A novel local region-based active contour model for image segmentation using Bayes theorem

Li, Yupeng; Cao, Guo; Wang, Tao; Cui, Qiongjie; Wang, Bisheng

doi:10.1016/j.ins.2019.08.021

Cited by 40 publications

(19 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The first tasks of the proposed method were presented in our previous work [28]. In this contribution, a continuation of the proposed work [13] is presented where widely of information are treated to obtain effective performances in images denoising scheme. The proposed method [28] is included a chief part.…”

Section: Description Of the Proposed Methodsmentioning

confidence: 99%

“…proposed in the literature which can reliably overcome histological noise and segment PG cancer in CT and MR images. In this context, both of active contours and watershed algorithms are commonly used for cerebral tumor segmentation [13,14]. In fact, snakes can be divided into two categories: geometric active contours and parametric snakes [15,16].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Parotid Gland Tumor Segmentation and Classification Using Geometric Active Contour Model and Deep Neural Network Framework

Slama¹,

Mbarki²,

Seddik³

et al. 2021

View full text Add to dashboard Cite

Manual assessment of parotid gland status from magnetic resonance imaging is a subjective, time consuming and error prone process. Automatic image analysis methods offer the possibility to get consistent, objective and rapid diagnoses of parotid gland tumor. In this kind of cancer, a large variety in their characteristics, that brings various difficulties for traditional image analysis methods. In this paper, we propose an automatic method to perform both segmentation and classification of Parotid gland region in order to give quantitative assessment and uniform indicators of PGs status that will help pathologists in their diagnostic. The experimental result illustrates the high accuracy of the results of the proposed method compared to the ground truth. Furthermore, a comparative study with existing techniques is presented in order to demonstrate the efficiency and the superiority of the proposed method.

show abstract

Section: Description Of the Proposed Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving Parotid Gland Tumor Segmentation and Classification Using Geometric Active Contour Model and Deep Neural Network Framework

Slama¹,

Mbarki²,

Seddik³

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The image segmentation by localizing region-based active contours was a model-based technique that could be used to process the viscera images (Duan, Peng, & Qi, 2020;Jayanthi & Shashikumar, 2020;Li, Cao, & Wang, 2020;Wang, Li, & Zhang, 2019). The curves could move to the target boundaries under the influence of internal forces and external forces, in which internal forces were used to hold the curves together and to keep them from bending too much.…”

Section: The Image Segmentation Methods Of Chicken Visceramentioning

confidence: 99%

Analysis of correlation between carcass and viscera for chicken eviscerating based on machine vision technology

Chen

2020

J Food Process Engineering

View full text Add to dashboard Cite

In the poultry evisceration, the inconsistent position of visible carcass and invisible viscera may be one of the most neglected problems, which increase the level of visceral damage by gripping manipulator. In order to detect the position of the chicken carcass and viscera, a computer vision‐based automation system is developed to extract the region of interest from each chicken in the image acquisition system. The segmentation method of carcass is proposed by applying the color space transformation and the threshold segmentation. This method combines with several operations of morphology and reconstruction to remove the other regions such as wings and legs. After a midline abdominal incision of the chicken, the viscera is segmented using the active contour algorithm. Following data analysis, the change trend of relative position is presented between carcass and viscera. The average longitudinal deviation value of weighting 1,000–1,500 g and 1,500–2000 g chickens were 22.9 and 32.4 mm, separately. These results indicate that the relative position is significantly changed between carcass and viscera with chicken size in the longitudinal direction. In this study, machine vision technology can be satisfactorily applied to predict the position of chicken viscera, which can provide technical support for poultry processing.Practical applicationsFor a long time, avian influenza virus and various pathogenic microorganism have been threatening the breeding and slaughtering of poultry, which can easily damage the health of people and cause widespread transmission of the virus. Therefore, automated evisceration technology by intelligent robot will become the development trend of the poultry slaughtering. However, due to the invisibility of the poultry viscera, it will easily cause damage of the internal organs during the manipulator evisceration. In this study, in order to avoid repetitive and boring work and manual operation errors, machine vision technology was introduced to automatically obtain the relative position between the visible carcass and the invisible viscera of individual chicken based on image segmentation algorithms. Thus, the position of the viscera can be predicted based on the data analysis and the carcass location, which provide useful information to guide the robot for evisceration, and it is also helpful to conduct further research in the slaughtering and processing of other poultry.

show abstract

“…The methodology based on the implementation of deformable contours that correspond to various attentive object shapes and motions. This powerful tool (active contour model) has the advantages of implementation in various domains of computer field and facilitates mostly computer vision task [6,7], image segmentation [8][9][10][11], visual tracking and visual navigation [12][13][14][15][16][17][18][19][20][21], synthetic and medical applications [22][23][24][25][26][27][28][29], and salient object detection [30,31].…”

Section: Introductionmentioning

confidence: 99%

Active Contour Model Using Fast Fourier Transformation for Salient Object Detection

Khan

Zhang

2021

Electronics

View full text Add to dashboard Cite

The active contour model is a comprehensive research technique used for salient object detection. Most active contour models of saliency detection are developed in the context of natural scenes, and their role with synthetic and medical images is not well investigated. Existing active contour models perform efficiently in many complexities but facing challenges on synthetic and medical images due to the limited time like, precise automatic fitted contour and expensive initialization computational cost. Our intention is detecting automatic boundary of the object without re-initialization which further in evolution drive to extract salient object. For this, we propose a simple novel derivative of a numerical solution scheme, using fast Fourier transformation (FFT) in active contour (Snake) differential equations that has two major enhancements, namely it completely avoids the approximation of expansive spatial derivatives finite differences, and the regularization scheme can be generally extended more. Second, FFT is significantly faster compared to the traditional solution in spatial domain. Finally, this model practiced Fourier-force function to fit curves naturally and extract salient objects from the background. Compared with the state-of-the-art methods, the proposed method achieves at least a 3% increase of accuracy on three diverse set of images. Moreover, it runs very fast, and the average running time of the proposed methods is about one twelfth of the baseline.

show abstract

A novel local region-based active contour model for image segmentation using Bayes theorem

Cited by 40 publications

References 26 publications

Improving Parotid Gland Tumor Segmentation and Classification Using Geometric Active Contour Model and Deep Neural Network Framework

Improving Parotid Gland Tumor Segmentation and Classification Using Geometric Active Contour Model and Deep Neural Network Framework

Analysis of correlation between carcass and viscera for chicken eviscerating based on machine vision technology

Active Contour Model Using Fast Fourier Transformation for Salient Object Detection

Contact Info

Product

Resources

About