Improved Image Segmentation Algorithm Research Articles

Image segmentation with boundary-to-pixel direction and magnitude based on watershed and attention mechanism

An improved image segmentation algorithm with boundary-to-pixel direction and magnitude (IS-BPDM) is proposed to deal with small regions segmentation while keeping the accuracy of edge segmentation. First, we develop a BPDM network embedded with watershed and attention module and use an adaptive loss function to learn each pixel’s robust and accurate BPDM which is defined as a two-dimensional vector, including direction and magnitude, and pointing from its nearest boundary pixel to itself. Then, we use the learned BPDMs to obtain the refined initial segmented regions by considering the pixels near boundary have shorter magnitude and near root pixels have longer magnitude, meanwhile adjacent pixels in different regions or nearby pixels on both sides of root pixel in same region have opposite directions and nearby pixels in same region have similar directions. Last, we utilize a fast grouping method according to direction similarity to combine these initial segmented regions into final segmentation. The experimental results show that compared with the state-of-the-art segmentation methods, the IS-BPDM approach proposed in this paper achieves better segmentation accuracy and high computational efficiency and outperforms in small regions segmentation on public datasets.

Thermally-induced mechanical degradation analysis of recycled aggregate concrete mixed with glazed hollow beads

The occurrence of fire often leads to the damage and deterioration of micro- and meso-structures of concrete materials, leading to the decomposition of hydrates, coarsening of porous structure, and thermal cracking induced by water vapor pressure, resulting in the decline of macro-physical and mechanical properties and durability. The meso-regulatory function of the lightweight, high-strength, internally porous and thermally stable glazed hollow beads (GHB) can improve the high-temperature resistance of concrete. In order to study the degradation characteristics of recycled aggregate concrete mixed with glazed hollow beads (RATIC), mechanical properties and internal meso-structural changes at high temperatures, the cube compressive strength test and CT test are carried. According to the improved image segmentation algorithm based on adaptive threshold and region growing methods, the influence of different recycled coarse aggregate (RCA) and GHB contents on the mesostructure of RATIC, such as thermal crack development and pore distribution, is systematically analyzed. Based on the self-compiled box dimension program, the corresponding relationship between compressive strength, fractal dimensions of mesostructure and temperature is obtained. The results reveal that the GHB can alleviate the stress concentration of coarse aggregates and cement paste caused by temperature expansion and deformation, provide a release channel for vapor pressure, alleviate cracks in the mortar area and pore boundaries, and slow down the spread of heat in the concrete. Overall, the GHB renders a positive effect on the heat-induced damage resistance of concrete.

Research on Local Feature Intelligent Extraction Algorithm of Blurred Image Under Complex Illumination Conditions

Traditionally, multi-label feature extraction algorithm is used to extract local features of blurred images under complex illumination conditions. The computational complexity is extremely high and the extraction efficiency is low. Therefore, in this paper, the local feature intelligent extraction algorithm for blurred images under complex illumination conditions is proposed. The improved image segmentation algorithm based on local fuzzy C-means clustering is used to cluster and segment the blurred images. The image feature recognition algorithm based on wavelet transform and LBP log domain feature extraction is adopted. The blurred image is transformed from the spatial domain to the logarithmic domain to make two-stage discrete wavelet decomposition, and the high-frequency component is used to reconstruct the original image to perform high-pass filtering on the blurred image. By filtering the low-frequency illumination component to compensate the complex illumination, the block LBP is used to extract the local texture features of the blurred image after illumination compensation. The experimental results on Yale-B face database show that the proposed algorithm can effectively extract the local features of blurred images under complex illumination conditions, and the maximum robustness of the algorithm is 0.44, the maximum value of feature extraction error rate is 0.25, and the maximum value of feature extraction speed growth rate is 96%, with high robustness, accuracy and extraction efficiency.

