An Adaptive Threshold Based on Multiple Resolution Levels for Canny Edge Detection

Othman, Zuraini; Abdullah, Azizi

doi:10.1007/978-3-319-59427-9_34

Cited by 11 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1 shows the membership assignment of proposed fuzzy logic approach. The TMFN for red color is represented as follows: The canny edge detector (Wang et al, 2016;Othman and Azizi, 2017) is recognized as one of the optimal edge detectors. This detector can use Gaussian filter to smooth the image.…”

Section: Proposed Methodologymentioning

confidence: 99%

A fuzzy approach to identify fish red spot disease

Bhoi

Panda

Jena

et al. 2020

View full text Add to dashboard Cite

PurposeFish are considered as one of the important aquatic animals in the planet. They play a vital role in the nutrient cycle. They can be considered as one of the healthy food for human beings. They can also act as a solution for some of the human health problems. If fish are affected by several diseases, they in turn provide an adverse effect on human health. Therefore, it is very much essential to protect fish from being affected by any diseases.Design/methodology/approachThis paper is mainly focused on the identification of the red spot diseased area in fish. In this work, a fuzzy rule based method (FRBAM) and triangular membership function (TMFN) is used to identify the red spot disease (RSD) in the fish by analyzing several red spot diseased fish (RSDF) images. The canny edge detector is used for intermediate processing of RSDF images.FindingsThe proposed method is able to identify the red pixels over the fish by marking the affected area with red color by using a standard RGB model.Originality/valueThe proposed method follows FRBAM and TMFN in order to detect the RSD and canny edge detector for processing of RSDF images. Finally, it is tested using ten different image sizes and the results show its better performance in terms of detection of RSD affected regions of fish and execution time.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

A fuzzy approach to identify fish red spot disease

Bhoi

Panda

Jena

et al. 2020

View full text Add to dashboard Cite

show abstract

“…We used the improved canny operator (Othman and Abdullah, 2018) to extract the edge of the radar image and boundary of the echoes in the RIAs: where P ( x, y ) is a two-dimensional Gaussian function, f ( x, y ) is the image data, A ( i, j ) is the edge feature of point ( i, j ) in the image, and a ( i, j ) is the normal vector of the image at point ( i, j ). Figure 5 illustrates the complete image processing for an RIA.…”

Section: Fusion Based On Detected Targetsmentioning

confidence: 99%

Fusion of Ship Perceptual Information for Electronic Navigational Chart and Radar Images based on Deep Learning

Guo

Zhang

et al. 2019

J. Navigation

View full text Add to dashboard Cite

Superimposing Electronic Navigational Chart (ENC) data on marine radar images can enrich information for navigation. However, direct image superposition is affected by the performance of various instruments such as Global Navigation Satellite Systems (GNSS) and compasses and may undermine the effectiveness of the resulting information. We propose a data fusion algorithm based on deep learning to extract robust features from radar images. By deep learning in this context we mean employing a class of machine learning algorithms, including artificial neural networks, that use multiple layers to progressively extract higher level features from raw input. We first exploit the ability of deep learning to perform target detection for the identification of marine radar targets. Then, image processing is performed on the identified targets to determine reference points for consistent data fusion of ENC and marine radar information. Finally, a more intelligent fusion algorithm is built to merge the marine radar and electronic chart data according to the determined reference points. The proposed fusion is verified through simulations using ENC data and marine radar images from real ships in narrow waters over a continuous period. The results suggest a suitable performance for edge matching of the shoreline and real-time applicability. The fused image can provide comprehensive information to support navigation, thus enhancing important aspects such as safety.

show abstract

“…He proposed 2D-IFCD-based edge extraction and conducted numerical experiments to evaluate the performance of 2D-IFCD-based edge extraction methods, and the obtained results proved its effectiveness. Othman et al [ 17 ] proposed a method to calculate pixel thresholds for foreground and background images from global and local image analysis. According to this method, an image is divided into blocks according to different resolution levels and then an improved sampling method is applied globally and locally.…”

Section: Introductionmentioning

confidence: 99%

Machine Vision-Based Method for Measuring and Controlling the Angle of Conductive Slip Ring Brushes

Liu

Wang

et al. 2022

Micromachines

View full text Add to dashboard Cite

The conductive slip ring is used for power or signal transmission between two objects rotating relative to each other. It has become an essential part of modern industrial development. In traditional automated production measurements, the typical method is to use calipers, goniometers, or angle gauges to measure a parameter of the workpiece several times and then average it. These inspection means have low measurement accuracy and slow measurement speed, and measurement data cannot be processed in a timely manner. A machine vision-based method for measuring and controlling the angle of the brushes is proposed for this problem. First, the brush angle forming device was built for the conductive slip ring brush wire, forming the principle and rebound characteristics. Then, machine vision and image processing algorithms were applied to measure the key parts of the conductive slip ring brushes. The data of the forming angle value and rebound angle value were obtained during the forming process of the brush wire angle. Finally, a pre-compensation model for the brush filament rebound was developed and validated based on the curve fitting method. The test results show that the error of the angle measurement is within 0.05°. The average error of the measured rebound angle and the calculated rebound angle of the brush filament pre-compensation model was 0.112°, which verifies the correctness of the pre-compensation model. The forming angle can be controlled more precisely, and the contact performance between the brush wire and the ring body can be improved effectively. This method has the potential to be extended to engineering applications.

show abstract

An Adaptive Threshold Based on Multiple Resolution Levels for Canny Edge Detection

Cited by 11 publications

References 11 publications

A fuzzy approach to identify fish red spot disease

A fuzzy approach to identify fish red spot disease

Fusion of Ship Perceptual Information for Electronic Navigational Chart and Radar Images based on Deep Learning

Machine Vision-Based Method for Measuring and Controlling the Angle of Conductive Slip Ring Brushes

Contact Info

Product

Resources

About