-
Improving Satellite Image Segmentation Using Evolutionary Computation
Issue:
Volume 1, Issue 2, April 2013
Pages:
13-20
Abstract: Segmentation is the process of dividing an imageinto disjoint regions. It is the most important task in image processing where the success of the object recognition depends strongly on the efficiency of the segmentation process. The most popular and important segmentation methods are clustering such asFuzzy c-Means (FCM), Iterative Self-Organizing Data (ISODATA) and K-means. Clustering methods depends strongly on the selection of the initial spectral signatures which represents initial cluster centers. Normally, this is done either manually or randomly based on statisticaloperations.In either case the outcome is unpredictable and sometime inaccurate. In this paper an unsupervised method based on Multi-Objective Genetic Algorithm (MO-GA) for the selection of spectral signature from satellite images is implemented. The new method worksby maximizing the number of the selected pixels and bymaximizinghomogeneitythrough the minimizing of the dif-ference between the pixels and their spectral signature. The objective is to create best cluster centers as an initial population for any segmentation technique. Experimental results are conducted usinghigh resolution SPOT V satellite imageandthe verification of the segmentation results is basedon a very high resolution satellite image of type Quickbird. The spectral signatures provided to K-means and Fuzzy c-meansby MO-GA process increased the speed of theclustering algorithmto approximately4 timesthe speed of the random based selection of signatures.At the same time MO-GA improved the accuracy of the results of clustering algorithmstomore than 10% compared to the random statistical cluster centers selection methods.
Abstract: Segmentation is the process of dividing an imageinto disjoint regions. It is the most important task in image processing where the success of the object recognition depends strongly on the efficiency of the segmentation process. The most popular and important segmentation methods are clustering such asFuzzy c-Means (FCM), Iterative Self-Organizing ...
Show More
-
An Efficient Hybrid Classification System for High Resolution Remote Sensor Data
Roopesh Tamma,
T. Ch. Malleswara Rao,
G. Jaisankar
Issue:
Volume 1, Issue 2, April 2013
Pages:
21-32
Abstract: The classification of aerial and satellite remote sensing data has become a challenging problem due to the recent advances in remote sensor technology that led to higher spatial and spectral resolutions. This research paper presents novel sensor independent algorithms and techniques for dealing with the challenges of classification of high volume remote sensor data. A fast unsupervised band reduction method is proposed to lower the dimensionality of the input image. The band reduced image is then split into two mutually disjoint pure and mixed pixel subsets by a pixel segregator built using extended mathematical morphology techniques. A novel hierarchical spectral-spatial support vector machine based classifier that adaptively includes the usage of expensive spatial information based on the pixel categorization is proposed. The final thematic map is obtained after merging the classification results of the two subsets and fixed spatial neighborhood homogenization. The accuracy, efficiency and flexibility of the developed system are demonstrated by evaluating the classification results using several hyperspectral and multispectral data sets. The obtained results demonstrate that the proposed method performs significantly better than conventional classifiers while alleviating the computational complexity involved in generating spatial information.
Abstract: The classification of aerial and satellite remote sensing data has become a challenging problem due to the recent advances in remote sensor technology that led to higher spatial and spectral resolutions. This research paper presents novel sensor independent algorithms and techniques for dealing with the challenges of classification of high volume r...
Show More
-
Remote Mine Sensing Technology by Using IR Images
Nobuhiro Shimoi,
Yoshihiro Takita
Issue:
Volume 1, Issue 2, April 2013
Pages:
33-37
Abstract: This paper proposes an IR camera system that performs the task of removing mines for humanitarian purposes. Because of the high risks involved, it is necessary to conduct mine detection from the most remote endeavoring. By making use of infrared ray (IR) cameras, scattered mines can be detected from remote locations. In the case of mines buried in the ground, detection is possible if the peripheral temperature difference is large enough between the ground and mine weapon. Tests with trial mines were used to study the detection characteristics of IR cameras for images and various technologies for collecting and processing image data in real time for optimum mine detection.
Abstract: This paper proposes an IR camera system that performs the task of removing mines for humanitarian purposes. Because of the high risks involved, it is necessary to conduct mine detection from the most remote endeavoring. By making use of infrared ray (IR) cameras, scattered mines can be detected from remote locations. In the case of mines buried in ...
