Image segmentation

Computer vision algorithms are natural candidates for high performance computing systems. Algorithms in computer vision are characterized by complex and repetitive operations on large amounts of data involving a variety of data interactions (e.g., point operations, neighborhood operations, global operations). In this paper, we describe the use of the custom computing approach to meet the computation and communication needs of computer vision algorithms. By customizing hardware architecture at the instruction level for every application, the optimal grain size needed for the problem at hand and the instruction granularity can be matched. A custom computing approach can also reuse the same hardware by reconfiguring at the software level for different levels of the computer vision application. We demonstrate the advantages of our approach using Splash 2-a Xilinx 4010-based custom computer.

This paper presents a new intensity-to-time processing paradigm suitable for very large scale integration (VLSI) computational sensor implementation of global operations over sensed images. Global image quantities usually describe images with fewer data. When computed at the point of sensing, global quantities result in a low-latency performance due to the reduced data transfer requirements between an image sensor and a processor. The global quantities also help global top-down adaptation: the quantities are continuously computed on-chip, and are readily available to sensing for adaptation. As an example, we have developed a sorting image computational sensor-a VLSI chip which senses an image and sorts all pixel by their intensities. The first sorting sensor prototype is a 21 2 2 2 26 array of cells. It receives an image optically, senses it, and computes the image's cumulative histogram-a global quantity which can be quickly routed off chip via one pin. In addition, the global cumulative histogram is used internally on-chip in a top-down fashion to adapt the values in individual pixel so as to reflect the index of the incoming light, thus computing an "image of indices." The image of indices never saturates and has a uniform histogram.

Page 1. Segmentation of Retinal Blood Vessels Based on the Second Directional Derivative and Region Growing M. Elena Martinez-Pkrez'; Alun D. Hughes2, Alice V. Stanton2, Simon A. Thorn2, Ani1 A. Bharath' and Kim H. Parker' ...

An offline cursive handwriting recognition system, based on hybrid of Neural Networks (NN) and Hidden Markov Models (HMM), is described in this paper. Applying SegRec principle, the recognizer does not make hard decision at the character segmentation process. Instead, it delays the character segmentation to the recognition stage by generating a segmentation graph that describes all possible ways to segment a word into letters. To recognize a word, the NN computes the observation probabilities for each segmentation candidates (SCs) in the segmentation graph. Then, using concatenated letter-HMMs, a likelihood is computed for each word in the lexicon by multiplying the probabilities over the best paths through the graph. We present in detail two approaches to train the word recognizer: 1). character-level training 2). word-level training. The recognition performances of the two systems are discussed. I.

In this paper an unsupervised colour image segmentation algorithm is presented. This method combines the advantages of the approaches based on split&merge and region growing, and the use of the RGB and HSV colour representation models. The effectiveness of the proposed method has been verified by the implementation of the algorithm using three different testing images with homogeneous regions, spatially compact and continuous. It was observed that the proposed algorithm outperforms the other analysed techniques requiring shorter processing time when compared with the other analysed methods.

We report our recent work on the recognition of scene text captured by mobile cameras, which we have named Kannada Pado. The text region is currently manually cropped using a user-friendly interface, which permits repeated croppings from the captured image in a hierarchical fashion. The scene text segment is then binarized using the algorithm, midline analysis, and propagation for segmentation. The segmented binary text image is recognized using Lipi Gnani Kannada OCR. The recognized text can be transcribed in Roman, Devanagari, and other principal Indian scripts. Such tools will be of immense use in metropolitan cities such as Bengaluru for business visitors and tourists to be able to read important textual information using their mobile itself. The entire implementation is of low computational complexity and hence, runs fully on the mobile itself, without any backend computation. Currently, text recognition accuracy is the bottleneck, which, when improved, will make the app immediately usable by people. Then, it will be made available to the public from Google Playstore.

