A new Rényi entropy-based local image descriptor for object recognition

Gabarda, Salvador; Cristóbal, Gabriel; Rodríguez, Paul; Miravet, Carlos; Cura, Juan Manuel Del

doi:10.1117/12.854901

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recall TP∕nP; (10) where TP are true positives, i.e., the number of salient pixels that are detected as salient object, and nD and nP are the number of detected salient pixels and positive pixels, respectively. Note that the positive pixels of all images are manually generated in our work.…”

Section: Evaluation and Experimental Resultsmentioning

confidence: 99%

“…However, its performance is data dependent as more than 2000 images are needed to make the parameter learning algorithm converge well. Recently, novel methods that exploited the pseudo-Wigner-Ville distribution (PWVD) and Rényi entropy to perform salient target detection and object recognition have been proposed [9,10]. In [9], PWVD is used to extract spatial-frequency information of input images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computational model for salient object detection with anisotropy

Sun

Xu³

et al. 2012

Appl. Opt.

View full text Add to dashboard Cite

An innovative computational model for salient objects detection is proposed. The model is based on the exploitation of the anisotropy property of images by means of pixelwise directional entropy. The generalized Rényi entropy and the discrete cosine transform (DCT) coefficients are selected for this purpose. An entropy map of an input image can be obtained by calculating the Rényi entropy via local patch-based DCT. Analyzing the statistical property of the power spectrum of the entropy map on log-log scale, we find the power law is also appropriate for entropy maps. Accordingly, a saliency map can be derived from the entropy residual computation. Salient objects are detected using a seeded region growing algorithm. Both qualitative and quantitative experiments are conducted. The corresponding results demonstrate the outstanding performance of the proposed model.

show abstract

Section: Evaluation and Experimental Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Computational model for salient object detection with anisotropy

Sun

Xu³

et al. 2012

Appl. Opt.

View full text Add to dashboard Cite

show abstract

“…The Rényi entropy results from the generalization of the Entropy of Shannon. It is an efficient tool which has shown good performances [12]. The Rényi entropy, H α , of order α (α ≥ 0, α = 1) is defined as:…”

Section: Rényi Entropy For 2d Histogrammentioning

confidence: 99%

“…In this work, we propose a method which enables characterizing the anisotropy of an image using the entropy of Rényi and a fully anisotropic Morlets. The Rényi entropy has shown its effectiveness especially to quantify the anisotropy [12]. The use of a fully anisotropic Morlet enables settling the problem of non-uniform changes.…”

Section: Introductionmentioning

confidence: 99%

Texture Analysis for Trabecular Bone X-Ray Images Using Anisotropic Morlet Wavelet and Rényi Entropy

Hassani

Jennane

Rziza

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this paper, we propose a new method based on texture analysis for the early diagnosis of bone disease such as osteoporosis. Our proposed method is based on a combination of four methods. First, bone X-ray images are enhanced using the algorithm of Retinex. Then, the enhanced images are analyzed using the fully anisotropic Morlet wavelet. This step is followed by the quantification of the anisotropy of the images using the Rényi entropy. Finally, the Rényi entropies are used as entries for a neural network. Applied on two different populations composed of osteoporotic (OP) patients and control (CT) subjects, a classification rate of 95% is achieved which provides a good discrimination between OP patients and CT subjects.

show abstract

Multiscale Anisotropic Morlet Wavelet for Texture Classification of Interstitial Lung Diseases

Das

Mahanta

2020

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

A new Rényi entropy-based local image descriptor for object recognition

Cited by 3 publications

References 0 publications

Computational model for salient object detection with anisotropy

Computational model for salient object detection with anisotropy

Texture Analysis for Trabecular Bone X-Ray Images Using Anisotropic Morlet Wavelet and Rényi Entropy

Multiscale Anisotropic Morlet Wavelet for Texture Classification of Interstitial Lung Diseases

Contact Info

Product

Resources

About