Segmentation

South Florida's watersheds have endured a century of urban and agricultural development and disruption of their hydrology. Spatial characterization of South Florida's estuarine and coastal waters is important to Everglades' restoration programs. We applied Factor Analysis and Hierarchical Clustering of water quality data in tandem to characterize and spatially subdivide South Florida's coastal and estuarine waters. Segmentation rendered forty-four biogeochemically distinct water bodies whose spatial distribution is closely linked to geomorphology, circulation, benthic community pattern, and to water management. This segmentation has been adopted with minor changes by federal and state environmental agencies to derive numeric nutrient criteria.

Quality of life (QOL) has become a central issue of concern in peoples’ lives and the research on this topic has largely increased in the past decades. However, some studies on QOL only adopted objective indicators and QOL research is still very scarce in some fields of study such as tourism. Additionally, in tourism, the majority of the studies on QOL focus on assessing the QOL of residents of destinations and neglect segmentation based on QOL as a tool for market segmentation.
The aim of this study is to overcome some previously referred to limitations and, specifically: (i) to measure visitors’ perceptions of tourism impact on their QOL by adopting subjective indicators; and (ii) to segment visitors based on perceptions of tourism impact on their QOL.
Study results reveal that tourism is likely to have a more positive impact on the psychological and social domains of QOL and that QOL is a good basis for segmenting the tourism market. Visitors perceiving more positive tourism impacts in their QOL differ from others on several features such as motivations to travel, travel group, interaction with local residents and satisfaction with the trip.

In this paper, we propose a novel system for beard and mustache detection and segmentation in challenging facial images. Our system first eliminates illumination artifacts using the self-quotient algorithm. A sparse classifier is then used on these self-quotient images to classify a region as either containing skin or facial hair. We conduct experiments on the MBGC and color FERET databases to demonstrate the effectiveness of our proposed system.

Image registration (or alignment) is a useful preprocessing tool for assisting in manual data extraction from handwritten forms, as well as for preparing documents for batch OCR of specific page regions. A new technique is presented for fast registration of lined tabular document images in the presence of a global affine transformation, using the Discrete Fourier-Mellin Transform (DFMT). Each component of the affine transform is handled separately, which dramatically reduces the total parameter space of the problem. This method is robust and deals with all components of the affine transform in a uniform way by working in the frequency domain. The DFMT is extended to handle shear, which can approximate a small amount of perspective distortion. In order to limit registration to foreground pixels only, and to eliminate Fourier edge effects, a novel, locally adaptive foreground-background segmentation algorithm is introduced, based on the median filter, which eliminates the need for Blackman windowing as usually required by DFMT image registration. A novel information-theoretic optimization of the median filter is presented. An original method is demonstrated for automatically obtaining blank document templates from a set of registered document images.

This paper describe the one of the method of text extraction from visiting card images with fanciful design containing complicated color background and reverse contrast regions. The proposed method is based on edge detection followed by grouping of edges based on size, orientation and color attributes. After detecting edges of text from card we can apply image processing steps such as noise removal, segmentation to extract text from complex image. This text image can be recognized using OCR .We can design OCR using Artificial Neural Network. Some post processing like color identification and binarization will be helpful to get a pure binary text image for OCR. Keywords— OCR (Optical Character Recognition), Binarization, Segmentation

It is common practice to utilize evidence from biological and psychological vision experiments to develop computational models for low-level feature extraction. The receptive profiles of simple cells in mammalian visual systems have been found to closely resemble Gabor filters. ...

With increasingly higher numbers of non-English language web searchers the problems of efficient handling of non-English Web documents and user queries are becoming major issues for search engines. The main aim of this review paper is to make researchers aware of the existing problems in monolingual non-English Web retrieval by providing an overview of open issues. A significant number of

In this paper, we describe an intelligent signal analysis system employing the wavelet transformation towards solving vehicle engine diagnosis problems. Vehicle engine diagnosis often involves multiple signal analysis. The developed system first partitions a leading signal into small segments representing physical events or stateds based on wavelet mutli-resolution analysis. Second, by applying the segmentation result of the leading signal to the other signals, the detailed properties of each segment, including inter-signal relationships, are extracted to form a feature vector. Finally a fuzzy intelligent system is used to learn diagnostic features from a training set containing feature vectors extracted from signal segments at various vehicle states. The fuzzy system applies its diagnostic knowledge to classify signals as abnormal or normal. The implementation of the system is described and experiment results are presented.