Gait analysis has been an interesting area of research for several decades. In this paper, we propose imageflow-based methods to compute the motion and velocities of different body segments automatically, using a single inexpensive video camera. We then identify and extract different events of the gait cycle (double-support, mid-swing, toe-off and heel-strike) from video images. Experiments were conducted in which four walking subjects were captured from the sagittal plane. Automatic segmentation was performed to isolate the moving body from the background. The head excursion and the shank motion were then computed to identify the key frames corresponding to different events in the gait cycle. Our approach does not require calibrated cameras or special markers to capture movement. We have also compared our method with the Optotrak 3D motion capture system and found our results in good agreement with the Optotrak results. The development of our method has potential use in the markerless and unencumbered video capture of human locomotion. Monitoring gait in homes and communities provides a useful application for the aged and the disabled. Our method could potentially be used as an assessment tool to determine gait symmetry or to establish the normal gait pattern of an individual.

Automated blood vessel segmentation is an important issue for assessing retinal abnormalities and diagnoses of many diseases. The segmentation of vessels is complicated by huge variations in local contrast, particularly in case of the minor vessels. In this paper, we propose a new method of texture based vessel segmentation to overcome this problem. We use Gaussian and L * a * b * perceptually uniform color spaces with original RGB for texture feature extraction on retinal images. A bank of Gabor energy filters are used to analyze the texture features from which a feature vector is constructed for each pixel. The Fuzzy C-Means (FCM) clustering algorithm is used to classify the feature vectors into vessel or non-vessel based on the texture properties. From the FCM clustering output we attain the final output segmented image after a post processing step. We compare our method with hand-labeled ground truth segmentation of five images and achieve 84.37% sensitivity and 99.61% specificity.

A procedure to fuse the information of short-axis cine and late enhanced magnetic resonance images is presented. First a coherent 3D reconstruction of the images is obtained by objectbased interpolation of the information of contiguous slices in stacked short-axis cine acquisitions and by the correction of slice misalignments with the aid of a set of reference longaxis slices. Then, late enhanced stacked images are also interpolated and aligned with the anatomical information. Thus, the complementary information provided by both modalities is combined in a common frame of reference and in a nearly isotropic grid, which is not possible with existing fusion procedures. Numerical improvement is established by comparing the distances between unaligned and aligned manual segmentations of the myocardium in both modalities. Finally, a set of snapshots illustrate the improvement in the information overlap and the ability to reconstruct the gradient in the long-axis.

We present a novel use of GPUs (Graphics Processing Units) for the analysis of histopathological images of neuroblastoma, a childhood cancer. Thanks to the advent of modern microscopy scanners, whole-slide histopathological images can now be acquired but the computational costs to analyze these images using sophisticated image analysis algorithms are usually high. In this study, we have implemented previously developed image analysis algorithms using GPUs to exploit their outstanding processing power and memory bandwidth. The resulting GPU code was contrasted and combined with a C++ implementation on a multicore CPU to maximize parallelism on emerging architectures. Our codes were tested on different classes of images, with performance gain factors about 5.6x when the execution time of a Matlab code running on the CPU is compared with a code running jointly on CPU and GPU.

Image segmentation is a process by which an image is partitioned into regions with similar features. Many approaches have been proposed for color images segmentation, but Fuzzy C-Means has been widely used, because it has a good performance in a wide class of images. However, it is not adequate for noisy images and it takes longer runtimes, as compared to other method like K-means. For this reason, several methods have been proposed to improve these weaknesses. Methods like Fuzzy C-Means with Gustafson-Kessel algorithm (FCM-GK), which improve its performance against the noise, but increase significantly the runtime. In this paper we propose to use the centroids generated by GK-FCM algorithms as seeding for K-means algorithm in order to accelerate the runtime and improve the performance of K-means with random seeding. These segmentation techniques were applied to feature extraction on vineyard images. Segmented images were evaluated using several quality parameters such as the rate of correctly classified area and runtime.

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. ...

