Performance comparison of Canny and Sobel edge detectors on Balloon Snake in segmenting masses

Jumaat, Abdul Kadir; Yasiran, Siti Salmah; Malek, Aminah Abdul; Rahman, Wan Eny Zarina Wan Abdul; Badrin, Norzaituleha; Osman, Siti Hajar; Rafiee, Siti Rohaina; Mahmud, Rozi

doi:10.1109/iccoins.2014.6868368

Cited by 17 publications

(13 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For all experiments, the tolerance, 𝑡𝑜𝑙 = 10 −6 and the maximum iterations, maxit=200. The values of 𝜎 to regularize the level set function in Algorithms 1 and 2 are in the range of 𝜎 = [0.1,0.45] while the values of 𝜎 to solve (9) of Algorithm 1 range from 𝜎 = [5,33] Figure 1. Segmentation results on natural images By visual observation, all models successfully segmented the targeted object.…”

Section: Resultsmentioning

confidence: 99%

“…In order to examine and separate a digital image into different components that may be used for fundamental applications such as in the disciplines of medical diagnostics [1], and object recognition [2]- [5], image segmentation is required. Intensity inhomogeneity is one of the main obstacles to image segmentation, which is produced by errors in image acquisition, the effects of illumination, and other environmental factors.…”

Section: Introductionmentioning

confidence: 99%

“…Here, 𝑊 𝑘 (𝑥, 𝑦) is a Gaussian window with standard deviation 𝜎 and size 4k+1 by 4k+1, 𝑘 ∈ 𝑍 + . Then, the local image fitting energy function is defined as (5).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Variational selective segmentation model for intensity inhomogeneous image

Saibin

Jumaat

2022

IJEECS

View full text Add to dashboard Cite

Variational selective image segmentation models aim to extract a particular object in an image depending on a set of user-defined prior points. The current model suffers from high computational costs due to the traditional total variation function that results in a slow segmenting process. In addition, it is not designed to segment images with intensity inhomogeneities. In this research, we formulate a new variational selective image segmentation model based on the Gaussian function. A Gaussian function is proposed to replace the traditional total variation function to regularize the variational level set function. To segment images with intensity inhomogeneities, the local image fitting idea was in corporate into the formulation. The efficiency of the proposed model was then assessed by recording the computation time while the accuracy was measured using Jaccard and Dice similarity values. Numerical experiments using synthetic, natural, and medical images demonstrate that the proposed model is about 6 times faster than the existing model, while the Jaccard and Dice values are about 11% and 7% higher, respectively, compared to the existing model. In the future, this research can be extended further into a 3-dimensional modeling and vector-valued image framework.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Variational selective segmentation model for intensity inhomogeneous image

Saibin

Jumaat

2022

IJEECS

View full text Add to dashboard Cite

show abstract

“…The enhanced FDMAS with lower side lobes and less clutter noise is expected to improve the balloon snake active contour (BSAC) segmentation process. Segmentation is a process of partitioning an image in which the intended region of interest (ROI) can be distinguished from the background [17], BSAC is a popular segmentation method that has been used in medical ultrasound imaging [18,19]. Segmenting complex topology such as a blood vessel in retinal angiography and cerebral cortex structures manually are not feasible and time consuming [20].…”

Section: Introductionmentioning

confidence: 99%

Optimizing the lateral beamforming step for filtered-delay multiply and sum beamforming to improve active contour segmentation using ultrafast ultrasound imaging

Moubark¹,

Alomari²,

Zaman³

et al. 2022

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

As an alternative to delay-and-sum beamforming, a novel beamforming technique called filtered-delay multiply and sum (FDMAS) was introduced recently to improve ultrasound B-mode image quality. Although a considerable amount of work has been performed to evaluate FDMAS performance, no study has yet focused on the beamforming step size, Δx, in the lateral direction. Accordingly, the performance of FDMAS was evaluated in this study by fine-tuning Δx to find its optimal value and improve boundary definition when balloon snake active contour (BSAC) segmentation was applied to a B-mode image in ultrafast imaging. To demonstrate the effect of altering Δx in the lateral direction on FDMAS, measurements were performed on point targets, a tissuemimicking phantom and in vivo carotid artery, by using the ultrasound array research platform II equipped with one 128-element linear array transducer, which was excited by 2-cycle sinusoidal signals. With 9-angle compounding, results showed that the lateral resolution (LR) of the point target was improved by 67.9% and 81.2%, when measured at − 6 dB and − 20 dB respectively, when Δx was reduced from λ to λ/5. Meanwhile the image contrast ratio (CR) measured on the CIRS phantom was improved by 10.38 dB at the same Δx reduction and the same number of compounding angles. The enhanced FDMAS results with lower side lobes and less clutter noise in the anechoic regions provides a means to improve boundary definition on a B-mode image when BSAC segmentation is applied.

show abstract

“…On top of that, the extracted boundaries of breast abnormalities can be used in disease diagnosis by identifying its shape and size [2,3,4,5,6]. The edge-based models and region-based models are two categories of segmentation models.…”

Section: Introductionmentioning

confidence: 99%

Gaussian Regularization Based Active Contour Model for Extraction of Shape Boundaries in Vector Valued Images

Jumaat¹,

Nithya²,

Kumar³

2022

IJETAE

Self Cite

View full text Add to dashboard Cite

—Extraction of shape boundaries also known as image segmentation that tries to divide a digital image into several segments for further processing is an important step in digital image analysis. The segmented images are useful in many applications such as object detection, object classification, biometric authentication, and disease diagnosis. This task can be accomplished effectively using active contour model. The two types of active contour models are global segmentation and selective segmentation. A global segmentation model is a way for segmenting an image's entire objects. Global models, unfortunately, are unable to segment a single object’s shape boundary that must be extracted. A selective segmentation model, which seeks to segment selected object’s shape boundary in an image, can overcome this restriction. The recent selective segmentation model for vector valued images has a significant computational cost due to the requirement of solving the curvature term, that result from the usage of traditional regularization term in the formulation. Hence, we proposed a new selective segmentation model for vector valued image by replacing the traditional regularization term with Gaussian function which is easier and faster to solve. The proposed model was tested using MATLAB software in segmenting synthetic, natural and medical images. Numerical experiments shows that the proposed model was about 247 times faster than the existing model with a comparable accuracy.

show abstract

Performance comparison of Canny and Sobel edge detectors on Balloon Snake in segmenting masses

Cited by 17 publications

References 1 publication

Variational selective segmentation model for intensity inhomogeneous image

Variational selective segmentation model for intensity inhomogeneous image

Optimizing the lateral beamforming step for filtered-delay multiply and sum beamforming to improve active contour segmentation using ultrafast ultrasound imaging

Gaussian Regularization Based Active Contour Model for Extraction of Shape Boundaries in Vector Valued Images

Contact Info

Product

Resources

About