Human vision inspired multi-scale line segments merging and filtering

Zheng, Xiaoxu; Chen, Xiang; Lu, Huchuan; Chen, Ben M.; Lee, Tong Heng

doi:10.1109/icca.2018.8444314

Cited by 1 publication

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are robust to noisy LSs and can be adopted to build a strong probabilistic model such as the Helmholtz principle, but are not as discriminating as geometric constraints. The limitations of some existing LS merging techniques [28], [30], [31] can be understood in relation to these constrains as such algorithms use part or all of the geometric constraints without an efficient validation step (constraint 4 and 5), leading to incorrect merging, as shown in Fig. 3.…”

Section: Line Segment Grouping Rulesmentioning

confidence: 99%

PLSD: A Perceptually Accurate Line Segment Detection Approach

Cheng

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Most existing line segment detection methods suffer from the over-segmentation phenomenon. An improved line segment detection method is presented in this work, which can generate more and longer line segments, yet still accurately reflect the structural details of the image. Line segment grouping, line segment validation and a multiscale framework are adopted to reach this end. Specifically, smart grouping rules are introduced to locate potential homologous line segments (derived from the same boundaries). Novel merging criteria based on Helmholtz principle is then used to evaluate the meaningfulness between separate line segments and their merged ones. The improved multiscale framework facilitates line segments merging in detection and post-detection processes, yielding more high-quality line segments. Finally, the proposed method is compared with four leading methods on the famous public dataset, YorkUrban-LineSegment. Experimental results demonstrate that the method has good continuity and outperforms the leading methods in F-measure.

show abstract

Section: Line Segment Grouping Rulesmentioning

confidence: 99%

PLSD: A Perceptually Accurate Line Segment Detection Approach

Cheng

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

Human vision inspired multi-scale line segments merging and filtering

Cited by 1 publication

References 28 publications

PLSD: A Perceptually Accurate Line Segment Detection Approach

PLSD: A Perceptually Accurate Line Segment Detection Approach

Contact Info

Product

Resources

About