The rapid advancement of DNA microarray technology has revolutionalized genetic research in bioscience. Due to the enormous amount of gene expression data generated by such technology, computer processing and analysis of such data has become indispensable. In this paper, we present a computational framework for the extraction, analysis and visualization of gene expression data from microarray experiments. A novel, fully automated, spot segmentation algorithm for DNA microarray images, which makes use of adaptive thresholding, morphological processing and statistical intensity modeling, is proposed to: (i) segment the blocks of spots, (ii) generate the grid structure, and (iii) to segment the spot within each subregion. For data analysis, we propose a binary hierarchical clustering (BHC) framework for the clustering of gene expression data. The BHC algorithm involves two major steps. Firstly, the fuzzy C-means algorithm and the average linkage hierarchical clustering algorithm are used to split the data into two classes. Secondly, the Fisher linear discriminant analysis is applied to the two classes to assess whether the split is acceptable. The BHC algorithm is applied to the sub-classes recursively and ends when all clusters cannot be split any further. BHC does not require the number of clusters to be known in advance. It does not place any assumption about the number of samples in each cluster or the class distribution. The hierarchical framework naturally leads to a tree structure representation for effective visualization of gene expressions.

Video event detection (VED) is a challenging task especially with a large variety of objects in the environment. Even though there exist numerous algorithms for event detection, most of them are unsuitable for a typical consumer purpose. A hybrid method for detecting and identifying the moving objects by their color and spatial information is presented in this paper. In tracking multiple moving objects, the system makes use of motion of changed regions. In this approach, first, the object detector will look for the existence of objects that have already been registered. Then the control is passed on to an event detector which will wait for an event to happen which can be object placement or object removal. The object detector becomes active only if any event is detected. Simple training procedure using a single color camera in HSV color space makes it a consumer application. The proposed model has proved to be robust in various indoor environments and different types of background scenes. The experimental results prove the feasibility of the proposed method.

In this paper, we propose a new method for estimating the number of embedding changes for non-adaptive ±K embedding in images. The method uses a high-pass FIR filter and then recovers an approximate message length using a Maximum Likelihood Estimator on those stego image segments where the filtered samples can be modeled using a stationary Generalized Gaussian random process. It is shown that for images with a low noise level, such as decompressed JPEG images, this method can accurately estimate the number of embedding changes even for K = 1 and for embedding rates as low as 0.2 bits per pixel. Although for raw, never compressed images the message length estimate is less accurate, when used as a scalar parameter for a classifier detecting the presence of ±K steganography, the proposed method gave us relatively reliable results for embedding rates as low as 0.5 bits per pixel.

Image blur and noise are difficult to avoid in many situations and can often ruin a photograph. We present a novel image deconvolution algorithm that deblurs and denoises an image given a known shift-invariant blur kernel. Our algorithm uses local color statistics derived from the image as a constraint in a unified framework that can be used for deblurring, denoising, and upsampling. A pixel's color is required to be a linear combination of the two most prevalent colors within a neighborhood of the pixel. This two-color prior has two major benefits: it is tuned to the content of the particular image and it serves to decouple edge sharpness from edge strength. Our unified algorithm for deblurring and denoising out-performs previous methods that are specialized for these individual applications. We demonstrate this with both qualitative results and extensive quantitative comparisons that show that we can out-perform previous methods by approximately 1 to 3 DB.

In medical diagnosis and therapy, finding an appropriate method to evaluate the effect of various drugs is crucial. There are several ways to qualify a drug for a specific disease and one way is through medical image analysis. This process varies with the tissues we want to analyze and the imaging technique that is employed. For hydrous tissues such as nasal and trachea, Magnetic Resonance Imaging can be helpful for further evaluations. Trachea can be challenged by an antigen which will increase both nasal vascular permeability and intranasal pressure. Another effect of antigen challenge into nasal cavity which may cause nasal blockage, is swelling of nasal mucosa and a decrease in nasopharyngeal airway. In this paper, we study the effect of an antihistamine drug on swelling of mucosa. This antihistamine is called Azelastine and is injected to guinea pig to evaluate the swelling changes of nasal and trachea mucosa. After 20 minutes of injection, a MR image of the motionless animal is taken and this imaging will continue for 30, 40, 50 and 60 minutes from injection. Due to the ambiguous nature of respiratory tract, finding a precise method for processing has useful results. Watershed algorithm has widespread function in medical images but its defects in segmentation can be modified by different methods. An enhanced level set method is used here; a nonparametric active contour for nasal and trachea detection. This automatic image segmentation and tissue detection can help physicians evaluate the effect of a specific drug from medical images.