In a chamber of the heart, large-scale vortices are shown to exist as the result of the dynamic blood flow and unique morphological changes of the chamber wall. As the cardiovascular flow varies over a cardiac cycle, there is a need for a robust quantification method to analyze its vorticity and circulation. We attempt to measure vortex characteristics by means of two-dimensional vorticity maps and vortex circulation. First, we develop vortex component analysis by segmenting the vortices using an data clustering algorithm before histograms of their vorticity distribution are generated. The next stage is to generate the statistics of the vorticity maps for each phase of the cardiac cycle to allow analysis of the flow. This is followed by evaluating the circulation of each segmented vortex. The proposed approach is dedicated to examining vortices within the human heart chamber. The vorticity field can indicate the strength and number of large-scale vortices in the chamber. We provide the results of the flow analysis after vorticity map segmentation and the statistical properties that characterize the vorticity components. The success of the cardiac measurement and analysis is illustrated by a case study of the right atrium. Our investigation shows that it is possible to utilize a data clustering algorithm to segment vortices after vorticity mapping, and that the vorticity and circulation analysis of a chamber vorticity can provide new insights into the blood flow within the cardiovascular structure.

Combining both spatial and intensity information in image, we present an MRI brain image segmentation approach based on multiresolution edge detection, region selection, and intensity threshold methods. The detection of white matter structure in brain is emphasized in this paper. First, a multi-resolution brain image representation and segmentation procedure based on a multi-scale image filtering method is presented. Given the nature of the structural connectivity and intensity homogeneity of brain tissues, region-based methods such as region growing and subtraction to segment the brain tissue structure from the multi-resolution images are utilized. From the segmented structure, the region-of-interest (ROI) image in the structure region is derived, and then a modified segmentation of the ROI based on an automatic threshold method using our threshold selection criterion is presented. Examples on both T1 and T2 weighted MRI brain image segmentation is presented, showing finer brain tissue structures. ᭧

Texture segmentation is one of the early steps towards identifying surfaces and objects in an image. Textures considered here are de ned in terms of primitives called tokens. In this paper we h a ve developed a texture segmentation algorithm based on the Voronoi tessellation. The algorithm rst builds the Voronoi tessellation of the tokens that make up the textured image. It then computes a feature vector for each V oronoi polygon. These feature vectors are used in a probabilistic relaxation labeling on the tokens, to identify the interior and the border regions of the textures. The algorithm has successfully segmented binary images containing textures whose primitives have identical second-order statistics and a n umber of gray level texture images.

Many desirable properties make fractals a powerful mathematic model applyied in several image processing and pattern recognition tasks: image coding, segmentation, feature extraction and indexing, just to cite some of them. Unfortunately, they are based on a strong asymmetric scheme, so suffering from very high coding times. On the other side, linear transfoms are quite time balanced, allowing to be usefully integrated in real-time applications, but they do not provide comparable performances with respect to the image quality for high bit rates. Owning to their potential for preserving the original image energy in a few coefficients in the frequency domain, linear transforms also known a widespread diffusion in some side applications such as to select representative features or to define new image quality measures. In this paper, we investigate different levels of embedding linear trasforms in the fractal coding scheme. Experimental results have been organized as to point out what is the contribution of each embedding step to the objective quality of the decoded image.

We present an approach for separating two speech signals when only one single recording of their linear mixture is available. For this purpose, we derive a filter, which we call the soft mask filter, using minimum mean square error (MMSE) estimation of the log spectral vectors of sources given the mixture's log spectral vectors. The soft mask filter's parameters are estimated using the mean and variance of the underlying sources which are modeled using the Gaussian composite source modeling (CSM) approach. It is also shown that the binary mask filter which has been empirically and extensively used in single channel speech separation techniques is, in fact, a simplified form of the soft mask filter. The soft mask filtering technique is compared with the binary mask and Wiener filtering approaches when the input consists of male+male, female+female, and male+female mixtures. The experimental results in terms of signal-to-noise ratio (SNR) and segmental SNR show that soft mask filtering outperforms binary mask and Wiener filtering.

In this paper, we propose a novel region-based active contour model for image segmentation. Our model incorporates the global and local information in the energy function, enabling efficient segmentation of images while accounting for intensity inhomogeneity. Another interesting property of the proposed model is its convexity, making it independent of the initial condition and hence ideal for an automatic segmentation. Furthermore, the energy function of the proposed model is minimized in a computationally efficient way by using the Chambolle method. Experimental results on natural and medical images demonstrate the performance of our model over the current state-of-the-art.

This article surveys deformable models, a promising and vigorously researched computer-assisted medical image analysis technique. Among model-based techniques, deformable models offer a unique and powerful approach to image analysis that combines geometry, physics, and approximation theory. They have proven to be effective in segmenting, matching, and tracking anatomic structures by exploiting (bottom-up) constraints derived from the image data together with (top-down) a priori knowledge about ...

