Moment based image segmentation
MetadataShow full item record
Usually, digital image of scene is not same as actual; it may degrade because of environment, camera focus, lightening conditions, etc. Segmentation is the key step before performing other operations like description, recognition, scene understanding, indexing, etc. Image segmentation is the identification of homogeneous regions in the image. This is accomplished by segmenting an image into subsets and later assigning the individual pixels to classes. There are various approaches for segmentation to identify the object and its spatial information. These approaches employ some features of the input image(s). The concept of feature is used to denote a piece of information which is relevant for solving the computational task related to a certain application. The moment is an invariant feature used in the pattern recognition field to recognize the test object from the database. The key point of using moment is to provide a unique identification for each object irrespective of its transformations. The moment is the weighted average intensity of pixels. It is used for object recognition so far. Now the idea is to use moment in object classification field. The propose method is to compute Set of Moments as a feature for each pixel to get information of the image. This information can be used further in its detail analysis or decision making systems by classification techniques. Moment requires an area to compute it. Hence, window based method is used for each pixel in the image. All possible windows have been defined in which current pixel is placed at different positions and moment is computed for each window representation. The moments define a relationship of that pixel with its neighbors. The set of moments computed will be feature vector of that pixel. After obtaining the feature vector of pixels, k-means classification technique is used to classify these vectors in k number of classes. The different types of moments are used to classify the images namely: Statistical, Geometric, Legendre moments. Experiments are performed using moments with different window sizes to analyze their effect on execution time and other features. The comparative study is performed on various moments using different window sizes. The comparison is done using mismatching between moments, window sizes and their computation time. The implementation is also performed on noisy images. The results conclude that the proposed method probably gives better result than pixel based classification. The Statistical moment gives better result as compared to Geometric and Legendry moment. Its computation time is also less because it does not involve polynomial function in computation. The window size also affects the segmentation. The small window size preserves edge information in segmented image. The computation time and noise tolerance of proposed algorithm also increases as window size increases. Hence, the selections of window size have trade between computation time and image quality. All the experiments have been performed on both gray and colour scale images in MATLAB(R).
- M Tech Dissertations