Motivated by the need to generate a pan-European coastline database from Landsat 7 ETM+ images, we present a new methodology for extracting automatically the coastline and its application to the entire European continent. Our approach consists of the combination of spectral and spatial information for the images using morphological image segmentation techniques. For these purposes several morphological segmentation algorithms were implemeted inside a GIS platform to evaluate their performance in coastline extraction. The results demonstrate the accuracy of the developed methodology and its applicability to a large area such as the European continent.

We present novel approaches for fully automated extraction of tree-like tubular structures from 3-D image stacks. A 4-D Open-Curve Active Contour (Snake) model is proposed for simultaneous 3-D centerline tracing and local radius estimation. An image energy term, stretching term, and a novel region-based radial energy term constitute the energy to be minimized. This combination of energy terms allows the 4-D open-curve snake model, starting from an automatically detected seed point, to stretch along and fit the tubular structures like neurites and blood vessels. A graph-based curve completion approach is proposed to merge possible fragments caused by discontinuities in the tree structures. After tree structure extraction, the centerlines serve as the starting points for a Fast Marching segmentation for which the stopping time is automatically chosen. We illustrate the performance of our method with various datasets.

The presented method addresses the problem of multi-spectral image segmentation. Multiple images of different modalities are used to improve segmentation, as better tissue separation can be achieved in a higher dimensional space. We use a model which takes into account the physical process of the medical image formation. In particular the method addresses the problem of partial volumes of tissues that are present in a single voxel at tissue boundaries. The parameters of the multi-dimensional tissue model are iteratively adjusted using an Expectation Maximisation (EM) optimisation technique. Bayes theory is used to generate probability maps for each segmented tissue which estimates the most likely tissue volume fraction within each voxel as opposed to previous approaches which attempt to compute how likely a certain grey level would be generated by a particular tissue class.

Computer vision systems attempt to recover useful information about the three-dimensional world from huge image arrays of sensed values. Since direct interpretation of large amounts of raw data by computer is difficult, it is often convenient to partition (segment) image arrays into low-level entities (groups of pixels with similar properties) that can be compared to higher-level entities derived from representations of world knowledge. Solving the segmentation problem requires a mechanism for partitioning the image array into low-level entities based on a model of the underlying image structure. Using a piecewise-smooth surface model for image data that possesses surface coherence properties, we have developed an algorithm that simultaneously segments a large class of images into regions of arbitrary shape and approximates image data with bivariate functions so that it is possible to compute a complete, noiseless image reconstruction based on the extracted functions and regions. Surface curvature sign labeling provides an initial coarse image segmentation, which is refined by an iterative region growing method based on variable-order surface fitting. Experimental results show the algorithm's performance on six range images and three intensity images.

Our previous works suggest that fractal texture feature is useful to detect pediatric brain tumor in multimodal MRI. In this study, we systematically investigate efficacy of using several different image features such as intensity, fractal texture, and level-set shape in segmentation of posterior-fossa (PF) tumor for pediatric patients. We explore effectiveness of using four different feature selection and three different segmentation techniques, respectively, to discriminate tumor regions from normal tissue in multimodal brain MRI. We further study the selective fusion of these features for improved PF tumor segmentation. Our result suggests that Kullback-Leibler divergence measure for feature ranking and selection and the expectation maximization algorithm for feature fusion and tumor segmentation offer the best results for the patient data in this study. We show that for T1 and fluid attenuation inversion recovery (FLAIR) MRI modalities, the best PF tumor segmentation is obtained using the texture feature such as multifractional Brownian motion (mBm) while that for T2 MRI is obtained by fusing level-set shape with intensity features. In multimodality fused MRI (T1, T2, and FLAIR), mBm feature offers the best PF tumor segmentation performance. We use different similarity metrics to evaluate quality and robustness of these selected features for PF tumor segmentation in MRI for ten pediatric patients.

