Image Segmentation Methods: A Survey Approach

Chauhan, Amit; Silakari, Sanjay; Dixit, Manish

doi:10.1109/csnt.2014.191

Cited by 18 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, neighboring pixels of seed points are merged based on similarity criteria like intensity or color value. Repeats this method until no pixel satisfies the similarity criteria [82]. The initial seed points and time-consuming are considered the two drawbacks of this method.…”

Section: Region Growing Methodsmentioning

confidence: 99%

Current Trends and Future Directions in Sea-Land Segmentation for Remote Sensing Images

Elkhateeb,

Mekky,

Atwan

et al. 2019

Mansoura Journal for Computer and Information Sciences

View full text Add to dashboard Cite

Nowadays, sea-land segmentation for remote sensing images has a valuable role in water resources monitoring, maritime safety, and coastal zones management. However, it has faced many challenges such as the complicated distribution of land area, noise, poor contrast between sea and land regions, different weather conditions, the development of sensors, and high-resolution images provide more information. Consequently, there are considerable efforts have been made to develop various methods to overcome these challenges. Therefore, this paper introduces the description of the main steps of the sea-land segmentation procedure and the main characteristics of each step. Also, the paper focuses on the taxonomy of the current sea-land segmentation methods. These methods are broadly categorized into six main groups namely thresholding-based methods, region-based methods, energy minimization-based methods, machine learning-based methods, watershed transformation-based methods, and hybrid methods. Finally, this paper also shows and discusses the common challenges which are facing the sea-land segmentation. Besides, the paper introduces promising future research directions in the sea-land segmentation field.

show abstract

Section: Region Growing Methodsmentioning

confidence: 99%

Current Trends and Future Directions in Sea-Land Segmentation for Remote Sensing Images

Elkhateeb,

Mekky,

Atwan

et al. 2019

Mansoura Journal for Computer and Information Sciences

View full text Add to dashboard Cite

show abstract

“…The Canny edge detector is an operator that works on a multi-stage algorithm to identify an extensive chain of edges in images. It was proposed by John F. Canny in 1986 [7] . The Canny edge detection method has the following different steps:…”

Section: Interactive Image Segmentation (Watershed Algorithm)mentioning

confidence: 99%

Image segmentation techniques using python and deep learning

Pandey¹,

Sharma²

2023

Int. J. Commun. Inf. Technol.

View full text Add to dashboard Cite

Computer vision is one of the most important technology emerging in the IT market. Computer vision is a way to provide a powerful ability to see and interpret the real-time objects to the computer just like us or possibly even better than us. An image segmentation is the key processes in machine vision. It is the method of separate a high quality picture into non-overlapping multiple regions to get more precise and significant result. This technique provide us much more granular and reliable information about images like shape, color, and texture, etc. Image segmentation makes a huge impression in Image compression or Object detection techniques, Content-based image retrieval, Video surveillance, Medical imaging, and Traffic control system, etc. It is efficient to process small segments of images one by one to gather information and renounce the regions without information than to process an entire image for particular information. So, image segmentation is help us to dividing image into small segments for advance processing. We can divide a digital image using properties of images such as pixel values, intensity value, texture, shape, etc. So, we can achieve image segmentation by segmenting the images based on these properties. There are many techniques through which one can achieve image segmentation. Here, we discussed multiple techniques apply to achieve image segmentation and compare their benefits and drawbacks followed by the conclusion.

show abstract

“…Early CAD methods used traditional machine learning (ML) algorithms. These algorithms included thresholding, edge detection, region‐based segmentation, and clustering techniques 7 …”

Section: Related Workmentioning

confidence: 99%

“…These algorithms included thresholding, edge detection, region-based segmentation, and clustering techniques. 7 Recently, DL model-based image segmentation models have developed with excellent performance. U-Net is one of the very popular CNNs architectures for medical image segmentation.…”

Section: Single-modality Workmentioning

confidence: 99%

Deep learning‐based multimodal fusion network for segmentation and classification of breast cancers using B‐mode and elastography ultrasound images

Misra

Yoon

Kim

et al. 2022

Bioengineering & Transla Med

View full text Add to dashboard Cite

Ultrasonography is one of the key medical imaging modalities for evaluating breast lesions. For differentiating benign from malignant lesions, computer‐aided diagnosis (CAD) systems have greatly assisted radiologists by automatically segmenting and identifying features of lesions. Here, we present deep learning (DL)‐based methods to segment the lesions and then classify benign from malignant, utilizing both B‐mode and strain elastography (SE‐mode) images. We propose a weighted multimodal U‐Net (W‐MM‐U‐Net) model for segmenting lesions where optimum weight is assigned on different imaging modalities using a weighted‐skip connection method to emphasize its importance. We design a multimodal fusion framework (MFF) on cropped B‐mode and SE‐mode ultrasound (US) lesion images to classify benign and malignant lesions. The MFF consists of an integrated feature network (IFN) and a decision network (DN). Unlike other recent fusion methods, the proposed MFF method can simultaneously learn complementary information from convolutional neural networks (CNNs) trained using B‐mode and SE‐mode US images. The features from the CNNs are ensembled using the multimodal EmbraceNet model and DN classifies the images using those features. The experimental results (sensitivity of 100 ± 0.00% and specificity of 94.28 ± 7.00%) on the real‐world clinical data showed that the proposed method outperforms the existing single‐ and multimodal methods. The proposed method predicts seven benign patients as benign three times out of five trials and six malignant patients as malignant five out of five trials. The proposed method would potentially enhance the classification accuracy of radiologists for breast cancer detection in US images.

show abstract

Image Segmentation Methods: A Survey Approach

Cited by 18 publications

References 5 publications

Current Trends and Future Directions in Sea-Land Segmentation for Remote Sensing Images

Current Trends and Future Directions in Sea-Land Segmentation for Remote Sensing Images

Image segmentation techniques using python and deep learning

Deep learning‐based multimodal fusion network for segmentation and classification of breast cancers using B‐mode and elastography ultrasound images

Contact Info

Product

Resources

About