A Brief Look at Image Segmentation

Mohammed El-Helly et al. [8] proposed an approach for integrating image analysis technique into diagnostic expert system. A diagnostic model was used to manage cucumber crop. According to this approach, an expert system finds out the diseases of user observation. In order to diagnose a disorder from a leaf image, five image processing phases are used: image acquisition, enhancement, and segmentation, feature extraction and classification. Images were captured using a high resolution color camera and auto focus illumination light. Firstly they transformed the defected RGB image to the HSI color space then analyzed the histogram intensity channel then increased the contrast of the image. Fuzzy C Means (FCM) segmentation is used in this

Medical image processing is the demanding task and emerging field. Medical imaging procedure will view the images that are present in internal portions of the human body for medical analysis. Automatic Brain tumor segmentation is a perceptive stage in medical field. In the MR images, the tumor part can be seen clearly by the accurate size and the correct measurement for the treatment. A necrotic part can be differentiated from the surrounding tissue. The automatic image segmentation algorithm, which exploit the information obtain from deducting tumor in brain MRI. Segmentation algorithm that will segment brain MR images into tumor, white matter, gray matter and cerebrospinal fluid separately. In this paper, improved automatic image segmentation

Normally, the automatic segmentation problem is very challenging and it is yet to be fully and satisfactorily solved. The aim of this tumor detection approach is to identify and segment the MRI tumor automatically. It takes into account the statistical features of the brain structure to represent it by significant feature points. Most of the early methods presented for tumor detection and segmentation may be broadly divided into three categories: region-based, edge-based and fusion of region and edge-based methods. Well known and widely used segmentation techniques are K-Means clustering algorithm, supervised method based on neural network classifier [4]. Also, the time spent to segment the tumor is getting reduced due to the detailed representation of the medical image by extraction of feature points. Region-based techniques look for the regions satisfying a given homogeneity criteria and edge based segmentation techniques look for edges between regions with different characteristics

Motta et al. [6] developed an automated segmentation method, which used thresholding based on highest temperature of the breast for the detection of lower border. Upper limit of region of interest (ROI) is obtained by detecting axilla. The center point of the segmented image is used for separating right and left breast. But in an asymmetric breast, the center point of the breast may not detect right and left breast ROI separation point.

Granular parakeratosis is a skin disease that is identified by brownish-red keratotic papules that can coalesce into plaques. This is a rare disorder of keratinization with a distinctive histology wherein parakeratosis with retention of keratohyaline granules is identified in the epidermis. An effective image processing system support vector machine can be potentially used to segment the lesions of granular parakeratosis. Image Segmentation is one of the important issues occurred in times of before computer visualization. The fundamental objective of image segmentation is to segment a picture into its constituent areas. This segmentation can be applied to skin disease like granular parakeratosis and later Support Virtual Machine

Abstract—A tumor is the growth in the abnormal tissue of the brain which causes damage to the other cells necessary for functioning. Detection of brain tumor is a difficult task, as there are various techniques involved in it. The active imaging resource used for brain tumor detection is Magnetic Resonance Imaging (MRI). It is necessary to use technique which can give the accurate location and size of the tumor. There are various algorithms proposed for brain tumor detection, this paper presents a survey on the various brain tumor detection algorithms. It gives the existing techniques and what are the advantages and disadvantages of these techniques.

Since medical imaging process requires to have a lot of experience, the aim of this project is designing a MATLAB program that is capable of sharpening image by edge-detection, simple moving average filter, and noise reduction among other features to make it easy for the physician to do it on its own. For this particular project the usage of Kernel matrixes and other Matlab functions will be required in order to obtain the desire outcome [3]. Some of these results will be obtained by using convolution and other build-in function. In addition, this program will be user friendly for the physicians and any other clinical member.

There are several approaches for extracting ROI in natural images like that are stated in [5] [6], but these techniques are not suitable for medical images. In [7], there are two methods of extracting ROI from medical images which are based on Mean square error and thresholding. But these methods do contains limitation like, the MSE approach require a reference image which is practically not

Preprocessing method involves series of operation to enhance and make it suitable for segmentation. Main function of preprocessing is removal of noise that is generated during image generation. Filters like min-max filter, Mean filter, Gaussian filter etc. may be used to remove noise. Binarization process is used to convert grayscale image into black and white image. To enhance the visibility and structural information Binary morphological operation is used. This involves opening, closing, thinning, hole filling etc. The captured image may not be perfectly aligned so, slant angle correction is performed. Input image may be resized according to the need of

This paper is about a selected few image processing applications. Optical Character Recognition is the translation of images of handwritten, typewritten or printed text into machine-editable text. Then I have introduced the captcha that we so frequently encounter in common websites. An algorithm trying to solve or break a captcha has been explained.

In this paper , the problem of identification of masses or tumors in the Magnetic Resonance Image (MRI) of Brain . Here a novel method of Power Law Transformation is introduced on the Brain Image. The gamma value for the Brain Image is fixed as 1.5 and thresholding is done. Thus the resulting binary image clearly separates any kind of tumors or a mass present in the brain images, and makes the identification process easier. By exhaustive experimentations it is found that the proposed algorithm is performs well than the literature. The experimentations is done with the Virtual Skeleton Database (VSD) which is a brain tumor image dataset obtained from Challenge on Multimodal Brain Tumor Segmentation with are the outcomes of BRATS2012 and BRATS2013. It is reported that the tumor in the brain is identified correctly in majority of cases and the efficiency of the proposed algorithm is 90% in case of normal images and 82.51% in case of multimodal images.

Abstract—Image captured by two-dimensional camera contains no depth information. However depth information is needed in many applications, for example in robotic vision, satellite imaging and target tracking. To extract depth information from images Stereo matching is used. The main aim of our project is to use stereo matching algorithms to plot the disparity map of segmented images which gives the depth information details. Particle Swarm Optimization and K-means algorithms are used for image segmentation. Our main objective is to implement stereo matching algorithms on the segmented images, compare the results of K-means and PSO on the basis of objective parameters such as PSNR, execution time, density of disparity map and compression ratio and perform subjective analysis of reconstructed 3-D images. The compared results show that the Particle Swarm Optimization algorithm gives better 3-D reconstructed image.

Abstract: In image processing, noise reduction and restoration of image is expected to improve the qualitative inspection of an image and the performance criteria of quantitative image analysis techniques Digital image is inclined to a variety of noise which affects the quality of image. The main purpose of de-noising the image is to restore the detail of original image as much as possible. The criteria of the noise removal problem depends on the noise type by which the image is corrupting .In the field of reducing the image noise several type of linear and non linear filtering techniques have been proposed . Different approaches for reduction of noise and image enhancement have been considered, each of which has their own limitation and advantages.

Abstract—The input CT image is processed out by Single Image Saliency. A Single image saliency is obtained by measuring the contrast and spatial cue of a CT image. The kernel for single image saliency is obtained by fusing contrast and spatial cue. This kernel matrix is convolved with the CT image in the saliency filter, there by improvising the image quality which is further used for tumor detection. The image obtained from the saliency filter is segmented into squared sub- regions from which mean and standard deviation are estimated from where the liver region is obtained. The same holds good for the detection of tumor region as well. The liver region is further processed by adaptive thresholding to identify the liver region, and this region is segmented by morphological operations and Region growing method. And the tumor region is finally segmented out by edge based active contour model using distance regularized level set evolution.

Here is a small tutorial that suffices you with the basic concepts required to put up eyes on your