Abstrak Kemampuan manusia untuk membedakan tekstur-tekstur yang berbeda secara perceptual merupakan permasalahan utama dalam visi mesin (machine vision) yang mengacu pada banyak pola tekstural dan kondisi iluminasi. Sehingga dalam beberapa dekade ini banyak dikembangkan penelitian teknik multiskala (multiscale) yang dapat mengisolasi daerah (region) yang mempunyai tekstur homogen secara perceptual dalam sebuah citra. Dari beberapa penelitian kebanyakan menggunakan citra gray-level yang mengabaikan unsur warna dari citra.Penelitian ini melakukan segmentasi citra berwarna berdasarkan karakteristik color-texture dengan menggunakan teknik multiskala, yaitu dengan menerapkan transformasi wavelet diskrit (Discrete Wavelet Transform) untuk mendapatkan region-region yang mempunyai tekstur yang homogen. Dalam metode ini, suatu citra disegmentasi dalam beberapa region dengan mengelompokkan (clustering) fitur color-texture yang diperhitungkan dari koefisien waveletnya. Percobaan dilakukan dengan menggunakan citra tekstur gray-level dan berwarna, serta citra riil. Dari hasil percobaan yang dilakukan, dapat dilihat bahwa hasil segmentasi region pada citra yang berwarna lebih dapat membedakan dua region yang mempunyai tekstur sama tetapi mempunyai warna yang agak berbeda. Pemilihan transformasi ruang warna juga mempengaruhi hasil segmentasi, dimana dari beberapa percobaan yang dilakukan transformasi ruang warna linier K-L (Karhunen-Loeve) memberikan hasil yang lebih baik dibandingkan transformasi ruang warna nonlinier HSV (Hue Saturation Value)

Recently, autonomous driving becomes a hot topic in research and industry area. Autonomous driving technology needs to perceive the semantic information of road scenes in the all-day and open environment. In this article, the semantic recognition of traffic scenes is studied using a deep learning network model, and a semantic representation model of road scenes is established. Besides, a semantic recognition algorithm of road scenes based on image data is proposed. Finally, a self-built data set is used to train the proposed model, and verified in the field of the test vehicle. It is found that the proposed method can quickly capture the perceptual road scene and over-performs better than traditional methods and demonstrated great potential to be used in road scene applications. INDEX TERMS Deep learning, environment awareness, road scene semantics, residual network.

Quantitative content analysis is increasingly used to surpass surface level analyses in computer-supported collaborative learning (eg, counting messages), but critical reflection on accepted practice has generally not been reported. A review of CSCL conference ...

This paper presents a new enhanced text extraction algorithm from degraded document images on the basis of the probabilistic models. The observed document image is considered as a mixture of Gaussian densities which represents the foreground and background document image components. The EM algorithm is introduced in order to estimate and improve the parameters of the mixtures of densities recursively. The initial parameters of the EM algorithm are estimated by the k-means clustering method. After the parameter estimation, the document image is partitioned into text and background classes by the means of ML approach. The performance of the proposed approach is evaluated on a variety of degraded documents comes from the collections of the National library of Tunisia.

Oil spill pollution plays a significant role in damaging marine ecosystem. Discharge of oil due to tanker accidents has the most dangerous effects on marine environment. The main waste source is the ship based operational discharges. Synthetic Aperture Radar (SAR) can be effectively used for the detection and classification of oil spills. Oil spills appear as dark spots in SAR images. One major advantage of SAR is that it can generate imagery under all weather conditions. However, similar dark spots may arise from a range of unrelated meteorological and oceanographic phenomena, resulting in misidentification. A major focus of research in this area is the development of algorithms to distinguish 'oil spills' from 'look-alikes'. The features of detected dark spot are then extracted and classified to discriminate oil spills from look-alikes. This paper describes the development of a new approach to SAR oil spill detection using Segmentation method and Artificial Neural Networks (ANN). A SAR-based oil-spill detection process consists of three stages: image segmentation, feature extraction and object recognition (classification) of the segmented objects as oil spills or look-alikes. The image segmentation was performed with Otsu method. Classification has been done using Back Propagation Network and this network classifies objects into oil spills or look-alikes according to their feature parameters. Improved results have been achieved for the discrimination of oil spills and look-alikes.

