An improved Douglas-Peucker algorithm for fast curve approximation

Li, Lelin; Jiang, Wanshou

doi:10.1109/cisp.2010.5647972

Cited by 12 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To make the process more robust, we ensured that the resulting contour is a rectangle. This was done by approximating the contour using the Douglas–Peucker algorithm, 31 , 32 ensuring that the contour consisted of four lines even when the frame was cut off or other artifacts were obstructing the frame. Next, we checked the angles between the four lines of the approximated contour, ensuring that it was at least close to a rectangle.…”

Section: Methodsmentioning

confidence: 99%

HIOP-Reader: Automated Data Extraction for the Analysis of Manually Recorded Nycthemeral IOPs and Glaucoma Progression

Agorastou

Schön

Verma-Fuehring

et al. 2022

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

Purpose Nycthemeral (24-hour) intraocular pressure (IOP) monitoring in glaucoma has been used in Europe for more than 100 years to detect peaks missed during regular office hours. Data supporting this practice are lacking, because it is difficult to correlate manually drawn IOP curves to objective glaucoma progression. To address this, we developed an automated IOP data extraction tool, HIOP-Reader. Methods Machine learning image analysis software extracted IOP data from hand-drawn, nycthemeral IOP curves of 225 retrospectively identified patients with glaucoma. The relationship between demographic parameters, IOP, and mean ocular perfusion pressure (MOPP) data to spectral-domain optical coherence tomography (SDOCT) data was analyzed. Sensitivities and specificities for the historical cutoff values of 15 mm Hg and 22 mm Hg in detecting glaucoma progression were calculated. Results Machine data extraction was 119 times faster than manual data extraction. The IOP average was 15.2 ± 4.0 mm Hg, nycthemeral IOP variation was 6.9 ± 4.2 mm Hg, and MOPP was 59.1 ± 8.9 mm Hg. Peak IOP occurred at 10 am and trough at 9 pm . Progression occurred mainly in the temporal-superior and temporal-inferior SDOCT sectors. No correlation could be established between demographic, IOP, or MOPP variables and disease progression on OCT. The sensitivity and specificity of both cutoff points (15 and 22 mm Hg) were insufficient to be clinically useful. Outpatient IOPs were noninferior to nycthemeral IOPs. Conclusions IOP data obtained during a single visit make for a poor diagnostic tool, no matter whether obtained using nycthemeral measurements or during outpatient hours. Translational Relevance HIOP-Reader rapidly extracts manually recorded IOP data to allow critical analysis of existing databases.

show abstract

Section: Methodsmentioning

confidence: 99%

HIOP-Reader: Automated Data Extraction for the Analysis of Manually Recorded Nycthemeral IOPs and Glaucoma Progression

Agorastou

Schön

Verma-Fuehring

et al. 2022

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

show abstract

“…To make the process more robust, we ensured that the resulting contour is a rectangle. This was done by approximating the contour using the Douglas-Peucker algorithm, 31,32 ensuring that the contour consisted of four lines even when the frame was cut-off or other artifacts were obstructing the frame.…”

Section: Image Analysis Of Manually Recorded 24-hour Iop Profilesmentioning

confidence: 99%

HIOP-Reader: Automated Data Extraction for the Analysis of Manually Recorded Nycthemeral IOPs and Glaucoma Progression

Agorastou¹,

Schoen²,

Verma-Fuehring³

et al. 2021

Preprint

View full text Add to dashboard Cite

Purpose: Nycthemeral (24-hour) glaucoma inpatient intraocular pressure (IOP) monitoring has been used in Europe for more than 100 years to detect peaks missed during regular office hours. Data supporting this practice is lacking, partially because it is difficult to correlate manually drawn IOP curves to objective glaucoma progression. To address this, we deployed automated IOP data extraction tools and tested for a correlation to a progressive retinal nerve fiber layer loss on spectral-domain optical coherence tomography (SDOCT). Methods: We created and deployed a machine-learning image analysis software to extract IOP data from hand-drawn, nycthemeral IOP curves of 225 retrospectively identified glaucoma patients. The relationship between demographic parameters, IOP and mean ocular perfusion pressure (MOPP) data to SDOCT data was analyzed. Sensitivities and specificities for the historical cut-off values of 15 mmHg and 22 mmHg in detecting glaucoma progression were calculated. Results: IOP data could be extracted efficiently. The IOP average was 15.2±4.0 mmHg, nycthemeral IOP variation was 6.9±4.2 mmHg, and MOPP was 59.1±8.9 mmHg. Peak IOP occurred at 10 AM and trough at 9 PM. Disease progression occurred mainly in the temporal-superior and -inferior SDOCT sectors. No correlation could be established between demographic, IOP, or MOPP parameters and SDOCT disease progression. The sensitivity and specificity of both cut-off points (15 and 22 mmHg) were insufficient to be clinically useful. Outpatient IOPs were non-inferior to nycthemeral IOPs. Conclusion: IOP data obtained during a single visit make for a poor diagnostic tool, no matter whether obtained using nycthemeral measurements or during outpatient hours.

show abstract

“…Since its introduction [6] the DP algorithm has become a classic reference approach for line partitioning, and still remains the subject of various extensions and improvements [7], [8]. The DP algorithm approximates a trajectory by recursively splitting the component at the point farthest from that line, until no interior points are farther than a pre-selected tolerance parameter ε (expressed for example as a number of pixels).…”

Section: Trajectory Partitioning Using MMLmentioning

confidence: 99%