Soft Segmentation Research Articles

Using Benefit Sought Variables for Soft Drinks Consumers Segmentation-Case Study City of Pristina

Soft drinks market is a very large and important market where competition is very fierce. In recent years this market in global terms has not greatly increased. Thus for all the actors of this market without understanding (recognition) of the customer/consumer, they may lose a market share from competitors given the fierce competition. The purpose of this study is the identification of market segments within the city of Prishtina regarding soft drinks consumers based on requiredbenefits /benefits sought. The result of this study supports the effectiveness of soft drinks consumer segmentation using the required benefit variables. Statistical Package for Social Science program ( SPSS version 20 ) was used for data analysis. This study used a descriptive analysis, factor analysis and cluster analysis. Based on differentiating factors in selecting soft drinks (refreshments), social-demographic variables and soft drinks consumer behavior throughout theses segments, the managers can modify their marketing strategies to fulfil the needs of these segments and at the same time maximize the profit.

Robust object tracking based on sparse representation and incremental weighted PCA

Object tracking plays a crucial role in many applications of computer vision, but it is still a challenging problem due to the variations of illumination, shape deformation and occlusion. A new robust tracking method based on incremental weighted PCA and sparse representation is proposed. An iterative process consisting of a soft segmentation step and a foreground distribution update step is adpoted to estimate the foreground distribution, cooperating with incremental weighted PCA, we can get the target appearance in terms of the PCA components with less impact of the background in the target templates. In order to make the target appearance model more discriminative, trivial and background templates are both added to the dictionary for sparse representation of the target appearance. Experiments show that the proposed method with some level of background awareness is robust against illumination change, occlusion and appearance variation, and outperforms several latest important tracking methods in terms of tracking performance.

Semisupervised Soft Mumford-Shah Model for MRI Brain Image Segmentation

One challenge of unsupervised MRI brain image segmentation is the central gray matter due to the faint contrast with respect to the surrounding white matter. In this paper, the necessity of supervised image segmentation is addressed, and a soft Mumford-Shah model is introduced. Then, a framework of semisupervised image segmentation based on soft Mumford-Shah model is developed. The main contribution of this paper lies in the development a framework of a semisupervised soft image segmentation using both Bayesian principle and the principle of soft image segmentation. The developed framework classifies pixels using a semisupervised and interactive way, where the class of a pixel is not only determined by its features but also determined by its distance from those known regions. The developed semisupervised soft segmentation model turns out to be an extension of the unsupervised soft Mumford-Shah model. The framework is then applied to MRI brain image segmentation. Experimental results demonstrate that the developed framework outperforms the state-of-the-art methods of unsupervised segmentation. The new method can produce segmentation as precise as required.

INTERLEAVED EM SEGMENTATION FOR MR IMAGE WITH INTENSITY INHOMOGENEITY

Expectation–maximization (EM) algorithm has been extensively applied in brain MR image segmentation. However, the conventional EM method usually leads to severe misclassifications MR images with bias field, due to the significant intensity inhomogeneity. It limits the applications of the conventional EM method in MR image segmentation. In this paper, we proposed an interleaved EM method to perform tissue segmentation and bias field estimation. In the proposed method, the tissue segmentation is performed by the modified EM classification, and the bias field estimation is accomplished by an energy minimization. Moreover, the tissue segmentation and bias field estimation are performed in an interleaved process, and the two processes potentially benefit from each other during the iteration. A salient advantage of the proposed method is that it overcomes the misclassifications from the conventional EM classification for the MR images with bias field. Furthermore, the modified EM algorithm performs the soft segmentation in our method, which is more suitable for MR images than the hard segmentation achieved in Li et al.'s12 method. We have tested our method in the synthetic images with different levels of bias field and different noise, and compared with two baseline methods. Experimental results have demonstrated the effectiveness and advantages of the proposed algorithm.

Color constancy using 3D scene geometry derived from a single image.

The aim of color constancy is to remove the effect of the color of the light source. As color constancy is inherently an ill-posed problem, most of the existing color constancy algorithms are based on specific imaging assumptions (e.g., gray-world and white patch assumption). In this paper, 3D geometry models are used to determine which color constancy method to use for the different geometrical regions (depth/layer) found in images. The aim is to classify images into stages (rough 3D geometry models). According to stage models, images are divided into stage regions using hard and soft segmentation. After that, the best color constancy methods are selected for each geometry depth. To this end, we propose a method to combine color constancy algorithms by investigating the relation between depth, local image statistics, and color constancy. Image statistics are then exploited per depth to select the proper color constancy method. Our approach opens the possibility to estimate multiple illuminations by distinguishing nearby light source from distant illuminations. Experiments on state-of-the-art data sets show that the proposed algorithm outperforms state-of-the-art single color constancy algorithms with an improvement of almost 50% of median angular error. When using a perfect classifier (i.e, all of the test images are correctly classified into stages); the performance of the proposed method achieves an improvement of 52% of the median angular error compared with the best-performing single color constancy algorithm.