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. ᭧

In this paper, a new algorithm for Automatic License Plate Localisation and Recognition (ALPR) is proposed on the basis of isotropic dilation that can be achieved using the binary image Euclidean distance transform. In a blob analysis problem, any two Region of Interest (RoIs) that is discontinuous are typically treated as separate blobs. However, the proposed algorithm combine with Connected Component Analysis (CCA) are coded to seek for RoI within a certain distance of other RoI to be treated as non-unique. This paper investigates the design and implementation of several pre-processing techniques and isotropic dilation algorithm to classify moving vehicles with different backgrounds and varying angles. A multi-layer feed-forward back-propagation Neural Network is used to train the segmented and refined characters. The results obtained can be used for implementation in the vehicle parking management system.

As the trends in mineral processing move towards the beneficiation of finer grained and more complex ore bodies, so too do the methods needed to understand and model these processes. During the heap leaching of low-grade ore bodies, the crack distribution and mineral dissemination in ore particles are important characteristics that determine the performance of sub-processes, such as the diffusion of reagents in and out of particle pores. Recent developments in X-ray computed tomography (CT) as an advanced diagnostic and nondestructive technique have indicated the potential for the technology to become a tool for the acquisition of 3-D mineralogical and structural data. The spatial distribution of cracks and mineral dissemination in particles derived from a sphalerite ore in the Northern Cape, South Africa, was characterized using a high-resolution industrial X-ray CT system. This paper describes the use of image analysis techniques including image segmentation, which uses a combination of thresholding and other methods to characterize and quantify crack and mineral dissemination in the sphalerite particles. The results are validated with those obtained using traditional techniques such as physical gas (with N 2) adsorption, mercury intrusion porosimetry, SEM and QEMSCAN. A comparison of the effect of different comminution devices (HPGR and Cone crusher) on crack generation is also given.

Texture identification in crops Automatic tasks in agriculture One important issue emerging strongly in agriculture is related with the automatization of tasks, where the optical sensors play an important role. They provide images that must be conveniently processed. The most relevant image processing procedures require the identification of green plants, in our experiments they come from barley and corn crops including weeds, so that some types of action can be carried out, including site-specific treatments with chemical products or mechanical manipulations. Also the identification of textures belonging to the soil could be useful to know some variables, such as humidity, smoothness or any others. Finally, from the point of view of the autonomous robot navigation, where the robot is equipped with the imaging system, some times it is convenient to know not only the soil information and the plants growing in the soil but also additional information supplied by global references based on specific areas. This implies that the images to be processed contain textures of three main types to be identified: green plants, soil and sky if any. This paper proposes a new automatic approach for segmenting these main textures and also to refine the identification of sub-textures inside the main ones. Concerning the green identification, we propose a new approach that exploits the performance of existing strategies by combining them. The combination takes into account the relevance of the information provided by each strategy based on the intensity variability. This makes an important contribution. The combination of thresholding approaches, for segmenting the soil and the sky, makes the second contribution; finally the adjusting of the supervised fuzzy clustering approach for identifying sub-textures automatically, makes the third finding. The performance of the method allows to verify its viability for automatic tasks in agriculture based on image processing.

A novel method of parametric active contours with geometric shape prior is presented in this paper. The main idea of the method consists in minimizing an energy function that includes additional information on a shape reference called a prototype. Shape prior introduced through a similarity measurement between evolving contour and Procrustes mean shape of desired object. This similarity measurement is full Procrustes distance between these two contours that is invariant with respect to similarity transformations (translation, scaling, and rotation). This extra shape knowledge enhances the model robustness to noise, occlusion and complex background. We also use gradient direction information in addition to gradient magnitude for more robustness to complex background. In this paper we introduce one important application of this new snake "3D object tracking". We obtain promising results for 3D object tracking which show the robustness of our method against noise, complex background, similarity transformations, occlusion, and changing viewpoint of 3D object.

