The goal of segmentation is to simplify and/or change the representation of an image into units that are easier to analyze. It is the process of assigning a label to every pixel in an image such that pixels with the same label share certain visual characteristics. A histogram based image segmentation method is presented which divides the whole image into sub regions based on two
Scanning and printing of documents can degrades their visibility that means it become difficult to understand them. Image binarization is the process of separation of pixel values into dual collections, black as foreground and white as background. Thresholding has created to be a well-known technique used for binarization of document images. Thresholding is further divide into the global and local thresholding technique. In document with uniform contrast delivery of background and foreground, global thresholding is has found to be best technique.
Moving object segmentation refers to the techniques that extract and locate the objects of interest in an image. There are some techniques that can be used to extract moving objects such as: optical flow, temporal differencing, and background subtraction. In between them background subtraction method is the common approach for identifying the moving objects in image sequences because of their flexibility and effectiveness. Background subtraction depends on subtracting the current image with the background image. Although when we are applying background subtraction method, we need to deal with some critical situations such as: illumination problem, noisy image, sudden change of light, small movements of non static objects etc.
More advanced methods have been used where global thresholding are combined with adaptive thresholding along with colour clustering (Ganster et al., 2001). A double thresholding techniques has also been proposed that claims to be the simplest, most accurate technique to date (Jain & Jain, 2012). The key parameters can be fixed by a fitted-curve of the RGB component histogram. Edge-based methods: This methods focusses on detecting edges on the contours of images. It however struggles when blurring and smooth transitions between skin and lesion leads to broken contours.
They have used smearing methods, horizontal projections, half transform. They first blur the image to enhance text line areas and then segment the images surface along several white paths in the blurred image. After they assign CCs of the original image to the appropriate line segment. They notice that most of them occurred when they had great variations in letter size. They could try and define locally the blurring window depending on a more local estimation of the average letter height.
This novel skin lesion segmentation algorithm is designed to be used for images taken by a digital camera. The segmentation algorithm uses a set of learned texture distributions and their texture distinctiveness metric (TD metric). The representative texture distributions used to identify pixels that belong to the lesion and skin classes and to find the border of the skin lesion. The proposed segmentation algorithm is referred to as the Texture Distinctiveness Lesion Segmentation
Correct image segmentation plays a major role in the realm of biomedical image processing by providing some typical practical assistance to the physicians. Such as it provide visual information to the general practitioner like diagnosis of disease and its advancement, anatomical construction and most importantly in surgical arrangement. Now a day’s Image processing is used to identify the brain tumor. According to the World Health Organization, every year more than 500,000 people undergo brain tumor treatment. A tumor is defined as a new growth which has the capability to attack the neighboring tissues which are placed at different locations.
CONCLUSION: We have implemented the scheme which is useful to improve results for clustering and identification of the face tracks, extracted from feature-length movie videos. This scheme may have better robustness to the noises in constructing affinity graphs than the traditional methods. We have mined the relationship between characters and provided a platform for character centered film
As shown in figure 1, first input samples are passed through a scanner to the system, where preprocessing converts the image into a form suitable for subsequent processing and feature extraction. Next stage is segmentation, where the input image is segmented into individual glyphs. This step separates out sentences from text and subsequently words and letters from sentences. Feature extraction black, extracts important features that forms a vital part of the recognition process. During training such data is stored in the database where, during classification, a character is placed in the appropriate class to which it belongs.
Segmentation of a text-document into lines, words and characters, is considered to be the crucial stage in Optical Character Recognition. The output of segmentation phase affects the overall recognition rate of the system. Segmentation is a big challenge in Sindhi OCR due to cursive nature of Sindhi. The Arabic text segmentation methods can be classified into two approaches Analytical Approach and Holistic Approach or Segmentation-Free