Colour and rotation invariant textural features based on Markov random fields

Vácha, Pavel; Haindl, Michal; Suk, Tomáš

doi:10.1016/j.patrec.2011.01.002

Cited by 12 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another option would be to derive invariant features similar to those proposed in the more general computer vision field (e.g., [45]- [47]). The local binary pattern operator, for instance, is by definition invariant to any monotonic gray-scale transformation.…”

Section: Discussionmentioning

confidence: 99%

A Novel Multiple-Instance Learning-Based Approach to Computer-Aided Detection of Tuberculosis on Chest X-Rays

Melendez

Ginneken

Maduskar

et al. 2015

IEEE Trans. Med. Imaging

113

View full text Add to dashboard Cite

To reach performance levels comparable to human experts, computer-aided detection (CAD) systems are typically optimized following a supervised learning approach that relies on large training databases comprising manually annotated lesions. However, manually outlining those lesions constitutes a difficult and time-consuming process that renders detailedly annotated data difficult to obtain. In this paper, we investigate an alternative approach, namely multiple-instance learning (MIL), that does not require detailed information for optimization. We have applied MIL to a CAD system for tuberculosis detection. Only the case condition (normal or abnormal) was required during training. Based upon the well-known miSVM technique, we propose an improved algorithm that overcomes miSVM's drawbacks related to positive instance underestimation and costly iteration. To show the advantages of our MIL-based approach as compared with a traditional supervised one, experiments with three X-ray databases were conducted. The area under the receiver operating characteristic curve was utilized as a performance measure. With the first database, for which training lesion annotations were available, our MIL-based method was comparable to the supervised system ( 0.86 versus 0.88 ). When evaluating the remaining databases, given their large difference with the previous image set, the most appealing strategy was to retrain the CAD systems. However, since only the case condition was available, only the MIL-based system could be retrained. This scenario, which is common in real-world applications, demonstrates the better adaptation capabilities of the proposed approach. After retraining, our MIL-based system significantly outperformed the supervised one ( 0.86 versus 0.79 and 0.91 versus 0.85 , and p=0.0002 , respectively).

show abstract

Section: Discussionmentioning

confidence: 99%

A Novel Multiple-Instance Learning-Based Approach to Computer-Aided Detection of Tuberculosis on Chest X-Rays

Melendez

Ginneken

Maduskar

et al. 2015

IEEE Trans. Med. Imaging

113

View full text Add to dashboard Cite

show abstract

“…MRF is one of the most prominent random field models in the model analysis methods. It is supported by a main theory that describes the gray value of any pixel in the image, only related to the pixel values around the image and the gray values of non-adjacent pixels (Cross and Jain, 1983; Vácha et al , 2011).…”

Section: Image Low-level Feature Expressionmentioning

confidence: 99%

Review of image low-level feature extraction methods for content-based image retrieval

Wang

Han

Jin

2019

View full text Add to dashboard Cite

Purpose In the past few decades, the content-based image retrieval (CBIR), which focuses on the exploration of image feature extraction methods, has been widely investigated. The term of feature extraction is used in two cases: application-based feature expression and mathematical approaches for dimensionality reduction. Feature expression is a technique of describing the image color, texture and shape information with feature descriptors; thus, obtaining effective image features expression is the key to extracting high-level semantic information. However, most of the previous studies regarding image feature extraction and expression methods in the CBIR have not performed systematic research. This paper aims to introduce the basic image low-level feature expression techniques for color, texture and shape features that have been developed in recent years. Design/methodology/approach First, this review outlines the development process and expounds the principle of various image feature extraction methods, such as color, texture and shape feature expression. Second, some of the most commonly used image low-level expression algorithms are implemented, and the benefits and drawbacks are summarized. Third, the effectiveness of the global and local features in image retrieval, including some classical models and their illustrations provided by part of our experiment, are analyzed. Fourth, the sparse representation and similarity measurement methods are introduced, and the retrieval performance of statistical methods is evaluated and compared. Findings The core of this survey is to review the state of the image low-level expression methods and study the pros and cons of each method, their applicable occasions and certain implementation measures. This review notes that image peculiarities of single-feature descriptions may lead to unsatisfactory image retrieval capabilities, which have significant singularity and considerable limitations and challenges in the CBIR. Originality/value A comprehensive review of the latest developments in image retrieval using low-level feature expression techniques is provided in this paper. This review not only introduces the major approaches for image low-level feature expression but also supplies a pertinent reference for those engaging in research regarding image feature extraction.

show abstract

“…According to a recent survey of Humeau-Heurtier [4,5] about texture analysis, texture attributes can be divided into seven categories defined in terms of statistical, structural, transform-based, model-based, graph-based, learning-based, and entropy-based. Several texture analysis approaches based on global feature, include color Gabor filtering [6], Markov random field model [7]. Some of the effective local feature methods are color scale invariant feature transform (SIFT) [8], color pyramid of histograms of [9], discriminative color descriptors (DCD) [10], three-dimensional adaptive sum and difference histograms (3D-ASDH) [11], color local binary pattern [12,13] and affine wavelet [14].…”

Section: Introductionmentioning

confidence: 99%

Rice seed image classiﬁcation based on HOG descriptor with missing values imputation

Quoc

Hoang

2020

TELKOMNIKA

View full text Add to dashboard Cite

Rice is a primary source of food consumed by almost half of world population. Rice quality mainly depends on the purity of the rice seed. In order to ensure the purity of rice variety, the recognition process is an essential stage. In this paper, we firstly propose to use histogram of oriented gradient (HOG) descriptor to characterize rice seed images. Since the size of image is totally random and the features extracted by HOG can not be used directly by classifier due to the different dimensions. We apply several imputation methods to fill the missing data for HOG descriptor. The experiment is applied on the VNRICE benchmark dataset to evaluate the proposed approach.

show abstract

Colour and rotation invariant textural features based on Markov random fields

Cited by 12 publications

References 26 publications

A Novel Multiple-Instance Learning-Based Approach to Computer-Aided Detection of Tuberculosis on Chest X-Rays

A Novel Multiple-Instance Learning-Based Approach to Computer-Aided Detection of Tuberculosis on Chest X-Rays

Review of image low-level feature extraction methods for content-based image retrieval

Rice seed image classiﬁcation based on HOG descriptor with missing values imputation

Contact Info

Product

Resources

About