Fast and Provably Accurate Bilateral Filtering

Chaudhury, Kunal N.; Dabhade, Swapnil Deelip

doi:10.1109/tip.2016.2548363

Cited by 86 publications

(60 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Investigational outcomes on genuine OCT retinal images and phantom images exhibit the adequacy of the offered filter [19]. Kunal N Chaudhury, et al (2016) proposed a quick and provably precise procedure alike to the bilateral filter. The algorithm has a straightforward execution including N + 1 spatial filtering, where N is the approximation order.…”

Section: J Bilateral Filteringmentioning

confidence: 94%

See 1 more Smart Citation

A Review on Noise and Denoise of Biometric Images

Shrivastava¹

2018

IJRASET

View full text Add to dashboard Cite

In our work we mainly focused on denoising of biometric images such as MRI and USI images. In digital image processing, lessening in the noise is an essential procedure to interpret, analyze & enhance the main facts in an image. Still Lessening of Noise is a demanding task. Hence this study offers knowledge of noise and its types and also briefly defines the general denoising techniques for biometric images.

show abstract

Section: J Bilateral Filteringmentioning

confidence: 94%

“…And furthermore give much better exactness. It is noted that the suggested scheme can be utilized to perform cross bilateral filtering, and can likewise be stretched out for the filtering of video and volume data [20].…”

Section: J Bilateral Filteringmentioning

confidence: 99%

A Review on Noise and Denoise of Biometric Images

Shrivastava¹

2018

IJRASET

View full text Add to dashboard Cite

show abstract

“…A bilateral filter is a smoothing filter, which preserves edges while reducing overall image noise [16]. The intensity value of each pixel is replaced by a weighted average of pixels in a defined neighborhood, N .…”

Section: Methodsmentioning

confidence: 99%

Automated Segmentation of Bioresorbable Vascular Scaffold Struts in Intracoronary Optical Coherence Tomography Images

Amrute

Athanasiou

Rikhtegar

et al. 2017

2017 IEEE 17th International Conference on Bioinformatics and Bioengineering (BIBE)

View full text Add to dashboard Cite

Bioresorbable vascular scaffolds (BVS), the next step in the continuum of minimally invasive vascular interventions present new opportunities for patients and clinicians but challenges as well. As they are comprised of polymeric materials standard imaging is challenging. This is especially problematic as modalities like optical coherence tomography (OCT) become more prevalent in cardiology. OCT, a light-based intracoronary imaging technique, provides cross-sectional images of plaque and luminal morphology. Until recently segmentation of OCT images for BVS struts was performed manually by experts. However, this process is time consuming and not tractable for large amounts of patient data. Several automated methods exist to segment metallic stents, which do not apply to the newer BVS. Given this current limitation coupled with the emerging popularity of the BVS technology, it is crucial to develop an automated methodology to segment BVS struts in OCT images. The objective of this paper is to develop a novel BVS strut detection method in intracoronary OCT images. First, we preprocess the image to remove imaging artifacts. Then, we use a K-means clustering algorithm to automatically segment the image. Finally, we isolate the stent struts from the rest of the image. The accuracy of the proposed method was evaluated using expert estimations on 658 annotated images acquired from 7 patients at the time of coronary arterial interventions. Our proposed methodology has a positive predictive value of 0.93, a Pearson Correlation coefficient of 0.94, and a F1 score of 0.92. The proposed methodology allows for rapid, accurate, and fully automated segmentation of BVS struts in OCT images.

show abstract

“…Previous implementations already employed a homomorphic filter to equalize the brightness distribution throughout the image and increase the contrast. In addition to that, the calibration images are now sharpened by the use of "unsharp masking" [27] and the naturally resulting increase of noise is compensated for by a bilateral filter [28], which preserves the relevant edges and corners of the checkerboard pattern. As before, a dynamic threshold for binarization is then determined using Otsu's method [29] and the detected corner points are checked for symmetry by the method of Wang et al [30].…”

Section: Challenges and Automation Of Calibration Processmentioning

confidence: 99%

Endoscopic Laser-Based 3D Imaging for Functional Voice Diagnostics

et al. 2017

View full text Add to dashboard Cite

Recently, we reported on the in vivo application of a miniaturized measuring device for 3D visualization of the superior vocal fold vibrations from high-speed recordings in combination with a laser projection unit (LPU). As a long-term vision for this proof of principle, we strive to integrate the further developed laserendoscopy as a diagnostic method in daily clinical routine. The new LPU mainly comprises a Nd:YAG laser source (532 nm/CW/2ω) and a diffractive optical element (DOE) generating a regular laser grid (31 × 31 laser points) that is projected on the vocal folds. By means of stereo triangulation, the 3D coordinates of the laser points are reconstructed from the endoscopic high-speed footage. The new design of the laserendoscope constitutes a compromise between robust image processing and laser safety regulations. The algorithms for calibration and analysis are now optimized with respect to their overall duration and the number of required interactions, which is objectively assessed using binary classifiers. The sensitivity and specificity of the calibration procedure are increased by 40.1% and 22.3%, which is statistically significant. The overall duration for the laser point detection is reduced by 41.9%. The suggested semi-automatic reconstruction software represents an important stepping-stone towards potential real time processing and a comprehensive, objective diagnostic tool of evidence-based medicine.

show abstract

Fast and Provably Accurate Bilateral Filtering

Cited by 86 publications

References 19 publications

A Review on Noise and Denoise of Biometric Images

A Review on Noise and Denoise of Biometric Images

Automated Segmentation of Bioresorbable Vascular Scaffold Struts in Intracoronary Optical Coherence Tomography Images

Endoscopic Laser-Based 3D Imaging for Functional Voice Diagnostics

Contact Info

Product

Resources

About