Image segmentation

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.

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. ...

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.

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.

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.

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.

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.

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

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