Data-driven hair segmentation with isomorphic manifold inference

Hair segmentation is challenging due to the diverse appearance, irregular region boundary and the influence of complex background. To deal with this problem, we propose a novel data-driven method, named Isomorphic Manifold Inference (IMI). The IMI method assumes the coarse probability map and the binary segmentation map as a couple of isomorphic manifolds and tries to learn hair specific priors from manually labeled training images. For an input image, firstly, the method calculates a coarse probability map. Then it exploits regression techniques to obtain the relationship between the coarse probability map of the test image and those of training images. Finally, this relationship, i.e., a coefficient set, is transferred to the binary segmentation maps and a soft segmentation of the test image will be achieved by a linear combination of those binary maps. Further, we employ this soft segmentation as a shape cue and integrate it with color and texture cues into a unified segmentation framework. A better segmentation is achieved by the Graph Cuts optimization. Extensive experiments are conducted to validate effectiveness of the IMI method, compare contributions of different cues and investigate the generalization of IMI method. The results strongly encourage our method.

Understanding rental prices in the UK: a comparative application of spatial modelling approaches

Purpose– Accounting for locational effects in determining price is of fundamental importance. The demise of the mainstream property market has culminated in increasing appetite and investment activity within the private rental sector. The primary purpose of this paper aims to analyse the local variation and spatial heterogeneity in residential rental prices in a large urban market in the UK using various geo-statistical approaches.Design/methodology/approach– Applying achieved price data derived from a leading internet-based rental agency for Belfast Northern Ireland is analysed in a number of spatially based modelling frameworks encompassing more traditional approaches such as hedonic regressive models to more complex spatial filtering methods to estimate rental values as a function of the properties implicit characteristics and spatial measures.Findings– The principal findings show the efficacy of the geographically weighted regression (GWR) technique as it provides increased accuracy in predicting marginal price estimates relative to other spatial techniques. The results reveal complex spatial non-stationarity across the Belfast metropole emphasizing the premise of location in determining and understanding rental market performance. A key finding emanating from the research is that the high level of segmentation across localised pockets of the Belfast market, as a consequence of socio-political conflict and ethno-religious territoriality segregation, requires further analytical insight and model specification in order to understand the exogenous spatial and societal effects/implications for rental value.Originality/value– This study is one of only a few investigations of spatial residential rent price variation applying the GWR methodology, spatial filtering and other spatial techniques within the confines of a UK housing market. In the context of residential rent prices, the research highlights that a soft segmentation modelling approaches are essential for understanding rental gradients in a polarised ethnocratic city.

Scaling calibration in region of interest reconstruction with the 1D and 2D ATRACT algorithm

Recently, a reconstruction algorithm for region of interest (ROI) imaging in C-arm CT was published, named Approximate Truncation Robust Algorithm for Computed Tomography (ATRACT). Even in the presence of substantial data truncation, the algorithm is able to reconstruct images without the use of explicit extrapolation or prior knowledge. However, the method suffers from a scaling and offset artifact in the reconstruction. Hence, the reconstruction results are not quantitative. It is our goal to reduce the scaling and offset artifact so that Hounsfield unit (HU) values can be used for diagnosis. In this paper, we investigate two variants of the ATRACT method and present the analytical derivations of these algorithms in the Fourier domain. Then, we propose an empirical correction measure that can be applied to the ATRACT algorithm, to effectively compensate the scaling and offset issue. The proposed method is evaluated on ten clinical datasets in the presence of different degrees of artificial truncation. With the proposed correction approach, we achieved an average relative root-mean-square error (rRMSE) of 2.81% with respect to non-truncated Feldkamp, Davis, and Kress reconstruction, even for severely truncated data. The rRMSE is reduced to as little as 10% of the image reconstructed without the scaling calibration. The reconstruction results show that ROI reconstruction of high accuracy can be achieved since the scaling and offset artifact are effectively eliminated by the proposed method. With this improvement, the HU values may be used for post-processing operations such as bone or soft tissue segmentation if some tolerance is accepted.

