CMUNE: A clustering using mutual nearest neighbors algorithm

Abbas, Mohamed A.; Shoukry, Amin

doi:10.1109/isspa.2012.6310472

Cited by 14 publications

(14 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Determining k value is a very important and key issue in this algorithm, and wrong estimation of k value leads to error in defining neighborhood. kNN algorithm is a method for locating mutual decision region among the points, and the equation between them is defined based on similarity criterion (Abbas & Shoukry, 2012, Brito et al, 1997, Hu & Bhatnagar,. 2012, Sardana & Bhatnagar, 2014.…”

Section: Review Of Related Literaturementioning

confidence: 99%

Improving neighborhood construction with Apollonius region algorithm based on density for clustering

Pourbahrami

Khanli

Azimpour

2020

Information Sciences

View full text Add to dashboard Cite

Section: Review Of Related Literaturementioning

confidence: 99%

Improving neighborhood construction with Apollonius region algorithm based on density for clustering

Pourbahrami

Khanli

Azimpour

2020

Information Sciences

View full text Add to dashboard Cite

“…Therefore, to reduce the effect of non-text candidates, we propose Mutual Nearest Neighbor (MNN) clustering for grouping the text candidates that share common properties [32]. It is noted that character components in a text line usually share uniform color, size, and distance.…”

Section: Mutual Nearest Neighbor Clustering For Seed Cluster Detecmentioning

confidence: 99%

Multi-Spectral Fusion Based Approach for Arbitrarily Oriented Scene Text Detection in Video Images

Liang

Shivakumara

Lü

et al. 2015

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Scene text detection from video as well as natural scene images is challenging due to the variations in background, contrast, text type, font type, font size, and so on. Besides, arbitrary orientations of texts with multi-scripts add more complexity to the problem. The proposed approach introduces a new idea of convolving Laplacian with wavelet sub-bands at different levels in the frequency domain for enhancing low resolution text pixels. Then, the results obtained from different sub-bands (spectral) are fused for detecting candidate text pixels. We explore maxima stable extreme regions along with stroke width transform for detecting candidate text regions. Text alignment is done based on the distance between the nearest neighbor clusters of candidate text regions. In addition, the approach presents a new symmetry driven nearest neighbor for restoring full text lines. We conduct experiments on our collected video data as well as several benchmark data sets, such as ICDAR 2011, ICDAR 2013, and MSRA-TD500 to evaluate the proposed method. The proposed approach is compared with the state-of-the-art methods to show its superiority to the existing methods.

show abstract

“…Typical methods, such as CURE [6], Canopies[S] and CMune [7], divides the input dataset into small subsets to improve the performance. But the cluster ing performance is greatly dependent on the choice of different parameters.…”

Section: A Clustering For Large Datasetsmentioning

confidence: 99%

“…To further reduce the time complexity of the hierarchical clustering, many methods partition the large input dataset into small subsets [5], [6], [7]. Parallel and distributed computing frameworks have also been used to resolve such expensive computa tion of clustering algorithms for large datasets [8], [9].…”

Section: Introductionmentioning

confidence: 99%

NNB: An efficient nearest neighbor search method for hierarchical clustering on large datasets

Zhang

Wang

et al. 2015

Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)

View full text Add to dashboard Cite

Nearest neighbor search is a key tech nique used in hierarchical clustering. The time com plexity of standard agglomerative hierarchical clus tering is O(n3), while the time complexity of more advanced hierarchical clustering algorithms (such as nearest neighbor chain) is O(n2). This paper presents a new nearest neighbor search method called nearest neighbor boundary(NNB), which first divides a large dataset into independent subsets and then finds near est neighbor of each point in the subsets. When NNB is used, the time complexity of hierarchical cluster ing can be reduced to O(n log2 n). Based on NNB, we propose a fast hierarchical clustering algorithm called nearest-neighbor boundary clustering(NBC), and the proposed algorithm can also be adapted to the parallel and distributed computing frameworks. The experimental results demonstrate that our proposal algorithm is practical for large datasets. Index Terms-Hierarchical clustering, nearest neighbor boundary, parallel and distributed comput ing, Map Reduce

show abstract

CMUNE: A clustering using mutual nearest neighbors algorithm

Cited by 14 publications

References 4 publications

Improving neighborhood construction with Apollonius region algorithm based on density for clustering

Improving neighborhood construction with Apollonius region algorithm based on density for clustering

Multi-Spectral Fusion Based Approach for Arbitrarily Oriented Scene Text Detection in Video Images

NNB: An efficient nearest neighbor search method for hierarchical clustering on large datasets

Contact Info

Product

Resources

About