Synthetic Aperture Radar (SAR) images are strongly corrupted by the speckle noise due to random electromagnetic waves interference. The speckle noise reduces the quality of images and makes their interpretation and analysis really difficult, so it's necessary to filter images to remove the noise in order to preserve as much as possible the most important features of the signals. To achieve this goal, in this paper we present an efficient method that reduces the speckle noise in SAR images, based on the Contourlet Transform (CT). The CT is a new image decomposition scheme that provides sparse representation of the data, constructed by combining two successive stages, applying in first a Laplacian pyramidal decomposition followed by a directional filter bank. This non-linear approach is designed to give a good representation of the geometrical content of the natural images. Recently, the Stationary version of the Contourlet Transform (SCT) has been proposed to preserve the shift-invariant property. In the present paper, we explore two different de-noising methods: the Bayesian Shrinkage based on a weighting factor that reduces noise by using the contourlet coefficients, and the Soft Thresholding based on the choice of the threshold that ensures adaptation to the noiseless signals. Hence, we present a comparative study of the results obtained through the SCT considering different stages of decomposition's levels and different kind of filters, and the Lee Adaptive Filter. A performance evaluation is realized to validate our methods.

Anatomical labeling of the cerebral arteries forming the Circle of Willis (CoW) enables inter-subject comparison, which is required for geometric characterization and discovering risk factors associated with cerebrovascular pathologies. We present a method for automated anatomical labeling of the CoW by detecting its main bifurcations. The CoW is modeled as rooted attributed relational graph, with bifurcations as its vertices, whose attributes are characterized as points on a Riemannian manifold. The method is first trained on a set of pre-labeled examples, where it learns the variability of local bifurcation features as well as the variability in the topology. Then, the labeling of the target vasculature is obtained as maximum a posteriori probability (MAP) estimate where the likelihood of labeling individual bifurcations is regularized by the prior structural knowledge of the graph they span. The method was evaluated by cross-validation on 50 subjects, imaged with magnetic resonance angiography, and showed a mean detection accuracy of 95%. In addition, besides providing the MAP, the method can rank the labelings. The proposed method naturally handles anatomical structural variability and is demonstrated to be suitable for labeling arterial segments of the CoW.

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.

Optical character recognition is perhaps the most studied application of pattern recognition. Recent work has increased accuracy in two ways. Combination of individual classifier outputs overcomes deficiencies of features and trainability of single classifiers. OCR systems take page images as input and output strings of recognized characters. Due to character segmentation errors, characters can be split or merged preventing output combination character-by-character. Merging of output strings is done using string alignment algorithms. 0-7803-4778-1 /98 $10.00 0 1998 IEEE

This work constitutes a theoretical study of the edge-detection method by means of the Jensen-Shannon divergence, as proposed by the authors. The overall aim is to establish formally the suitability of the procedure of edge detection in digital images, as a step prior to segmentation. In specific, an analysis is made not only of the properties of the divergence used, but also of the method's sensitivity to the spatial variation, as well as the detection-error risk associated with the operating conditions due to the randomness of the spatial configuration of the pixels. Although the paper deals with the procedure based on the Jensen-Shannon divergence, some problems are also related to other methods based on local detection with a sliding window, and part of the study is focused to noisy and textured images.

In this paper, we present an efficient coarse-tofine multiresolution framework for multidimensional scaling and demonstrate its performance on a large-scale nonlinear dimensionality reduction and embedding problem in a texture feature extraction step for the unsupervised image segmentation problem. We demonstrate both the efficiency of our multiresolution algorithm and its real interest to learn a nonlinear low-dimensional representation of the texture feature set of an image which can then subsequently be exploited in a simple clustering-based segmentation algorithm. The resulting segmentation procedure has been successfully applied on the Berkeley image database, demonstrating its efficiency compared to the best existing state-ofthe-art segmentation methods recently proposed in the literature.

Color-based region segmentation of skin lesions is one of the key steps for correctly collecting statistics that can help clinicians in their diagnosis. This study describes the use of differential evolution algorithm for segmentation of wounds on the skin. The abilities of differential evolution optimization algorithm, such as easiness, simple operations using, effectiveness and converging to global optimum reflected to wound image segmentation by using differential evolution algorithm in image segmentation. The system does not have the disadvantages of classical systems such as K-means clustering algorithm and the results obtained from different wound images have been discussed.