Leveraging colour segmentation for upper-body detection

This paper presents an upper-body detection algorithm that extends classical shape-based detectors through the use of additional semantic colour segmentation cues. More precisely, candidate upper-body image patches produced by a base detector are soft-segmented using a multi-class probabilistic colour segmentation algorithm that leverages spatial as well as colour prior distributions for different semantic object regions (skin, hair, clothing, background). These multi-class soft segmentation maps are then classified as true or false upper-bodies. By further fusing the score of this latter classifier with the base detection score, the method shows a performance improvement on three different public datasets and using two different upper-body base detectors, demonstrating the complementarity of the contextual semantic colour segmentation and the base detector.

Soft Image Segmentation Based on the Mixture of Gaussians and the Phase-Transition Theory

In this paper, we propose a new soft multi-phase segmentation model where it is assumed that the pixel intensities are distributed as a Gaussian mixture. The model is formulated as a minimization problem through the use of the maximum likelihood estimator and phase-transition theory. The mixture coefficients, which are estimated using a spatially varying mean and variance procedure, are used for image segmentation. The experimental results indicate the effectiveness of the method.

A New Multiphase Soft Segmentation with Adaptive Variants

Soft segmentation is more flexible than hard segmentation. But the membership functions are usually sensitive to noise. In this paper, we propose a multiphase soft segmentation model for nearly piecewise constant images based on stochastic principle, where pixel intensities are modeled as random variables with mixed Gaussian distribution. The novelty of this paper lies in three aspects. First, unlike some existing models where the mean of each phase is modeled as a constant and the variances for different phases are assumed to be the same, the mean for each phase in the Gaussian distribution in this paper is modeled as a product of a constant and a bias field, and different phases are assumed to have different variances, which makes the model more flexible. Second, we develop a bidirection projected primal dual hybrid gradient (PDHG) algorithm for iterations of membership functions. Third, we also develop a novel algorithm for explicitly computing the projection fromRKto simplexΔK-1for any dimensionKusing dual theory, which is more efficient in both coding and implementation than existing projection methods.

AN EFFECTIVE FRAMEWORK FOR AUTOMATIC SEGMENTATION OF HARD EXUDATES IN FUNDUS IMAGES

In this paper, we propose an effective framework to automatically segment hard exudates (HEs) in fundus images. Our framework is based on a coarse-to-fine strategy, as we first get a coarse result allowed of some negative samples, then eliminate the negative samples step by step. In our framework, we make the most of the multi-channel information by employing a boosted soft segmentation algorithm. Additionally, we develop a multi-scale background subtraction method to obtain the coarse segmentation result. After subtracting the optical disc (OD) region from the coarse result, the HEs are extracted by a SVM classifier. The main contributions of this paper are: (1) propose an efficient and robust framework for automatic HEs segmentation; (2) present a boosted soft segmentation algorithm to combine multi-channel information; (3) employ a double ring filter to segment and adjust the OD region. We perform our experiments on the pubic DIARETDB1 dateset, which consists of 89 fundus images. The performance of our algorithm is assessed on both lesion-based criterion and image-based criterion. Our experimental results show that the proposed algorithm is very effective and robust.

Non-interactive automatic video segmentation of moving targets

Extracting moving targets from video accurately is of great significance in the field of intelligent transport. To some extent, it is related to video segmentation or matting. In this paper, we propose a non-interactive automatic segmentation method for extracting moving targets. First, the motion knowledge in video is detected with orthogonal Gaussian-Hermite moments and the Otsu algorithm, and the knowledge is treated as foreground seeds. Second, the background seeds are generated with distance transformation based on foreground seeds. Third, the foreground and background seeds are treated as extra constraints, and then a mask is generated using graph cuts methods or closed-form solutions. Comparison showed that the closed-form solution based on soft segmentation has a better performance and that the extra constraint has a larger impact on the result than other parameters. Experiments demonstrated that the proposed method can effectively extract moving targets from video in real time.

Colorization and Automated Segmentation of Human T2 MR Brain Images for Characterization of Soft Tissues

Characterization of tissues like brain by using magnetic resonance (MR) images and colorization of the gray scale image has been reported in the literature, along with the advantages and drawbacks. Here, we present two independent methods; (i) a novel colorization method to underscore the variability in brain MR images, indicative of the underlying physical density of bio tissue, (ii) a segmentation method (both hard and soft segmentation) to characterize gray brain MR images. The segmented images are then transformed into color using the above-mentioned colorization method, yielding promising results for manual tracing. Our color transformation incorporates the voxel classification by matching the luminance of voxels of the source MR image and provided color image by measuring the distance between them. The segmentation method is based on single-phase clustering for 2D and 3D image segmentation with a new auto centroid selection method, which divides the image into three distinct regions (gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) using prior anatomical knowledge). Results have been successfully validated on human T2-weighted (T2) brain MR images. The proposed method can be potentially applied to gray-scale images from other imaging modalities, in bringing out additional diagnostic tissue information contained in the colorized image processing approach as described.

