A goal-driven unsupervised image segmentation method combining graph-based processing and Markov random fields

Trombini, Marco; Solarna, David; Moser, Gabriele; Dellepiane, S.

doi:10.1016/j.patcog.2022.109082

Cited by 17 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method is simple to calculate, has high computational e ciency, and is fast, but it is not ideal for processing images that contain excessive information. Edge based image segmentation method is a classic segmentation technique, whose basic principle is to analyze the brightness values between pixels in the image to inspect possible boundaries [49]. If the difference in brightness value between pixel points and adjacent edge pixels points is signi cant, it is assumed that the corresponding pixel points are located at a boundary point.…”

Section: Image Segmentation Methods Based On Convolutional Neural Net...mentioning

confidence: 99%

Fine-grained image processing based on convolutional neural networks

Miao

2023

Preprint

View full text Add to dashboard Cite

In the field of computer vision, convolutional neural networks are deep learning algorithms that can classify or detect images by learning image features. In order to achieve advanced recognition and analysis of images, multi-layer neural network models are employed in the discipline of image processing to gather and recall intricate aspects and patterns in the pictures. In this paper, we summarize and analyze the fine-grained image processing methods based on convolutional neural networks, including fine-grained image segmentation, image super-resolution reconstruction, and image edge detection methods. We also analyze the research progress of the three techniques both domestically and internationally. At the same time, experimental comparisons are conducted on mainstream datasets in the corresponding fields to obtain the performance of various fine-grained image processing methods. Finally, the development of convolutional neural networks in the field of fine-grained image processing is prospected.

show abstract

Section: Image Segmentation Methods Based On Convolutional Neural Net...mentioning

confidence: 99%

Fine-grained image processing based on convolutional neural networks

Miao

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Dierckx proposed a super-quadratic surface method with a small number of parameters for the target model [18]. Scholar Park introduced the functional parameters [19], [20] on the basis of the superconducting surface concept, and extended the flexibility of the quadratic surface, and obtained a more elaborate left ventricle model by this method. Zoran et al proposed a segmentation method combining the posterior energy function based on the Markov random field function and the annealing algorithm [21].…”

Section: Related Workmentioning

confidence: 99%

An Automatic Cardiac Computed Tomography (Ct) Images Sequence segmentation Technique

Ahmed,

Hongsong,

Khan

et al. 2024

Preprint

View full text Add to dashboard Cite

Segmentation of the Whole Cardiac CT Image Sequence is the Key to Computer-baseddiagnosis and the analysis of internal lesions in the Human Heart. According to the flow of the blood, contraction and Dilation, the cardiac CT image is prone to weak boundaries and artefacts. The technique of Segmentation for a fast, accurate, reproducible, and fully facilitate the diagnosis of Cardiovascular diseases, it is also the consuming of time, intensive of clinical staff to produce over-segmentation. Therefore, in this paper, we proposed the automatic cardiac CT images sequence segmentation technique to depend on the visual saliency method to understand the saliency of the foreground object relative to the background area used for ImageSegmentation. Using visual attention mechanism we will find the accurate location information, filtering ribs, and muscles of the heart area. The distinctness between the background and the target area is not obvious, and internal structure diversification. It can filter out most of the non-heart tissue part, which is more conducive to the doctor on the patient's heart health status observation.

show abstract

“…When realizing pattern recognition problems within the realm of computer vision, various algorithms can be employed. These encompass rule-based algorithms, which consists of contour analysis, snakes, region growing, Markov chains, level set methods, and graphs, as referenced in [9][10][11][12][13][14]. Additionally, there are Artificial Intelligence (AI) approaches, which involve Machine Learning (ML) and Deep Learning (DL) algorithms, as depicted in [15][16][17].…”

Section: Introductionmentioning

confidence: 99%

“…However, they are susceptible to specific implementation conditions, such as confined environments and standardized lighting conditions. As indicated in [9][10][11][12][13][14][15][16][17][18][19],…”

Section: Introductionmentioning

confidence: 99%

Welding Bead Detection and Inspection on Shear Reinforcement with Dual-Anchorage Using Enhanced Mask RCNN

Mlyahilu,

Lee,

Choi

et al. 2024

Preprint

View full text Add to dashboard Cite

Welding processes pose significant challenges and risks to both humans and the environment, as well as the machines involved. To mitigate the potential negative impacts of welding, we suggest the development of a four-camera system that can replace human involvement in the assessment and evaluation of welded products. In this research paper, we introduce an algorithm based on Mask-RCNN and Green’s theorem-based classifier, designed to assess the quality of welding beads. For the optimization of our model, we trained the enhanced model on COCO weights using various backbone networks, including VGG16, ResNet101, MobileNet, Inception, and EfficientNet. Our findings revealed that Effi-cientNet reduced computational time compared to the other options. Due to constraints in data availability, we treated the problem as a single-class classification task. We addressed the issue of imbalanced datasets by incorporating a classifier with a decision threshold of 75% to distinguish between correctly and incorrectly welded beads. Furthermore , our proposed algorithm is versatile and adaptable, functioning effectively under different environmental conditions, with various types of cameras, diverse brightness settings, and multiple resolutions. Based on a thorough evaluation using performance metrics and the specified decision threshold, our algorithm achieved impressive results, a mean recall of 100%, precision of 100%, an accuracy of 99.56%, and an Intersection over Union (IoU) score of 98.92%. Additionally, the algorithm is capable of detecting and assessing the quality of welding beads within a mean processing time of 0.55 seconds per image, obtained from 172 frames. Based on these promising results, we recommend the adoption of our proposed algorithm for real-time applications that involve the detection and evaluation of welding bead quality, especially when integrated with the four-camera system we have developed. JEL Classification: D8 , H51

show abstract

A goal-driven unsupervised image segmentation method combining graph-based processing and Markov random fields

Cited by 17 publications

References 43 publications

Fine-grained image processing based on convolutional neural networks

Fine-grained image processing based on convolutional neural networks

An Automatic Cardiac Computed Tomography (Ct) Images Sequence segmentation Technique

Welding Bead Detection and Inspection on Shear Reinforcement with Dual-Anchorage Using Enhanced Mask RCNN

Contact Info

Product

Resources

About