An improved image segmentation algorithm based on the maximum class variance method

Image segmentation is an important part of image processing. The result of image segmentation directly affects the effect of subsequent image processing. However the efficiency of the traditional maximum class variance method is low. This paper uses the cuckoo algorithm to optimize the traditional maximum class variance method to achieve a better segmentation effect. This image segmentation method combined with optimization theory can achieve the purpose of finding the optimal segmentation.

Improving image segmentation based on patch-weighted distance and fuzzy clustering

Image segmentation is the basis of image analysis, object tracking, and other fields. However, image segmentation is still a bottleneck due to the complexity of images. In recent years, fuzzy clustering is one of the most important selections for image segmentation, which can retain information as much as possible. However, fuzzy clustering algorithms are sensitive to image artifacts. In this study, an improved image segmentation algorithm based on patch-weighted distance and fuzzy clustering is proposed, which can be divided into two steps. First, the pixel correlation between adjacent pixels is retrieved based on patch-weighted distance, and then the pixel correlation is used to replace the influence of neighboring information in fuzzy algorithms, thereby enhancing the robustness. Experiments on simulated, natural and medical images illustrate that the proposed schema outperforms other fuzzy clustering algorithms.

Grasping Point Detection of Randomly Placed Fruit Cluster Using Adaptive Morphology Segmentation and Principal Component Classification of Multiple Features

Precise and rapid grasping point detection based on machine vision is one of the challenging problems in automatic sorting of randomly placed fruit clusters by robot. Grasping stalk of fruit cluster can improve grasping success probability and reduce fruit damage. For the problem that the segmentation of stalk candidates for randomly placed fruit cluster based on existing morphology algorithm tends to be low precision, an improved image segmentation algorithm based on adaptive morphology is proposed. According to edge distances defined based on minimum distance between edge point and unconnected components in minimum domain, the adaptive convolution kernel is constructed. In addition, a run analysis method with different and unordered labels is designed to reduce calculation time of edge distances. For the problem that it is difficult to describe and classify unconstraint stalk by existing features, an improved region classification algorithm based on principal components of multiple features is proposed. The descriptors based on features of object region are designed and principal components of multiple features are extracted based on variance contribution to improve precision and speed of stalk extraction. The proposed grasping point detection method of randomly placed fruit cluster based on improved morphology image segmentation and region classification algorithms is verified by experiments with grape clusters based on parallel robot sorting system. The results show that, compared with existing methods, the average precisions of segmentation and extraction for stalk increase by 9.89% and 2.17% respectively, the average precision and time of grasping point detection reach 94.50% and 2.01s respectively.

Ground Penetrating Radar Based Experimental Simulation and Signal Interpretation on Coal-Rock Interface Detection

Coal-rock interface recognition is one of the key unaddressed problems in unmanned mining condition. Therefore, it is important that efforts should be made to detect coal-rock interface. In the study, Ground Penetrating Radar (GPR) has been used as a non-contacting means for coal-rock detection. We first establish three layered model of coal-rock and give the mathematical analysis of this model. Then numerical simulation and field experiment are carried out. Finally, in order to interpret radar image, an improved image segmentation algorithm is proposed. The experimental results show that it is feasible to detect coal-rock interface by GPR and the improved algorithm is well to interpret radar image of coal-rock interface.

An Improved Image Segmentation Algorithm Based on Local Gaussian Distribution Fitting Energy Model

The active contours driven by local Gaussian distribution fitting (LGDF) energy segmentation method can effectively handle brain tumors and other medical image segmentation. But this method needs a manual initial contour and is more sensitive to the position of the initial contour. It may fail to segment the target image when the initial contours are inappropriate. Therefore, an improved method based on LGDF model is proposed. It combines the unsupervised learning algorithm of K-means clustering algorithm with the LGDF segmentation algorithm. First the K-means clustering algorithm is used to get the primary segmentation and make it as the initial contour position of LGDF model instead of a manual one. Then the LGDF model is used for fine segmentation based on the coarse segmentation of clustering algorithm so as to get an accurate segmentation result. The experimental results show that the proposed method could obtain segmentation automatically rather than manually labeling of the initial contour, and satisfied results are obtained with less calculation time.

