Higher Order Conditional Random Field for Multi-Label Interactive Image Segmentation

Nguyen, Vu; Pham, N.; Tran, Trung; Le, Bac

doi:10.1109/rivf.2012.6169870

Cited by 4 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…High-order connections between nodes that are spaced further apart in the image have been considered in response to the need for richer and more expressive prior information from the training data. Some approaches define hierarchical connectivity and high-order potentials over image regions [2,94,4,46,98,80,75,111] whereas others consider fully-connected dense random fields defined over all image pixels [3,28,34,33]. Comparing the two approaches, accuracy of image labeling in the former approach is limited by the accuracy of image segmentation algorithm that is applied to partition the image into regions.…”

Section: Connectivity Structurementioning

confidence: 99%

Robust Image Labeling Using Conditional Random Fields

Arani¹

2021

Preprint

View full text Add to dashboard Cite

Object recognition has become a central topic in computer vision applications such as image search, robotics and vehicle safety systems. However, it is a challenging task due to the limited discriminative power of low-level visual features in describing the considerably diverse range of high-level visual semantics of objects. Semantic gap between low-level visual features and high-level concepts are a bottleneck in most systems. New content analysis models need to be developed to bridge the semantic gap. In this thesis, algorithms based on conditional random fields (CRF) from the class of probabilistic graphical models are developed to tackle the problem of multiclass image labeling for object recognition. Image labeling assigns a specific semantic category from a predefined set of object classes to each pixel in the image. By well capturing spatial interactions of visual concepts, CRF modeling has proved to be a successful tool for image labeling. This thesis proposes novel approaches to empowering the CRF modeling for robust image labeling. Our primary contributions are twofold. To better represent feature distributions of CRF potentials, new feature functions based on generalized Gaussian mixture models (GGMM) are designed and their efficacy is investigated. Due to its shape parameter, GGMM can provide a proper fit to multi-modal and skewed distribution of data in nature images. The new model proves more successful than Gaussian and Laplacian mixture models. It also outperforms a deep neural network model on Corel imageset by 1% accuracy. Further in this thesis, we apply scene level contextual information to integrate global visual semantics of the image with pixel-wise dense inference of fully-connected CRF to preserve small objects of foreground classes and to make dense inference robust to initial misclassifications of the unary classifier. Proposed inference algorithm factorizes the joint probability of labeling configuration and image scene type to obtain prediction update equations for labeling individual image pixels and also the overall scene type of the image. The proposed context-based dense CRF model outperforms conventional dense CRF model by about 2% in terms of labeling accuracy on MSRC imageset and by 4% on SIFT Flow imageset. Also, the proposed model obtains the highest scene classification rate of 86% on MSRC dataset.

show abstract

Section: Connectivity Structurementioning

confidence: 99%

Robust Image Labeling Using Conditional Random Fields

Arani¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In the process of Alzheimer's disease research, the selection of different classifiers, model structures and appropriate attention mechanisms all play a crucial role in image classification, image recognition, and image segmentation [24]. For example, decision tree is a very common classification method [25].…”

Section: Introductionmentioning

confidence: 99%

Image Classification of Alzheimer’s Disease Based on External-Attention Mechanism and Fully Convolutional Network

Jiang

Yan

et al. 2022

Brain Sciences

View full text Add to dashboard Cite

Automatic and accurate classification of Alzheimer’s disease is a challenging and promising task. Fully Convolutional Network (FCN) can classify images at the pixel level. Adding an attention mechanism to the Fully Convolutional Network can effectively improve the classification performance of the model. However, the self-attention mechanism ignores the potential correlation between different samples. Aiming at this problem, we propose a new method for image classification of Alzheimer’s disease based on the external-attention mechanism. The external-attention module is added after the fourth convolutional block of the fully convolutional network model. At the same time, the double normalization method of Softmax and L1 norm is introduced to obtain a better classification performance and richer feature information of the disease probability map. The activation function Softmax can increase the degree of fitting of the neural network to the training set, which transforms linearity into nonlinearity, thereby increasing the flexibility of the neural network. The L1 norm can avoid the attention map being affected by especially large (especially small) eigenvalues. The experiments in this paper use 550 three-dimensional MRI images and use five-fold cross-validation. The experimental results show that the proposed image classification method for Alzheimer’s disease, combining the external-attention mechanism with double normalization, can effectively improve the classification performance of the model. With this method, the accuracy of the MLP-A model is 92.36%, the accuracy of the MLP-B model is 98.55%, and the accuracy of the fusion model MLP-C is 98.73%. The classification performance of the model is higher than similar models without adding any attention mechanism, and it is better than other comparison methods.

show abstract

“…In a MRF‐based prior model, the probability of a whole field is defined based on the potential (or energy) of the local cliques. MRF‐based prior models, especially higher‐order potentials for enforcing label consistency have demonstrated great successes in the community of multi‐label image segmentation [2, 3]. The exploited higher‐order potentials are constructed on sets of pixels (i.e.…”

Section: Introductionmentioning

confidence: 99%

“…The FoE model has a larger clique structure that is capable of capturing higher order interactions around each image pixel than models based on pairwise interactions. The FoE model differs from those MRF models, such as [2, 3] in three aspects: (i) it is a continuously‐valued MRF model in contrast to a discrete field with finite labels; (ii) its local potentials are built on the filter response of certain linear filters; (iii) its connections related to neighbourhood labels are directly based on image pixels, not super‐pixels.…”

Section: Introductionmentioning

confidence: 99%

Higher‐order MRFs based image super resolution: why not MAP?

Chen

2016

IET Image Processing

View full text Add to dashboard Cite

A trainable filter-based higher-order Markov Random Fields (MRFs) model -the so called Fields of Experts (FoE), has proved a highly effective image prior model for many classic image restoration problems. Generally, two options are available to incorporate the learned FoE prior in the inference procedure:(1) sampling-based minimum mean square error (MMSE) estimate, and (2) energy minimization-based maximum a posteriori (MAP) estimate. This paper is devoted to the FoE prior based single image super resolution (SR) problem, and we suggest to make use of the MAP estimate for inference based on two facts: (I) It is well-known that the MAP inference has a remarkable advantage of high computational efficiency, while the sampling-based MMSE estimate is very time consuming. (II) Practical SR experiment results demonstrate that the MAP estimate works equally well compared to the MMSE estimate with exactly the same FoE prior model. Moreover, it can lead to even further improvements by incorporating our discriminatively trained FoE prior model. In summary, we hold that for higher-order natural image prior based SR problem, it is better to employ the MAP estimate for inference. I. INTRODUCTIONMarkov Random Fields (MRFs) based models have a long history in low-level computer vision problems, which treat the image (can be also seen as a label field) as a random field [7]. It is well-known that MRFs are particularly effective for image/label prior modeling in image processing. In a MRF-based prior model, the probability of a whole field is defined based on the potential (or energy) of the local cliques. MRF-based prior models, especially higher-order potentials for enforcing label consistency have demonstrated great successes in the community of multi-label image segmentation [9], [6]. The exploited Y.J. Chen is with the

show abstract

Higher Order Conditional Random Field for Multi-Label Interactive Image Segmentation

Cited by 4 publications

References 11 publications

Robust Image Labeling Using Conditional Random Fields

Robust Image Labeling Using Conditional Random Fields

Image Classification of Alzheimer’s Disease Based on External-Attention Mechanism and Fully Convolutional Network

Higher‐order MRFs based image super resolution: why not MAP?

Contact Info

Product

Resources

About