A new perspective and extension of the Gaussian Filter

Wüthrich, Manuel; Trimpe, Sebastian; Cifuentes, Cristina Garcia; Kappler, Daniel; Schaal, Stefan

doi:10.1177/0278364916684019

Cited by 13 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Gaussian smoothing operator is a 2-D convolution operator employed to blur images and remove detail and noise. In this sense, it is similar to the median filter, but it uses a discrete kernel representing the shape of the Gaussian hump (Wüthrich, Trimpe, Cifuentes, Kappler, & Schaal, 2017). The gaussian filter was generally used to suppress the speckle noise in OCT images (Devi, Ramkumar, Kumar, & Sasi, 2021).…”

Section: Image Preprocessingmentioning

confidence: 99%

Detection of retinal diseases from ophthalmological images based on convolutional neural network architecture

2022

View full text Add to dashboard Cite

The retina is an eye layer that incorporates light- and color-sensitive cells as well as nerve fibers. It collects light and distributes it to the brain for image processing through the use of the optic nerve. Diseases that end up causing vision loss and blindness are generated by retinal ailments. As a result, it is imperative to diagnose and treat certain disorders as early as possible. Optical coherence tomography (OCT), an angiography imaging technique, is operated to help diagnose retinal disorders. Deep learning approaches, which are extensively utilized, have now become a convenient way for diagnosing retinal illnesses through OCT images as a result of their effective outcomes in interpreting medical images. To diagnose retinal disorders utilizing OCT scans, this investigation developed a hybrid methodology based on image pre-processing and convolutional neural networks (CNNs) (a deep learning method). Image pre-processing techniques including background filling, resizing, noise reduction, and highlighting are exercised at the pre-processing stage. The segmentation process provides a new CNN architecture with five convolution layers that does have a low computational cost. Compared to other publications using the same data set, the proposed method seems to have a success rate of 99.48 percent in the detection of retinal disorders, closing a significant gap in the literature. The proposed approach has the advantage of maintaining low computing costs in comparison to other studies in the literature. When the conclusions are regarded, it is noticed that the suggested method might be exerted as a decision support system to assist physicians in the clinical context during the diagnosis of retinal disorders.

show abstract

Section: Image Preprocessingmentioning

confidence: 99%

Detection of retinal diseases from ophthalmological images based on convolutional neural network architecture

2022

View full text Add to dashboard Cite

show abstract

“…In general, Gaussian noise with zero mean and unit variance during the process of measurement is typically assumed [20] in analytical developments, whereas it has been observed that in some cases this is not accurate [6]. A Gaussian noise with non-zero mean and non-unit variance errors, w ∼ N ( w , σ 2 w ), introduces a systematic error and a random uncertainty respectively in field measurements.…”

Section: Simulationsmentioning

confidence: 99%

“…In general, the existing filtering methodologies compute either the predictions with respect to the conditional probability distribution p(x k |z :k ), such as PF, or with respect to the probability joint distribution p(x k , z k |z :k−1 ), such as EKF, see [20] and the references therein. One of the differences between these methods is the computational cost.…”

Section: Introductionmentioning

confidence: 99%

Range-Only Single-Beacon Tracking of Underwater Targets From an Autonomous Vehicle: From Theory to Practice

Masmitja¹,

Gomáriz²,

Río³

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Underwater localization is one of the main problems that must be addressed in subsea exploration, where no global positioning system (GPS) is available. In addition to the traditional underwater localization systems, such as long base line (LBL), new methods have been developed to increase the navigation performance and flexibility and to reduce the deployment costs. For example, range-only and single-beacon (ROSB) is based on an autonomous vehicle that localizes and tracks different underwater targets using slant range measurements carried out with acoustic modems. This paper presents different strategies to improve ROSB tracking methods. The ROSB target tracking method can be seen as a hidden Markov model (HMM) problem. Using Bayes' rule, the probability distribution function of the HMM states can be solved by using different filtering methods. Here, we present and compare different methods under different scenarios, both evaluated in simulations and field tests. The main mathematical notation and performance of each algorithm are presented, where best practice has been derived. From a methodological point of view, this paper advanced the understanding of accuracy that can be achieved by using the ROSB target tracking methods with autonomous underwater vehicles. INDEX TERMS Particle filter, range-only target tracking, single-beacon, autonomous underwater vehicles, acoustic modems, slant range.

show abstract

“…10 Then, the images are filtered to eliminate noise with a Gaussian filter whose window size is 16 3 16. 11 Consequently, the images are segmented by illumination to extract the laser strip in the image. The extracted laser strips from the two cameras are shown in Figure 9.…”

Section: The Tire Profile Laser Strip Image Processingmentioning

confidence: 99%

“…There is a difference between the measured depth and the real depth when the laser plane does not pass through the tire's axis as mentioned in section ''Mathematical model of the measuring system and analysis.'' The real depth can be obtained with the measured depth by following steps: (1) calculate l with the measured h and the known r by expression (8); (2) calculate the angle u by expression (9) or (10); and (3) calculate the real depth with the measured depth by expression (11). The abovementioned steps are implemented in a LabVIEW program developed in this research.…”

Section: The Measure Of the Tread Depthmentioning

confidence: 99%

The study on tire tread depth measurement method based on machine vision

Wang

Qin-peng

et al. 2019

Advances in Mechanical Engineering

View full text Add to dashboard Cite

The tire tread depth has strong influence on the braking performance of the vehicle and should be inspected periodically for driving safety. In order to determine the tire tread depth accurately and automatically, a tire tread depth measurement method based on machine vision was developed. During the measuring, a tire tread radial section image formed by a laser plane was captured when the tire rolls over the measuring device. Then, the image was calibrated to eliminate the lens distortion and processed to get the single-pixel center line. Consequently, the center line's pixel coordinates were transformed to world coordinates with the calibration information of the laser plane, and a profile curve of the tire radial section was obtained. Then, the tread grooves on the profile curve were identified and their positions are determined by an algorithm developed in this research. Finally, the depth of each groove was calculated successively. An experiment was conducted on a prototype system based on the measurement method developed in this article. The experimental result indicates that the measurement method can identify the tire tread groove and determine its position and measure its depth. The depth absolute error is less than 0.2 mm, which can meet the demand of tire tread depth measurement.

show abstract

A new perspective and extension of the Gaussian Filter

Cited by 13 publications

References 30 publications

Detection of retinal diseases from ophthalmological images based on convolutional neural network architecture

Detection of retinal diseases from ophthalmological images based on convolutional neural network architecture

Range-Only Single-Beacon Tracking of Underwater Targets From an Autonomous Vehicle: From Theory to Practice

The study on tire tread depth measurement method based on machine vision

Contact Info

Product

Resources

About