High-temperature failure in asphalt mixtures using micro-structural investigation and image analysis

In this study, evaluating the effect of internal structure in asphalt mixture on high-temperature deformation is the main objective. Three asphalt mixture types, dense-graded asphalt concrete, superpave and stone mastic asphalt, which widely used as pavement were selected to investigate the internal structure at meso-scale level. The internal microstructures were established by X-ray computed tomography data, and three-dimensional models were processed by digital image processing technology. Adaptive threshold segmentation algorithm based on annular regions was improved, and then utilized to extract aggregates and air-voids from gray image. Meanwhile, the morphology and distribution of air-voids and aggregates were measured. Results indicate that the improved image segmentation algorithm segregates the target and background effectively. Air-voids can be extended into a macro cracks mainly because of the horizontal shear damage, but air-voids nearby the load action area are compressed and eliminated. The content and size of coarse aggregates have an obvious influence on high-temperature failure, compressive region and shear rheological region can be divided due to the different failure mechanism. Moreover, it is found that the position changes which horizontal displacement greater than vertical displacement of aggregate particles mainly appears in shear rheological region. The method developed in this paper is an effective tool to study high-temperature failure mechanisms of asphalt mixture.

An Improved Image Segmentation Algorithm in Automatic Light Communication System

Light Communication is one of the most common means of vessel communication, with merits of simple, easy-to-use, resistance to electromagnetic interference and so on. Compared with other means of vessel communication, the shortcomings of traditional lighting communication are highlighted, for example, it requires specialized training soldiers, and the information transfer rate is too low. In this paper, an automatic light receiver is presented, and an improved image segmentation algorithm in automatic light communication system is investigated. In the end, some conclusions are given to show the effectiveness of automatic light communication system and its particular application for military use.

An Image Segmentation Algorithm Based on Watershed Transform

An improved image segmentation algorithm based on watershed transform is presented In this paper. Firstly the normalized cut method and watershed transform are explained and analyzed. Secondly the idea of the improved algorithm and the main formula are explained. We consider the area and perimeter when we merge adjacent regions. We define a new weight value and discuss the value of the parameter α and β. Finally the experiment result is presented. The new algorithm reduces the nodes and the computational demand of the common normalized cut technique.

Remote Sensing Image Segmentation Based on Improved Statistical Region Merging

Statistical Region Merging (SRM) is an efficient image segmentation algorithm for images with noise and partial occlusion. However, due to the complexity of remote sensing image, SRM can’t give satisfactory results. This paper proposes an improved image segmentation algorithm for remote sensing image based on SRM. Firstly, 8-connexity gradient estimation models are used to obtain more precisely edges. Secondly, the dissimilarity criterion between regions is replaced by a normalized distance standard. Finally, it dynamically updates and sorts dissimilarity between regions during region merging. Experimental results show the proposed algorithm can achieve better segmentation results from coarse to fine compared with original SRM.

An Improved Image Segmentation Algorithm Based on GPU Parallel Computing

In the process of image segmentation, the classic Fuzzy C-Means (FCM) algorithm is time-consuming and depends heavily on initialization center. Based on Graphic Processing Unit (GPU), this paper proposes a novel FCM algorithm by improving the computational formulas of membership degree and the update criterion of cluster centers. Our algorithm can initialize cluster centers purposefully and further optimize them according to the analysis on the thread model of the graphic hardware. The compared experimental results with the classic FCM algorithm show that our algorithm has obvious superiority in improving image segmentation quality and efficiency.