This paper presents a study highlighting the predictive performance of a radial basis function (RBF) network in estimating the grade of an offshore placer gold deposit. In applying the radial basis function network to grade estimation of the deposit, several pertinent issues regarding RBF model construction are addressed in this study. One of the issues is the selection of the RBF network along with its center and width parameters. Selection was done by an evolutionary algorithm that utilizes the concept of cooperative coevolutions of the RBFs and the associated network. Furthermore, the problem of data division, which arose during the creation of the training, calibration and validation of data sets for the RBF model development, was resolved with the help of an integrated approach of data segmentation and genetic algorithms (GA). A simulation study conducted showed that nearly 27% of the time, a bad data division would result if random data divisions were adopted in this study. In addition, the efficacy of the RBF network was tested against a feed-forward network and geostatistical techniques. The outcome of this comparative study indicated that the RBF model performed decisively better than the feed-forward network and the ordinary kriging (OK).

This paper presents a color object recognition scheme which proceeds in three sequential steps: segmentation, features extraction and classification. We mainly focus on the first and the third steps here. A color watershed using global and local criteria is first described. A color contrast value is defined to select the best color space for segmenting color objects. Then, an architecture of binary neural networks is described. Its properties relies on the simplification of the recognition problem, leading to a noticeable increase in the classification rate. We conclude with the abilities of such a recognition scheme and present an automated cell sorting system.

This paper presents a system for spoken term detection in a continuousspeech stream. Spoken terms are predefined through a set of acoustic examples provided by the users. Spoken term detection proceeds in two steps: speech segmentation and term verification. We suggest the use of an acoustic-based algorithm for the segmentation which exploits acoustic particularities of the speech stream to detect word frontiers. From the segmentation stage a collection of utterances are delimited, and they are aligned with the spoken term acoustic representation. Tests were conducted on an Arabic corpus using spectral features of the signal. A correct detection rate of about 100% was reached with a false alarm of 20%.

This paper sketches the author's research in nine areas related to speech translation: interactive disambiguation (two demonstrations of highly-interactive, broad-coverage speech translation are reported); system architecture; datastructures; the interface between speech recognition and analysis; the use of natural pauses for segmenting utterances; example-based machine translation; dialogue acts; the tracking of lexical co-occurrences; and the resolution of translation mismatches.

This paper addresses the problem of parametric representation and estimation of complex planar curves in 2-D, surfaces in 3-D and nonplanar space curves in 3-D. Curves and surfaces can be defined either parametrically or implicitly, and we use the latter representation. A planar curve is the set of zeros of a smooth function of two variables X-Y, a surface is the set of zeros of a smooth function of three variables X-~-Z, and a space curve is the intersection of two surfaces, which are the set of zeros of two linearly independent smooth functions of three variables X-!/-Z. For example, the surface of a complex object in 3-D can be represented as a subset of a single implicit surface, with similar results for planar and space curves. We show how this unified representation can be used for object recognition, object position estimation, and segmentation of objects into meaningful subobjects, that is, the detection of "interest regions" that are more complex than high curvature regions and, hence, more useful as features for object recognition. Fitting implicit curves and surfaces to data would be ideally based on minimizing the mean square distance from the data points to the curve or surface. Since the distance from a point to a curve or surface cannot be computed exactly by direct methods, the approximate distance, which is a first-order approximation of the real distance, is introduced, generalizing and unifying previous results. We fit implicit curves and surfaces to data minimizing the approximate mean square distance, which is a nonlinear least squares problem. We show that in certain cases, this problem reduces to the generalized eigenvector fit, which is the minimization of the sum of squares of the values of the functions that define the curves or surfaces under a quadratic constraint function of the data. This fit is computationally reasonable to compute, is readily parallelizable, and, hence, is easily computed in real time. In general, the generalized eigenvector lb provides a very good initial estimate for the iterative minimization of the approximate mean square distance. Although we are primarily interested in the 2-D and 3-D cases, the methods developed herein are dimension independent. We show that in the case of algebraic curves and surfaces, i.e., those defined by sets of zeros of polynomials, the minimizers of the approximate mean square distance and the generalized eigenvector fit are invariant with respect to similarity transformations. Thus, the generalized eigenvector lit is independent of the choice of coordinate system, which is a very desirable property for object recognition, position estimation, and the stereo matching problem. Finally, as applications of the previous techniques, we illustrate the concept of "interest regions"

The mammography is the most effective procedure for an early diagnosis of the breast cancer. The goal of segmentation is to detect abnormalities and to extract the entire suspicious mass region from mammograms. In this paper we have reviewed different segmentation methods of mammograms for the detection of breast cancer. Different segmentation methods are studied and their merits and drawbacks are outlined.