Show More
-
A New Approach for Automatic Fuzzy Clustering Applied to Magnetic Resonance Image Clustering
E. A. Zanaty,
Ashraf Afifi
Issue:
Volume 1, Issue 2, April 2013
Pages:
38-46
Abstract: Many clustering and segmentation algorithms suffer from the limitation that the number of clusters/segments is specified manually by human operators. It is often impractical to expect a human with sufficient domain knowledge to be available to select the number of clusters/segments to return. Thus, the estimation of optimal cluster number during the clustering process is our prime concern. In this paper, we introduce a new validity index method based on multi-degree entropy algorithm for determining the number of clusters automatically. This multi-degree entropy algorithm combines multi-degree immersion and entropy algorithms to partition an image into levels of intensity. The output of the multi-degree immersion processes are regions in which the interior does not contain any sharp grey value transitions, i.e. each level of intensity contains one or more regions of connected points or oversegmentation. These regions are passed to the entropy procedure to perform a suitable merging which produces the final number of clusters based on validity function criteria. Validity functions are used to find a relation between intra-cluster and inter-cluster variability, which is of course a reasonable principle. The latter process uses a region-based similarity representation of the image regions to decide whether regions can be merged. The proposed method is experimented on a discrete image example to prove its efficiency and applicability. The existing validation indices like PC, XB, and CE are evaluated and compared with the proposed index when applied on two simulation and one real life data. A direct benefit of this method is being able to determine the number of clusters for given application medical images.
Abstract: Many clustering and segmentation algorithms suffer from the limitation that the number of clusters/segments is specified manually by human operators. It is often impractical to expect a human with sufficient domain knowledge to be available to select the number of clusters/segments to return. Thus, the estimation of optimal cluster number during th...
Show More
-
A visual mining based fame work for classification accuracy estimation
Arun,
Pattathal Vijayakumar
Issue:
Volume 1, Issue 2, April 2013
Pages:
47-52
Abstract: Classification techniques have been widely used in different remote sensing applications and correct classi-fication of mixed pixels is a tedious task. The problem is more complex with the classification of hyperspectral data and requires a thorough analysis. Traditional approaches adopt various statistical parameters, however does not facilitate effective visualisation. Data mining tools are proving very helpful in the classification process. We propose a visual mining based frame work for accuracy assessment of classification techniques using open source tools such as WEKA and PREFUSE. These tools in integration can provide an efficient approach for getting information about improvements in the classification accuracy and helps in refining training data set. We have illustrated frame work for investigating the effects of various resampling methods on classification accuracy and found that bilinear (BL) is best suited for preserving radiometric characteristics. We have also investigated the optimal number of folds required for effective analysis of LISS4 images.
Abstract: Classification techniques have been widely used in different remote sensing applications and correct classi-fication of mixed pixels is a tedious task. The problem is more complex with the classification of hyperspectral data and requires a thorough analysis. Traditional approaches adopt various statistical parameters, however does not facilitate ...
Show More
-
Improved Region Growing Method for Magnetic Resonance Images (MRIs) Segmentation
Issue:
Volume 1, Issue 2, April 2013
Pages:
53-60
Received:
3 May 2013
Published:
30 May 2013
Abstract: Segmentation of magnetic resonance images (MRIs) is challenging due to the poor image contrast and artifacts that result in missing tissue boundaries, i.e. pixels inside the region and on the boundaries have similar intensity. In this paper, we adapt a region growing method to segment MRIs which contain weak boundaries between different tissues. The proposed region growing algorithm is developed to learn its homogeneity criterion automatically from characteristics of the region to be segmented. An automatic homogeneity criterion based on estimating probability of pixel intensities of a given image is described. The homogeneity criterions as well as the probability are calculated for each pixel. The proposed algorithm selects the pixels sequentially in a random walk starting at the seed point, and the homogeneity criterion is updated continuously. The proposed algorithm is applied to challenging applications: gray matter/white matter segmentation in magnetic resonance image (MRI) datasets. The experimental results show that the proposed technique produces accurate and stable results.
Abstract: Segmentation of magnetic resonance images (MRIs) is challenging due to the poor image contrast and artifacts that result in missing tissue boundaries, i.e. pixels inside the region and on the boundaries have similar intensity. In this paper, we adapt a region growing method to segment MRIs which contain weak boundaries between different tissues. Th...
Show More
