An efficient filling algorithm for counting regions

Geraets, W.G.M.; Daatselaar, A.N. van; Verheij, J G C

doi:10.1016/j.cmpb.2003.09.004

Cited by 21 publications

(12 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The module consisted of four major parts. The first part reduced noise and suppressed local contrasts due to holes in the implants (Geraets et al 2004). The next part searched for straight line segments approximating the implant contours.…”

Section: Methodsmentioning

confidence: 99%

Detecting bone loss along dental implants by subtraction of panoramic radiographs

Geraets¹,

Verheij²,

Wismeijer³

et al. 2011

Clinical Oral Implants Res

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Detecting bone loss along dental implants by subtraction of panoramic radiographs

Geraets¹,

Verheij²,

Wismeijer³

et al. 2011

Clinical Oral Implants Res

View full text Add to dashboard Cite

show abstract

“…After the SVM process, the decomposed full-waveform LIDAR data of the debris and residual ground points could be grouped into several species, including ground surface point-cloud, plastic point-cloud, paper point-cloud, cloth point-cloud, and metal point-cloud. The point-clouds obtained, except for the ground surface point-cloud, were further separated into individuals using spatial position information and a scanline seed fill algorithm 44 . Additionally, objects with points that were less than the threshold value were ignored to reduce misclassification on the edge of the objects ( Supplementary ).…”

Section: Methodsmentioning

confidence: 99%

Semi-automatic recognition of marine debris on beaches

Shi

Mei

et al. 2016

Sci Rep

View full text Add to dashboard Cite

An increasing amount of anthropogenic marine debris is pervading the earth’s environmental systems, resulting in an enormous threat to living organisms. Additionally, the large amount of marine debris around the world has been investigated mostly through tedious manual methods. Therefore, we propose the use of a new technique, light detection and ranging (LIDAR), for the semi-automatic recognition of marine debris on a beach because of its substantially more efficient role in comparison with other more laborious methods. Our results revealed that LIDAR should be used for the classification of marine debris into plastic, paper, cloth and metal. Additionally, we reconstructed a 3-dimensional model of different types of debris on a beach with a high validity of debris revivification using LIDAR-based individual separation. These findings demonstrate that the availability of this new technique enables detailed observations to be made of debris on a large beach that was previously not possible. It is strongly suggested that LIDAR could be implemented as an appropriate monitoring tool for marine debris by global researchers and governments.

show abstract

“…Then the seed fill algorithm [17] could fill two column and two row scan maps to obtain two column and two row connected graphs. The row connected graphs are merged to obtain a horizontal region map, and the column connected graphs are combined to obtain a vertical region map.…”

Section: Global Similarity Measurement Based On Edgementioning

confidence: 99%

Superpixel Segmentation Based on Global Similarity and Contour Region Transform

Luo

Xiong

Liu

et al. 2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

This letter proposes a new superpixel segmentation algorithm based on global similarity and contour region transformation. The basic idea is that pixels surrounded by the same contour are more likely to belong to the same object region, which could be easily clustered into the same superpixel. To this end, we use contour scanning to estimate the global similarity between pixels and corresponded centers. In addition, we introduce pixel's gradient information of contour transform map to enhance the pixel's global similarity to overcome the missing contours in blurred region. Benefited from our global similarity, the proposed method could adherent with blurred and low contrast boundaries. A large number of experiments on BSDS500 and VOC2012 datasets show that the proposed algorithm performs better than traditional SLIC.

show abstract

An efficient filling algorithm for counting regions

Cited by 21 publications

References 24 publications

Detecting bone loss along dental implants by subtraction of panoramic radiographs

Detecting bone loss along dental implants by subtraction of panoramic radiographs

Semi-automatic recognition of marine debris on beaches

Superpixel Segmentation Based on Global Similarity and Contour Region Transform

Contact Info

Product

Resources

About