A Fast Method for Segmenting Images with Additive Intensity Value

The soft additive segmentation model attempts to solve the problem related to the segmentation of overlapping objects with additive intensity value. An issue in optimizing the soft additive segmentation functional is that a high-order nonlinear partial differential equation needs to be solved, which, for most standard algorithms, involves high computational cost. In this paper, we propose a fast and efficient numerical algorithm to optimize the soft additive segmentation model. We reformulate the original minimization problem into a sequence of simpler minimization problems that can be solved efficiently by using the augmented Lagrangian method. Numerical tests on real and synthetic cases are presented to demonstrate the efficiency of our algorithm.

Consistent segmentation using a Rician classifier.

Several popular classification algorithms used to segment magnetic resonance brain images assume that the image intensities, or log-transformed intensities, satisfy a finite Gaussian mixture model. In these methods, the parameters of the mixture model are estimated and the posterior probabilities for each tissue class are used directly as soft segmentations or combined to form a hard segmentation. It is suggested and shown in this paper that a Rician mixture model fits the observed data better than a Gaussian model. Accordingly, a Rician mixture model is formulated and used within an expectation maximization (EM) framework to yield a new tissue classification algorithm called Rician Classifier using EM (RiCE). It is shown using both simulated and real data that RiCE yields comparable or better performance to that of algorithms based on the finite Gaussian mixture model. As well, we show that RiCE yields more consistent segmentation results when used on images of the same individual acquired with different T1-weighted pulse sequences. Therefore, RiCE has the potential to stabilize segmentation results in brain studies involving heterogeneous acquisition sources as is typically found in both multi-center and longitudinal studies.

A new fast multiphase image segmentation algorithm based on nonconvex regularizer

We present a new variational model for the soft multiphase image segmentation. In the model, we introduce a nonconvex regularizer on the membership functions which are used as indicators of different homogeneous regions. The nonconvex regularizer performs better than the usual convex ones in that (i) it well preserves geometric shapes of the homogeneous regions, and (ii) it protects edges from oversmoothing which is a common drawback of the convex regularizer. To solve the nonconvex minimization problem, we design a new fast alternative iteration algorithm, which is robust to the setting of the parameters in the model. We conduct comprehensive experiments to measure the performance of the algorithm in terms of visual evaluation and a variety of quantitative indices for image segmentation. The algorithm achieves more accurate results compared to other well-known convex variational methods for image segmentation.

A new stochastic variational PDE model for soft Mumford–Shah segmentation

In this paper, a new stochastic variational PDE model is developed, using instead of hard segmentation soft segmentation. In this way, each pixel is allowed to belong to each image pattern with some probability. Our work proposes a functional with variable exponent, which provides a more accurate model for image segmentation and denoising. The diffusion resulting from the proposed model is a combination between TV-based and isotropic smoothing. The modeling procedure, computational implementation and results are explored in detail and numerical examples of real and synthetic images are presented.

Phoneme and tonal accent recognition for Thai speech

In this paper, we investigate the application of a phoneme recognition system with a soft phoneme segmentation procedure for Thai speech. In addition, we propose a new method to classify the tonal accent of a syllable. The recognition system classifies Thai phonemes, including the 21-class initial consonants, the 18-class vowels, and the 9-class final consonants, using discrete hidden Markov models. Two features, i.e., the Mel frequency with perceptual linear prediction and the Mel frequency cepstrum coefficients, are compared to investigate their utilities in phoneme recognition. Neural networks are applied to classify the 5-class tonal accents by using the temporal variation of pitch frequencies across syllables as features. Speaker-dependent and speaker-independent data sets recorded from 30 speakers are used to test our recognition system. The experimental results show promising recognition performances for the phonemes and tonal accents in both data sets.

Colorization based on soft segmentation

This paper proposes a new colorization method based on the chrominance blending. The weights for the blending are com- puted by using the random walker algorithm, which is a soft segmen- tation technique that provides sharp probability transition on object boundaries. As a result, the proposed method reduces color bleed- ing and provides improved colorization performances compared to conventional ones. © 2011 SPIE and IS&T. (DOI: 10.1117/1.3565470)