Segmentation of brain tumor from medical images is an interesting topic which is investigated by many researchers. It is important to locate tumor at an early stage so that it can be easily healed and can be used for further diagnosis. There are different imaging techniques which are used in segmentation of brain tumor. Among them, Magnetic Resonance Imaging (MRI) is most widely used radiological tool as it is radiation free in nature. For detecting the size, shape, and location of the tumor many segmentation algorithms were used. In this paper, an exhaustive study of brain tumor from MRI images has made by using different techniques. A comparative study and performance evaluation of different techniques based on certain performance metrics are also discussed in this paper.

Although it is well established in the academic literature that entrepreneurs share common traits, there has been limited research dedicated to evaluating psychographic profiles of the self-employed. Using the Nominal Group Technique, the authors gleaned insight from a panel of experts in an effort to segment the self-employed based on personality traits and the benefits they receive from an entrepreneurial career. The findings show that self-employed individuals can be classified into four distinct segments: Exemplars, Generals, Moms and Dads, and Altruists. Each group derives different benefits from self-employment. Understanding these benefits can greatly assist entrepreneurship educators and marketers of small business oriented products and services.

After collecting a data base of fingerprint images, we design a neural network algorithm for fingerprint recognition. When presented with a pair of fingerprint images, the algorithm outputs an estimate of the probability that the two images originate from the same finger. In one experiment, the neural network is trained using a few hundred pairs of images and its performance is subsequently tested using several thousand pairs of images originated from a subset of the database corresponding to 20 individuals. The error rate currently achieved is less than 0.5%. Additional results, extensions, and possible applications are also briefly discussed.

In this paper we present an instance based machine learning algorithm and system for real-time object classification and human action recognition which can help to build intelligent surveillance systems. The proposed method makes use of object silhouettes to classify objects and actions of humans present in a scene monitored by a stationary camera. An adaptive background subtracttion model is used for object segmentation. Template matching based supervised learning method is adopted to classify objects into classes like human, human group and vehicle; and human actions into predefined classes like walking, boxing and kicking by making use of object silhouettes.

The detection, recognition and classification of features in a digital image is an important component of quality control systems in production and process engineering and industrial systems monitoring, in general. In this paper, a new pattern recognition system is presented that has been designed for the specific task of monitoring the quality of sheet-steel production in a rolling mill. The system is based on using both the Euclidean and Fractal geometric properties of an imaged object to develop training data that is used in conjunction with a supervised learning procedure based on the application of a fuzzy inference engine. Thus, the classification method includes the application of a set of features which include fractal parameters such as the Lacunarity and Fractal Dimension and thereby incorporates the characterisation of an object in terms of texture that, in this application, has metallurgical significance. The principal issues associated with object recognition are presented including a new segmentation algorithm. The selflearning procedure for designing a decision making engine using fuzzy logic and membership function theory is also presented and a new technique for the creation and extraction of information from a membership function considered. The methods discussed, and the system developed, have a range of applications in 'machine vision' and automatic inspection. However, in this publication, we focus on the development and implementation of a surface inspection system designed specifically for monitoring surface quality in the manufacture of sheet-steel. For this publication, we include a demonstration version of the system which can be downloaded, installed and utilised by interested readers as discussed in Section VI.

The segmentation of an image can be considered as a preprocessing step for many of the algorithms such as object detection and identification. Many algorithms exist in the field of remote sensing for segmentation, in every case the desirable output of segmentation is a well defined region or features of object which can be distinguished from another. The desirable features include well based edges, gradients, textures etc. For a real world image the desirable features are difficult to identify. With the advancement of the high resolution imagery, the features which defined the object are too finely defined. It also contains noises which are due to fine edges, gradient variations and non-uniform textures. Segmentation algorithms are plenty in image processing which can be broadly categorized as edge based, color based and textured based. Edge based techniques fails due to the noise content. Textures are not uniform in real world images leading to problems of segmentation. Color based...

Clustering is a division of data into groups of similar objects. Representing the data by fewer clusters necessarily loses certain fine details, but achieves simplification. It models data by its clusters. Data modeling puts clustering in a historical perspective rooted in mathematics, statistics, and numerical analysis. From a machine learning perspective clusters correspond to hidden patterns, the search for clusters is unsupervised learning, and the resulting system represents a data concept. From a practical perspective clustering plays an outstanding role in data mining applications such as scientific data exploration, information retrieval and text mining, spatial database applications, Web analysis, CRM, marketing, medical diagnostics, computational biology, and many others. Clustering is the subject of active research in several fields such as statistics, pattern recognition, and machine learning. This survey focuses on clustering in data mining. Data mining adds to clustering the complications of very large datasets with very many attributes of different types. This imposes unique computational requirements on relevant clustering algorithms. A variety of algorithms have recently emerged that meet these requirements and were successfully applied to real-life data mining problems. They are subject of the survey.