CLBP for scale and orientation adaptive mean shift tracking

Sliti, Oumaima; Hamam, Habib; Amiri, Hamid

doi:10.1016/j.jksuci.2017.05.003

Cited by 10 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, this method tends to produce inconsistent codes. [14]One example is shown in Figure 3. Here, the 8-bit uniform LBP code (11111111) corresponds to a flat area or a dark spot at the center pixel [16], which is not correct in this case.…”

Section: Compound Local Binary Pattern (Clbp)mentioning

confidence: 99%

Face Spoofing Detection using Mixed Feature with Deep Convolutional Neural Networks

N V*,

U.,

2020

IJRTE

View full text Add to dashboard Cite

Nowadays, face biometric-based access control systems are becoming ubiquitous in daily life while they are still vulnerable to spoofing attacks. Developing robust and reliable methods to prevent such frauds is unavoidable. As deep learning techniques have achieved satisfactory performances in computer vision, they have also been applied to face spoofing detection. However, the numerous parameters in these deep learning-based detection methods cannot be updated to optimum due to limited data. In this paper,a highly accurate face spoof detection system using multiple features and deep learning is proposed. The input video is broken into frames using content-based frame extraction. From each frame, the face of the person is cropped.From the cropped images multiple features like Histogram of Gradients (HoG), Local Binary Pattern (LBP), Center Symmetric LBP (CSLBP), and Gray level co-occurrence Matrix (GLCM) are extracted to train the Convolutional Neural Network(CNN). Training and testing are performed separately by using collected sample data.Experiments on the standard spoof database called Replay-Attack database the proposed system outperform other state-of-the-art techniques, presenting great results in terms of attack detection.

show abstract

Section: Compound Local Binary Pattern (Clbp)mentioning

confidence: 99%

Face Spoofing Detection using Mixed Feature with Deep Convolutional Neural Networks

N V*,

U.,

2020

IJRTE

View full text Add to dashboard Cite

show abstract

“…[16] In any case, RGB space isn't perceptually uniform so the color separate in RGB color space does not compare to color divergence in observation. [19] Along these lines we like to change picture information in RGB color space to other perceptual uniform space before highlight extraction.in our method, the RGB components of the image are extracted separately.…”

Section: E Color Featurementioning

confidence: 99%

“…In the event that the estimation of the center pixel is littler than or on the other hand equivalent to the estimation of the neighbor then an" l" will be taken into the record, generally a "0" is considered. [17] [19] The resulted value is a binary number that is associated with a pattern. A weight is doled out to every digit of the got double number and a comparing thing can be determined.…”

Section: F Texture Feature A) Local Binary Patterns (Lbp)mentioning

confidence: 99%

“…Here, the first bit represents the sign of the difference between the center and the corresponding neighbor gray values like the basic LBP pattern and the other bit is used to encode the magnitude of the difference with respect to a threshold value, the average magnitude (Mavg) of the difference between the center and the neighbor gray values in the local neighborhood of interest. [19] The CLBP operator sets this bit to 1 if the magnitude of the difference between the center and the corresponding neighbor is greater than the threshold M avg .Otherwise, it is set to 0. Thus, the indicator s(x) of (2) is replaced by the following function:…”

Section: B) Compound Local Binary Pattern (Clbp)mentioning

confidence: 99%

“…As far as picture handling it indicates the level of variety or "scattering" available from the normal (mean or anticipated esteem. [19] A low Std gives the information directs incline toward being very near the mean, while elevated expectation deviation shows that the information calls attention to spread out over an enormous scope of qualities. Mathematically standard deviation is given by…”

Section: B) Standard Deviation (Std)mentioning

confidence: 99%

See 2 more Smart Citations

Highly Accurate Melanoma Detection from Skin Images using Multiple Feature Extraction and Support Vector Machine (SVM)

A.S*,

Graceline.H,

Jey J B

2020

IJRTE

View full text Add to dashboard Cite

Digital image processing (DIP) plays a major role in the biomedical image segmentation and classification process. Melanoma detection from skin images is most widely using the application in biomedical imaging. In this paper, a novel algorithm for Melanoma Detection from digital images using multiple feature extraction with a Support Vector Machine (SVM) for highly accurate classification. Multiple features such as color, texture and statistical features are considered to train the SVM. To increase the classification sensitivity, feature extraction is done in (Red, Green, Blue) RGB and (Hue, Intensity, Saturation) HIS color domains. Two separate modules for training and testing is performed with collected sample data by using medical experts. To separate the region from the skin, a cantor-based segmentation technique is used in the gray level component of the input image. The proposed method is tested with various images that are collected from different patients from different places. Form the result validation it is clear that the proposed algorithm can give maximum accuracy of 95% which is best when compared to the conventional classification algorithms

show abstract