고리듬을 제안하였다. 본 연구의 목적은 기존의 방식들의 문제점인 라인 불일치 문제, 에지부분의 Blurring 문제 등을 고려하여 보다 정밀하고 효과적인 선소를 추출하는데 있다. 먼저 항공영상으로부터 에지맵을 추출한 후, 에지 점들의 체인 코드 추적을 수행하고 에지강도와 방향성분을 고려한 선소의 추출을 행하였다. 에지맵의 추출은 Smith가 제안한 SUSAN(Smallest Univalue Segment Assimilating Nucleus) 알고리듬을 이용하였다. 제안한 알고리듬은 다음의 4 단계로 구성된다. 에지 맵의 체인코드 추적 결과에 기반하여 비선소 후보점을 감소시키기 위한 수평/수직/대각 성분 제거, 인접점 제거, 각도 일치점 제거, 선소를 이루는 시작점 및 끝점 검출 등의 과정을 통하여 선소추출을 행하였다. 제안한 알고리듬과 기존의 Boldt 알고리듬을 비교한 결과 제안한 알고리듬이 건물을 이루고 있는 주요 선소를 더욱 충실히 찾아냈고 불필요한 선소는 적게 찾아냄을 확인하였다. A new algorithm is proposed for the extraction of line segments to construct 3D wire-frame models of building from the high-resolution aerial images. The purpose of this study Is the accurate and effective extraction of line segments, considering the problems such as discordance of lines and blurred edges existing in the conventional methods. Using the edge map extracted from aerial images, chain code tracking of edges was performed. Then, we extract the line segments considering the strength of edges and the direction of them. SUSAN (Smallest Uni-value Segment Assimilating Nucleus) algorithm proposed by Smith was used to extract an edge map. The proposed algorithm consists of 4 steps: removal of the horizontal, vertical and diagonal components of edges to reduce non-candidate point of line segments based on the chain code tracking of the edge map, removal of contiguous points, removal of the same angle points, and the extraction of the start and end points to be line segments. By comparing the proposed algorithm with Boldt algorithm, better results were obtained regarding the extraction of the representative line segments of buildings, having relatively less extraction of unnecessary line segments.