Color Texture Image Retrieval Based on Local Extrema Features and Riemannian Distance

Pham, Minh‐Tan; Mercier, Grégoire; Bombrun, Lionel

doi:10.3390/jimaging3040043

Cited by 23 publications

(20 citation statements)

References 51 publications

(99 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other feature lengths from the table are illustrated from their related papers. We observe that the proposed SLED has lower dimension than the standard LED in [31] (i.e. 210 compared to 561) but can provide faster and better retrieval performance.…”

Section: Methodsmentioning

confidence: 92%

“…We used the 4096-D feature vector from the FC7 layer (also followed by a ReLu layer) and the L1 distance for dissimilarity measure as recommended in [30]. + the LED framework proposed [31] by setting equivalent parameters to our algorithm. In details, we set the 3 window sizes for keypoint extraction (ω 1 ), local extrema detection (ω 2 ) and LED generation (W ) to 9 × 9, 3 × 3 and 36 × 36, respectively.…”

Section: Methodsmentioning

confidence: 99%

“…Vistex Stex GT+GGD+KLD [4] 76.57 49.30 MGG+Gaussian+KLD [6] 87.40 -MGG+Laplace+GD [6] 91.70 71.30 Gaussian Copula+Gamma+ML [8] 89.10 69.40 Gaussian Copula+Weibull+ML [8] 89.50 70.60 Student-t Copula+GG+ML [8] 88.90 65.60 Gaussian Copula+Gabor Wavelet [10] 92.40 76.40 LMEBP [13] 87.77 -LtrP [15] 90.02 -LEP+colorhist [18] 82.65 59.90 DDBTC [25] 92.65 44.79 ODBTC [23] 90.67 -EDBTC [24] 92.55 -LECoP [20] 92.99 74.15 ODII [22] 93.23 -CNN-AlexNet [30] 91.34 68.84 CNN-VGG16 [30] 92.97 74.92 CNN-VGG19 [30] 93.04 73.93 LED [31] 94 The best ARR of 94.95% and 79.87% was produced for Vistex and Stex by our MS-SLED algorithm. A gain of 0.82% and 3.16% was achieved compared to Table 3.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Efficient Texture Retrieval Using Multiscale Local Extrema Descriptors and Covariance Embedding

Pham¹

2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

We present an efficient method for texture retrieval using multiscale feature extraction and embedding based on the local extrema keypoints. The idea is to first represent each texture image by its local maximum and local minimum pixels. The image is then divided into regular overlapping blocks and each one is characterized by a feature vector constructed from the radiometric, geometric and structural information of its local extrema. All feature vectors are finally embedded into a covariance matrix which will be exploited for dissimilarity measurement within retrieval task. Thanks to the method's simplicity, multiscale scheme can be easily implemented to improve its scale-space representation capacity. We argue that our handcrafted features are easy to implement, fast to run but can provide very competitive performance compared to handcrafted and CNN-based learned descriptors from the literature. In particular, the proposed framework provides highly competitive retrieval rate for several texture databases including 94.95% for MIT Vistex, 79.87% for Stex, 76.15% for Outex TC-00013 and 89.74% for USPtex.

show abstract

Section: Methodsmentioning

confidence: 92%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Texture Retrieval Using Multiscale Local Extrema Descriptors and Covariance Embedding

Pham¹

2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this paper, we propose to exploit the affine-invariant Riemannian (AIR) metric proposed in [21]. This metric has been employed in several works related to covariance descriptors [20], [21], [24], [37], [38]. Another alternative could be to exploit the log-Euclidean (LE) metric which has been proved to be also effective for SPD matrices, especially in terms of computational time [39], [40].…”

Section: Supervised Classification Based On Air Kernel-based Svmmentioning

confidence: 99%

Fusion of Polarimetric Features and Structural Gradient Tensors for VHR PolSAR Image Classification

Pham

2018

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

This article proposes a fast texture-based supervised classification framework for fully polarimetric synthetic aperture radar (PolSAR) images with very high spatial resolution (VHR). With the development of recent polarimetric radar remote sensing technologies, the acquired images contain not only rich polarimetric characteristics but also high spatial content. Thus, the notion of geometrical structures and heterogeneous textures within VHR PolSAR data becomes more and more significant. Moreover, when the spatial resolution is increased, we need to deal with large-size image data. In this work, our motivation is to characterize textures by incorporating (fusing) both polarimetric and structural features, and then use them for classification purpose. First, polarimetric features from the weighted coherency matrix and local geometric information based on the Di Zenzo structural tensors are extracted and fused using the covariance approach. Then, supervised classification task is performed by using Riemannian distance measure relevant for covariancebased descriptors. In order to accelerate the computational time, we propose to perform texture description and classification only on characteristic points, not all pixels from the image. Experiments conducted on the VHR F-SAR data as well as the AIRSAR Flevoland image using the proposed framework provide very promising and competitive results in terms of terrain classification and discrimination.

show abstract

“…In References [32,33,36,39], the methods were not tested in the complete databases. In References [26,45,46], the methods used a different metric to calculate the classification.…”

Section: Introductionmentioning

confidence: 99%

Color–Texture Pattern Classification Using Global–Local Feature Extraction, an SVM Classifier, with Bagging Ensemble Post-Processing

Navarro-Clavería¹

2019

Applied Sciences

View full text Add to dashboard Cite

Many applications in image analysis require the accurate classification of complex patterns including both color and texture, e.g., in content image retrieval, biometrics, and the inspection of fabrics, wood, steel, ceramics, and fruits, among others. A new method for pattern classification using both color and texture information is proposed in this paper. The proposed method includes the following steps: division of each image into global and local samples, texture and color feature extraction from samples using a Haralick statistics and binary quaternion-moment-preserving method, a classification stage using support vector machine, and a final stage of post-processing employing a bagging ensemble. One of the main contributions of this method is the image partition, allowing image representation into global and local features. This partition captures most of the information present in the image for colored texture classification allowing improved results. The proposed method was tested on four databases extensively used in color–texture classification: the Brodatz, VisTex, Outex, and KTH-TIPS2b databases, yielding correct classification rates of 97.63%, 97.13%, 90.78%, and 92.90%, respectively. The use of the post-processing stage improved those results to 99.88%, 100%, 98.97%, and 95.75%, respectively. We compared our results to the best previously published results on the same databases finding significant improvements in all cases.

show abstract

Color Texture Image Retrieval Based on Local Extrema Features and Riemannian Distance

Cited by 23 publications

References 51 publications

Efficient Texture Retrieval Using Multiscale Local Extrema Descriptors and Covariance Embedding

Efficient Texture Retrieval Using Multiscale Local Extrema Descriptors and Covariance Embedding

Fusion of Polarimetric Features and Structural Gradient Tensors for VHR PolSAR Image Classification

Color–Texture Pattern Classification Using Global–Local Feature Extraction, an SVM Classifier, with Bagging Ensemble Post-Processing

Contact Info

Product

Resources

About