Breast Cancer is one of the significant reasons for death among ladies. Many research has been done on the diagnosis and detection of breast cancer using various image processing and classification techniques. Nonetheless, the disease remains as one of the deadliest disease. Having conceive one out of six women in her lifetime. Since the cause of breast cancer stays obscure, prevention becomes impossible. Thus, early detection of tumour in breast is the only way to cure breast cancer. Using CAD (Computer Aided Diagnosis) on mammographic image is the most efficient and easiest way to diagnosis for breast cancer. Accurate discovery can effectively reduce the mortality rate brought about by using mamma cancer. Masses and microcalcifications clusters are an important early symptoms of possible breast cancers. They can help predict breast cancer at it's infant state. The image for this work is being used from the DDSM Database (Digital Database for Screening Mammography) which contains approximately 3000 cases and is being used worldwide for cancer research. This paper quantitatively depicts the analysis methods used for texture features for detection of cancer. These texture featuresare extracted from the ROI of the mammogram to characterize the microcalcifications into harmless, ordinary or threatening. These features are further decreased using Principle Component Analysis(PCA) for better identification of Masses. These features are further compared and passed through Back Propagation algorithm (Neural Network) for better understanding of the cancer pattern in the mammography image.

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.

Coronary calcified plaque (CP) is both an important marker of atherosclerosis and major determinant of the success of coronary stenting. Intracoronary optical coherence tomography (OCT) with high spatial resolution can provide detailed volumetric characterization of CP. We present a semiautomatic method for segmentation and quantification of CP in OCT images. Following segmentation of the lumen, guide wire, and arterial wall, the CP was localized by edge detection and traced using a combined intensity and gradient-based level-set model. From the segmentation regions, quantification of the depth, area, angle fill fraction, and thickness of the CP was demonstrated. Validation by comparing the automatic results to expert manual segmentation of 106 in vivo images from eight patients showed an accuracy of 78 ± 9%. For a variety of CP measurements, the bias was insignificant (except for depth measurement) and the agreement was adequate when the CP has a clear outer border and no guide-wire overlap. These results suggest that the proposed method can be used for automated CP analysis in OCT, thereby facilitating our understanding of coronary artery calcification in the process of atherosclerosis and helping guide complex interventional strategies in coronary arteries with superficial calcification.

A new solution is proposed for 3D scene analysis in security and surveillance applications. It is based on binocular stereo-vision using a prediction-verification paradigm. Adaptive change-motion detection is performed at video rate to detect moving objects in the scene. 3D information is recovered by "scanning" the scene along parallel planes at different heights. Prediction of stereo correspondence is performed through

Iris recognition imaging constraints are receiving increasing attention. There are several proposals to develop systems that operate in the visible wavelength and in less constrained environments. These imaging conditions engender acquired noisy artifacts that lead to severely degraded images, making iris segmentation a major issue. Having observed that existing iris segmentation methods tend to fail in these challenging conditions, we present a segmentation method that can handle degraded images acquired in less constrained conditions. We offer the following contributions: 1) to consider the sclera the most easily distinguishable part of the eye in degraded images, 2) to propose a new type of feature that measures the proportion of sclera in each direction and is fundamental in segmenting the iris, and 3) to run the entire procedure in deterministically linear time in respect to the size of the image, making the procedure suitable for real-time applications.

Magnetic Resonance Imaging is a powerful technique that helps in the diagnosis of various medical conditions. MRI Image pre-processing followed by detection of brain abnormalities, such as brain tumors, are considered in this work. These images are often corrupted by noise from various sources. The Discrete Wavelet Transforms (DWT) with details thresholding is used for efficient noise removal followed by edge detection and threshold segmentation of the denoised images. Segmented image features are then extracted using morphological operations. These features are finally used to train an improved Support Vector Machine classifier that uses a Gausssian radial basis function kernel. The performance of the classifier is evaluated and the results of the classification show that the proposed scheme accurately distinguishes normal brain images from the abnormal ones and benign lesions from malignant tumours. The accuracy of the classification is shown to be 100% which is superior to the results reported in the literature. Keyword: Discrete wavelet transform support vector machine Classifier Feature extraction MRI brain image processing Image segmentation