A novel multi-scale and multi-expert edge detector based on common vector approach

Özkan, Kemal; Işık, Şahin

doi:10.1016/j.aeue.2015.05.011

Cited by 12 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[14], [16]. Other valuable quantitative classification metrics are Specificity, Sensitivity and Accuracy [17].…”

Section: E Performance Measurementioning

confidence: 99%

“…So, several kernel sizes and numbers of feature maps in successive CNN layers have been evaluated for overall classification accuracy, see below. The FCL layer is a standard neural network classification layer [14]; the type of activation function used is a sigmoid function. It can be bounded within the range [minimum, maximum], so allows simple thresholding to get the final output classifications [15].…”

Section: Bcnn Configurationmentioning

confidence: 99%

See 1 more Smart Citation

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images

Jabbar

Day

Heinz

et al. 2016

2016 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Fast and accurate segmentation of musculoskeletal ultrasound images is an on-going challenge. Two principal factors make this task difficult: firstly, the presence of speckle noise arising from the interference that accompanies all coherent imaging approaches; secondly, the sometimes subtle interaction between musculoskeletal components that leads to non-uniformity of the image intensity. Our work presents an investigation of the potential of Convolutional Neural Networks (CNNs) to address both of these problems. CNNs are an effective tool that has previously been used in image processing of several biomedical imaging modalities. However, there is little published material addressing the processing of musculoskeletal ultrasound images, particularly using a panoramic technique. In our work we explore the effectiveness of CNNs when trained to act as a pre-segmentation pixel classifier that determines whether a pixel is an edge or non-edge pixel. Our CNNs are trained using two different ground truth interpretations. The first one uses an automatic Canny edge detector to provide the ground truth image; in the second interpretation, the ground truth was obtained using the same image marked-up by an expert anatomist. In this initial study the CNNs have been trained using half of the prepared data from one image, using the other half for testing; validation was also carried out using three unseen ultrasound images. CNN performance was assessed using Mathew's Correlation Coefficient, Sensitivity, Specificity and Accuracy. The results show that CNN performance when using expert ground truth image is better than in the case of using Canny ground truth image. Our technique is promising and has the potential to speed-up the image processing pipeline using appropriately trained CNNs.

show abstract

“…[14], [16]. Other valuable quantitative classification metrics are Specificity, Sensitivity and Accuracy [17].…”

Section: E Performance Measurementioning

confidence: 99%

Section: Bcnn Configurationmentioning

confidence: 99%

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images

Jabbar

Day

Heinz

et al. 2016

2016 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…Both gradient-based and Laplacian based ED methods have some disadvantages such as noise sensitivity, illumination sensitivity and non-adaptive parameters [1]. Some new approaches that include a multi-scale method for ED based on increasing Gaussian smoothing and edge tracking [11] and a model based on the multi-scale and multi-expert analyses inspired by common vector approach and the concept of Gaussian scale [12] have been outlined. An objective performance analysis of statistical tests for ED of textured or cluttered images has been performed [13].…”

Section: Introductionmentioning

confidence: 99%

An improved teaching–learning based robust edge detection algorithm for noisy images

Thirumavalavan

Jayaraman

2016

Journal of Advanced Research

View full text Add to dashboard Cite

show abstract

“…CVA is a popular subspace based classification algorithm as applied for face recognition [11], spam classification [12], image denoising [13] and edge detection [14] tasks. The motivation of CVA is inspired from theory behind the PCA.…”

Section: Cva With Application To Background Modellingmentioning

confidence: 99%

A new subspace based solution to background modelling and change detection

Işık

Özkan

Gerek

2016

ijisae

Self Cite

View full text Add to dashboard Cite

For surveillance system, the background subtraction plays an important role for moving object detection with an algorithm embedded in the camera. Since the existence algorithms cannot satisfy the good accuracy on complex backgrounds including illumination change and dynamic objects, we have put forward the concept of Common Vector Approach (CVA) as a new idea for background modelling. Effectiveness of proposed method is presented through the experiments on popular Wallflower dataset. The obtained visual outputs are compared with well-known methods based on the subjective and objective criteria. From the overall evaluation, we can note the proposed method is not only exhibit successful foreground detection results, but also promises an effective and efficient system for background modelling.

show abstract

A novel multi-scale and multi-expert edge detector based on common vector approach

Cited by 12 publications

References 31 publications

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images

An improved teaching–learning based robust edge detection algorithm for noisy images

A new subspace based solution to background modelling and change detection

Contact Info

Product

Resources

About