Automatic detection and concealment of specular reflections for endoscopic images

Karapetyan, Gevorg; Sarukhanyan, Hakob G.

doi:10.1109/csitechnol.2013.6710353

Cited by 17 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The previous work on this problem was limited to the interpolation (or removal) of specular reflections on colonoscopic, endoscopic or other medical images. For endoscopic images, Guo et al suggested a method to eliminate specular reflection, 18 Stehle used spectral deconvolution algorithm to remove reflections, 19 Arnold et al 20 and Karapetyan et al 21 preferred different inpainting algorithms. In addition, Tchoulack et al proposed using a real‐time inpainting algorithm to eliminate specular reflections from endoscopic images 28 .…”

Section: Discussionmentioning

confidence: 99%

“…In the bilinear interpolation, the main idea is to perform linear interpolation first in one direction, and then in the other direction. Although each step is linear in the sampled values and in the position, the interpolation as a whole is quadratic in the sample location 21‐23 . The bicubic interpolation is a method that uses four neighboring pixels to fill the missing part of the image.…”

Section: Methodsmentioning

confidence: 99%

“…In that study, they proposed two steps: (a) Detection of reflection using thresholding and (b) elimination of reflection using an inpainting algorithm 18 . Among other methods proposed in the literature, Stehle used spectral deconvolution algorithm to remove reflections, 19 Arnold et al 20 and Karapetyan et al 21 preferred inpainting algorithms which can also be called as an interpolation technique. In general, image interpolation approaches compute new values for pixels whose intensity values are saturated due to specular reflection using adjacent/surrounding pixels that have normal intensity values.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Effect of interpolation on specular reflections in texture‐based automatic colonic polyp detection

Kacmaz

Yılmaz

Aydın

2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Reflections of LED light cause unwanted noise effects called specular reflection (SR) on colonoscopic images. The aim of this study was to seek answers to the following two questions. (a) How are the texture features used in automatic detection of polyps affected by the interpolation on specular reflections? (b) If they are affected does it really affect the classification performance? In order to answer these questions, we used 610 colonoscopy images, and divided each image into tiles whose sizes were 32‐by‐32 pixels. From these tiles, we selected the ones without any specular reflection. We added different shape and size specular reflections cropped from real images onto the reflection‐free tiles. We then used the nearest neighbors, bilinear and bicubic interpolation techniques on the tiles on which SRs were added. On these tiles we extracted 116 texture features using 3 second‐order approaches, and 4 first‐order statistics. First, we used paired sample t test. Second, we performed automatic classification of polyps and background using random forest and k nearest neighbors (k‐NN) approaches using the texture features for different combinations of specular reflections added on the tiles from the polyp or background. The results showed that depending on the size of specular reflection, interpolation can cause a significant difference between the texture features that were coming from reflection‐free tiles and the same tiles on which interpolation was performed. In addition, we note that bicubic interpolation may be preferred to eliminate specular reflection when texture features are used for background and polyp discrimination.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effect of interpolation on specular reflections in texture‐based automatic colonic polyp detection

Kacmaz

Yılmaz

Aydın

2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…The specular detection is the subject in different applications has investigated by many researchers. In some cases, the thresholding algorithms show the effectiveness of detecting specular regions [6,7]. Authors in [8] used the thresholding for the saturation and intensity components that reduce the highlights in laparoscopic surgery.…”

Section: Related Workmentioning

confidence: 99%

Automated visual inspection algorithm for the reflection detection and removing in image sequences

Sizyakin

Voronin

Gapon

et al. 2020

Twelfth International Conference on Machine Vision (ICMV 2019)

View full text Add to dashboard Cite

Specular reflections are undesirable phenomena that can impair overall perception and subsequent image analysis. In this paper, we propose a modern solution to this problem, based on the latest achievements in this field. The proposed method includes three main steps: image enhancement, detection of specular reflections, and reconstruction of damaged areas. To enhance and equalize the brightness characteristics of the image, we use the alpha-rooting method with adaptive choice of the optimal parameter-alpha. To detect specular reflections, we apply morphological filtering in the HSV color space. At the final stage there is a reconstruction of damaged areas using adversarial neural networks. This combination makes it possible to quickly and effectively detect and remove specular reflections, which is confirmed by a series of experiments given by the experimental section of this work.

show abstract

“…This type of reflection is a common cause of degradation in quality of colonoscopy and endoscopy images. Physicians usually prefer elimination of specular reflection in medical images [1]. In the case of endoscopy or colonoscopy, the imaging device carries flash lights that produce reflections in presence of moisture in the inner surface of gastrointestinal tract.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Specular Reflection Detection and Inpainting in Colonoscopy Video Frames

Akbari

Mohrekesh

Najariani

et al. 2018

2018 25th IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Colonoscopy video frames might be contaminated by bright spots with unsaturated values known as specular reflection. Detection and removal of such reflections could enhance the quality of colonoscopy images and facilitate diagnosis procedure. In this paper we propose a novel two-phase method for this purpose, consisting of detection and removal phases. In the detection phase, we employ both HSV and RGB color space information for segmentation of specular reflections. We first train a non-linear SVM for selecting a color space based on image statistical features extracted from each channel of the color spaces. Then, a cost function for detection of specular reflections is introduced. In the removal phase, we propose a two-step inpainting method which consists of appropriate replacement patch selection and removal of the blockiness effects. The proposed method is evaluated by testing on an available colonoscopy image database where accuracy and Dice score of 99.68% and 71.79% are achieved respectively.

show abstract

Automatic detection and concealment of specular reflections for endoscopic images

Cited by 17 publications

References 10 publications

Effect of interpolation on specular reflections in texture‐based automatic colonic polyp detection

Effect of interpolation on specular reflections in texture‐based automatic colonic polyp detection

Automated visual inspection algorithm for the reflection detection and removing in image sequences

Adaptive Specular Reflection Detection and Inpainting in Colonoscopy Video Frames

Contact Info

Product

Resources

About