Long-distance precision inspection method for bridge cracks with image processing

Abstract The detection of cracks is the most important step during the inspection of bridge substructures. However, traditional crack detection methods are subjective and expensive. Therefore, crack detection techniques based on image processing have been proposed. In this paper, a long-distance image acquisition device and an integrated image processing method are proposed for precisely extracting cracks. The proposed method consists of three parts. Firstly, general steps for crack extraction are realized which include image clipping, enhancement, smoothing, segmentation, crack marking and rotation. Secondly, the electronic distance measurement algorithm is approved to calculate the crack width in millimeters. Finally, an improved image segmentation algorithm based on C–V model is provided for crack extraction. We evaluate the proposed method on a collection of 1000 bridge images which have been gathered under different conditions. Experimental results show that the modified algorithm could effectively improve the detection precision rate and reduce the running time.

Improved image segmentation algorithm based on GrabCut

To solve the problem that GrabCut algorithm is sensitive to local noise,time consuming and edge extraction is not ideal,the paper put forward a new algorithm of improving image segmentation based on GrabCut.Multi-scale watershed was used for gradient image smoothing and denoising.Watershed operation was proposed again for the new gradient image,which not only enhanced image edge points,but also reduced the computation cost of the subsequent processing.Then the entropy penalty factor was used to optimize the segmentation energy function to prevent target information loss.The experimental results show that the error rate of the proposed algorithm is reduced,Kappa coefficient is increased and the efficiency is improved compared with the traditional algorithm.In addition,the edge extraction is more complete and smooth.The improved algorithm is applicable to different types of image segmentation.

Research on Improved Methods of Watershed Algorithm

In this paper an improved image segmentation algorithm based on watershed transform is presented. Firstly the normalized cut method and watershed transform are explained and analyzed. Secondly the idea of the improved algorithm and the main formula are explained. We consider the area and perimeter when we merge adjacent regions. We define a new weight value and discuss the value of the parameter αand β. Finally the experiment result is presented. The new algorithm reduces the nodes and the computational demand of the common normalized cut technique.

Improved fruit fuzzy clustering image segmentation algorithm based on visual saliency

Improved fruit fuzzy clustering image segmentation algorithm based on visual saliency

Recognition of the operational statuses of reagent addition using dynamic bubble size distribution in copper flotation process

The output PDF (probability density function) shape of surface bubble size in froth flotation is believed to be closely related to the operational statuses of reagent additions. An online operational status recognition method for quality evaluation of reagent addition is presented based on adaptive learning of the dynamic distribution features of the surface bubble size. We avoid the bubble over-segmentation problem by exploring an improved image segmentation algorithm to get the accurate bubble size statistics taking account of the local regional distribution of the image brightness value. By utilizing the kernel density estimation, we obtain the PDF and CDF (cumulative distribution function) of the bubble size statistics effectively. The distribution features of the bubble size statistics under the PDROS (pre-defined reagent operation statuses) are learned by FNC (furthest neighbor clustering), successively, the current health status of the reagent addition in the test time period is inferred by Bayesian inference according to the dynamic change of the bubble size PDFs; what is more, the statistical distribution features under PDROS are updated online according to the disturbance of the process operation conditions. This status recognition method is tested and practically applied in a copper ore beneficiation plant. The experimental results on the real production data demonstrate that this method outperforms other quasi machine vision based production condition recognition methods with much lower error recognition rate. It paves the way for the realization of an optimal control and fault diagnosis for reagent addition in the flotation process operation.

A New Normalized-Cut Image Segmentation Algorithm Based on Watershed Transform

In this paper an improved image segmentation algorithm based on watershed transform is presented. Firstly the normalized cut method and watershed transform are explained and analyzed. Secondly the idea of the improved algorithm and the main formula are explained. We consider the area and perimeter when we merge adjacent regions. We define a new weight value and discuss the value of the parameterαandβ. Finally the experiment result is presented. The new algorithm reduces the nodes and the computational demand of the common normalized cut technique.

Improved Image Segmentation Algorithm based on OTSU Algorithm

Improved Image Segmentation Algorithm based on OTSU Algorithm