&lt;title&gt;Optimal splitting technique for remote sensing satellite imagery data&lt;/title&gt;

Chaudhuri, Debasis; Mishra, Amit Kumar; Anand, S. K.; Gohri, V.

doi:10.1117/12.438244

Cited by 2 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So, the result obtained by the proposed algorithm is better than the result by Revol and Jourlin region growing method. 15 is shown in Fig. 5(b).…”

Section: Resultsmentioning

confidence: 99%

“…5(a)) are almost merged with the background. These black circular-shape objects are not segmented as separate objects from the background by algorithm 15 (Fig. 5(b)), where these objects are isolated from the background properly by ISODATA algorithm (Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Earlier an approach 15 was suggested for segmentation of remote sensing satellite imagery. Initially, seed point detection technique 15 was suggested.…”

Section: Algorithm: Splitting Techniquementioning

confidence: 99%

“…Earlier an approach 15 was suggested for segmentation of remote sensing satellite imagery. Initially, seed point detection technique 15 was suggested. The technique was based on mode (m), max d (maximum distance between the mode and the other gray-level values of a particular region) and Sd wrt mode.…”

Section: Algorithm: Splitting Techniquementioning

confidence: 99%

“…To capture the data of a nonconvex cluster, a novel, multi-seed clustering method was proposed by Chaudhuri and Chaudhuri 14 . Chaudhuri, et al 15 proposed a novel split-and-merge image segmentation technique to overcome the three basic characteristics non-parametric, highly overlapping, and non-Gaussian of remote sensing satellite imagery. A voting approach-based multi-seed supervised classification technique 16,17 is used to classify the image pixels into eight land cover types.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Split-and-merge Procedure for Image Segmentation using Bimodality Detection Approach

Chaudhuri¹,

Agrawal²

2010

DSJ

View full text Add to dashboard Cite

Image segmentation, the division of a multi-dimensional image into groups of associated pixels, is an essential step for many advanced imaging applications. Image segmentation can be performed by recursively splitting the whole image or by merging together a large number of minute regions until a specified condition is satisfied. The split-and-merge procedure of image segmentation takes an intermediate level in an image description as the starting cutest, and thereby achieves a compromise between merging small primitive regions and recursively splitting the whole images to reach the desired final cutest. The proposed segmentation approach is a split-andmerge technique. The conventional split-and-merge algorithm is lacking in adaptability to the image semantics because of its stiff quadtree-based structure. In this paper, an automatic thresholding technique based on bimodality detection approach with non-homogeneity criterion is employed in the splitting phase of the split-and-merge segmentation scheme to directly reflect the image semantics to the image segmentation results. Since the proposed splitting technique depends upon homogeneity factor, some of the split regions may or may not split properly. There should be rechecking through merging technique between the two adjacent regions to overcome the drawback of the splitting technique. A sequential-arrange-based or a minimal spanning-tree based approach, that depends on data dimensionality of the weighted centroids of all split regions for finding the pair wise adjacent regions, is introduced. Finally, to overcome the problems caused by the splitting technique, a novel merging technique based on the density ratio of the adjacent pair regions is proposed. The algorithm has been tested on several synthetic as well as real life data and the results show the efficiency of the segmentation technique.

show abstract

“…So, the result obtained by the proposed algorithm is better than the result by Revol and Jourlin region growing method. 15 is shown in Fig. 5(b).…”

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

“…Earlier an approach 15 was suggested for segmentation of remote sensing satellite imagery. Initially, seed point detection technique 15 was suggested.…”

Section: Algorithm: Splitting Techniquementioning

confidence: 99%

Section: Algorithm: Splitting Techniquementioning

confidence: 99%