Hybrid graphical model for semantic image segmentation

Wang, Lili; Yung, N.H.C.

doi:10.1016/j.jvcir.2015.01.014

Cited by 9 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For semantic image segmentation, a hybrid Bayesian Network (BN) model and Hierarchical Conditional Random Field model (HCRF) [13] were proposed. HRCF generated initial semantic sub-scene prediction by capturing non-casual relationship whereas BN modeled contextual interactions for each semantic sub-scene.…”

Section: Literature Surveymentioning

confidence: 99%

Edge detection based on Improved Non-Maximum Suppression Method

Sreedhar¹,

Sathappan²

2019

IJITEE

View full text Add to dashboard Cite

Semantic Segmentation and edge detection are important research fields for scene understanding in computer vision. A hierarchical framework called Contextual Hierarchical Model (CHM) was proposed for semantic image segmentation and edge detection. It learned contextual information using a Logistic Disjunctive Normal Networks (LDNN) classifier. The class average accuracy of CHM was improved by defining a global constraint using Conditional Random Field (CRF), Hierarchical CRF (HCRF), Higher order HCRF (HHCRF). The LDNN was improved by using proximal gradient method which minimizes the quadratic error and it had high convergence rate than gradient descent method. The weight and bias terms of LDNN was optimized by using Grey Wolf Optimization algorithm (GWO) which improves the classification accuracy and it also reduces time complexity of LDNN. During the edge detection using CHM, a multi-scale strategy was adopted to compute edge maps. A Non-Maximum Suppression (NMS) was used to obtain the thinned edges in images. However, it is a post-processing step which consumes additional time in edge detection process. So, in this paper, the edge detection is interpreted as a classification problem where the thinned edges in images are obtained without any post-processing step. It reduces the time consumption. Two key ingredients such as loss and joint processing are included in NMS to improve the detection of thinned edges. The loss is used to penalize the double edge detection and the joint processing is used to reduce the loss of edge detection by including a pair features as additional feature for edge detection. The pair features, Haar, Histogram of Gradient (HOG) and SIFT features are given as input to LDNN to detect the edges that improve the efficiency of CHM based edge detection.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Edge detection based on Improved Non-Maximum Suppression Method

Sreedhar¹,

Sathappan²

2019

IJITEE

View full text Add to dashboard Cite

show abstract

“…Fully supervised semantic segmentation works [ 13 , 14 , 15 , 16 , 17 ] based on deep learning have achieved satisfactory results, even if they only use single-modal image as their model’s input. Despite the structure of deep networks being effective, it still has some limitations that the model needs a large number of annotated examples.…”

Section: Introductionmentioning

confidence: 99%

Self-Enhanced Mixed Attention Network for Three-Modal Images Few-Shot Semantic Segmentation

Song,

Zhang,

Bao

et al. 2023

Sensors

View full text Add to dashboard Cite

As an important computer vision technique, image segmentation has been widely used in various tasks. However, in some extreme cases, the insufficient illumination would result in a great impact on the performance of the model. So more and more fully supervised methods use multi-modal images as their input. The dense annotated large datasets are difficult to obtain, but the few-shot methods still can have satisfactory results with few pixel-annotated samples. Therefore, we propose the Visible-Depth-Thermal (three-modal) images few-shot semantic segmentation method. It utilizes the homogeneous information of three-modal images and the complementary information of different modal images, which can improve the performance of few-shot segmentation tasks. We constructed a novel indoor dataset VDT-2048-5i for the three-modal images few-shot semantic segmentation task. We also proposed a Self-Enhanced Mixed Attention Network (SEMANet), which consists of a Self-Enhanced module (SE) and a Mixed Attention module (MA). The SE module amplifies the difference between the different kinds of features and strengthens the weak connection for the foreground features. The MA module fuses the three-modal feature to obtain a better feature. Compared with the most advanced methods before, our model improves mIoU by 3.8% and 3.3% in 1-shot and 5-shot settings, respectively, which achieves state-of-the-art performance. In the future, we will solve failure cases by obtaining more discriminative and robust feature representations, and explore achieving high performance with fewer parameters and computational costs.

show abstract

“…It was and still is a challenging task to achieve an accurate and meaningful segmentation [2] [3]. Semantic segmentation is a process of assigning every pixel to predefined classes and aims to solve structured pixel-wise labelling problems [4] [5]. Semantic image segmentation has been widely used in many computer vision applications and remote sensing area.…”

Section: Introductionmentioning

confidence: 99%

“…Semantic image segmentation has been widely used in many computer vision applications and remote sensing area. Some examples are content-based image retrieval, foreground/background extraction, face recognition, human pose estimation and scene categorization [5]. In the last decade, most semantic segmentation relied on hand-crafted features [6] and classifiers such as Random Forests [7], Boosting [8] or Support Vector Machines [9].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of VGG Networks for Semantic Image Segmentation of Malaysian Meals

Jamil¹,

Redzuan²,

Ismail³

et al. 2019

Proceedings of the Proceedings of the 1st International Conference on Informatics, Engineering, Science and Technology, INCITES

View full text Add to dashboard Cite

This paper evaluates VGG-16 and VGG-19 networks in performing semantic image segmentation of Malaysian meals. This is a preliminary investigation of using transfer learning models to recognize food objects in typical Malaysian meals. Most current works of food recognition system calculate the calories and nutritional content of a meal based on the food object recognition, regardless of the portion size. Our final aim is to develop a food recognition system that considers the portion size in calculating the calories and nutritional content. Therefore, semantic segmentation of the food objects in the meal is a very important stage. Our work also initiated the training datasets for Malaysian meals that will be made available to the public. Using a small training dataset and a basic configuration of the VGG network, our results show inconsistent findings of the performance of VGG-16 and VGG-19. These findings will serve as a fundamental guideline to improve the semantic segmentation of food images.

show abstract

Hybrid graphical model for semantic image segmentation

Cited by 9 publications

References 41 publications

Edge detection based on Improved Non-Maximum Suppression Method

Edge detection based on Improved Non-Maximum Suppression Method

Self-Enhanced Mixed Attention Network for Three-Modal Images Few-Shot Semantic Segmentation

Evaluation of VGG Networks for Semantic Image Segmentation of Malaysian Meals

Contact Info

Product

Resources

About