9 Image Segmentation by Autoregressive Time Series Model
نویسندگان
چکیده
The objective of the image segmentation is to simplify the representation of pictures into meaningful information by partitioning into image regions. Image segmentation is a software technique to locate certain objects or boundaries within an image. There are many algorithms and techniques have been developed to solve image segmentation problems for the past 20 years, though, none of the method is a general solution. Among the best, they are neural networks segmentation, one-dimensional signal segmentation, multi-scale segmentation, model based segmentation, graphic partitioning, region growing and K-mean clustering segmentation methods. In this chapter, the newly developed Autoregressive (AR) time series model will be introduced for image segmentation. Time series statistical models such as Autoregressive Moving Average (ARMA) were considered useful in describing the texture and contextual information of an image. To simplify the computation, a two-dimensional (2-D) Autoregressive (AR) model was used instead. The 2-D AR time series model is particularly suitable to capture the rich image pixel contextual information. This model has been applied for both rough and smooth target surfaces and performed very well for image segmentation. In the typical statistical approach of image segmentation, there are two broad classes of segmentation procedures: The supervised and the unsupervised segmentation methods. The unsupervised segmentation procedure is the means by which pixels in the image are assigned to classes without prior knowledge of the existence or labeling of the classes. Whereas, in the supervised learning process, a teacher provides a label and cost function for each pattern in a training set and tries to minimize the sum of cost function for all patterns. Each method finds its own applications in the areas of the image analysis. The Support Vector Machine, a close cousin of classical multilayer perceptron neural networks and a newer supervised segmentation procedure, was adopted after feature extraction for single AR model image or pixel features vector extraction from multi-spectral image stack. On the other hand, the unsupervised region growing segmentation method was applied after univariate time series model was built. For the experimental results by applying the proposed AR time series segmentation model, the USC texture data set as well as satellite digital remote sensing image data are used. The algorithms performance comparisons with other existing contextual models such as Markov Random Field model, K-means, PCA, ICA ...etc can be found in reference (Ho, 2008).
منابع مشابه
Image Segmentation and Time Series Clustering Based on Spatial and Temporal ARMA Processes
Spatial autoregressive moving average (ARMA) processes have been extensively used in several applications in image/signal processing. In particular, these models have been used for image segmentation, edge detection and image filtering. Image restoration algorithms based on robust estimation of a two-dimensional process have been developed (Kashyap & Eom 1988). Also the two-dimensional autoregr...
متن کاملAn Improved Automatic EEG Signal Segmentation Method based on Generalized Likelihood Ratio
It is often needed to label electroencephalogram (EEG) signals by segments of similar characteristics that are particularly meaningful to clinicians and for assessment by neurophysiologists. Within each segment, the signals are considered statistically stationary, usually with similar characteristics such as amplitude and/or frequency. In order to detect the segments boundaries of a signal, we ...
متن کاملSegmentation for rock fractures based on ARMA model
Rock fracture mapping is very important in many applications related to rock mechanics. The toughest task is the extraction of the fractures from the images of the rocks. Time series model has been used in this paper for segmentation of fractures from the rock images. The model is compared with orthodox edge detection algorithms. A first order autoregressive image model has been implemented. Th...
متن کاملPulsative Flow Segmentation in MRA Image Series by AR Modeling and EM Algorithm
Segmentation of CSF and pulsative blood flow, based on a single phase contrast MRA (PC-MRA) image can lead to imperfect classifications. In this paper, we present a novel automated flow segmentation method by using PC-MRA image series. The intensity time series of each pixel is modeled as an autoregressive (AR) process and features including the Linear Prediction Coefficients (LPC), covariance ...
متن کاملCluster-Based Image Segmentation Using Fuzzy Markov Random Field
Image segmentation is an important task in image processing and computer vision which attract many researchers attention. There are a couple of information sets pixels in an image: statistical and structural information which refer to the feature value of pixel data and local correlation of pixel data, respectively. Markov random field (MRF) is a tool for modeling statistical and structural inf...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2012