Local directional gradient pattern: a local descriptor for face recognition

Chakraborty, Soumendu; Singh, Satish Kumar; Chakraborty, Pavan

doi:10.1007/s11042-015-3111-6

Cited by 70 publications

(32 citation statements)

References 24 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…LBP is texture feature methodology that takes into account the relationship between the center pixel and neighboring pixels [32]. Variants of LBP algorithm have been employed by many researchers [33][34][35][36][37][38]. Nevertheless, the most important drawbacks of LBP, which uses local spatial features overlooks macro texture information and is sensitive to noise.…”

Section: Introductionmentioning

confidence: 99%

Content-Based Image Retrieval with Combined Features: Color and Gradient

Kılıçaslan

Demi̇rci̇

2021

Preprint

View full text Add to dashboard Cite

Feature extraction is fundamental stage of effective content based image retrieval (CBIR). However, it remains challenging issue to extract low-level features for retrieval systems. This paper puts forward an effective solution proposal for the aforementioned problem. Initially, images and their gradients are clustered with multi-level thresholding. A codebook is generated with threshold values. The size of the codebook generated depends on the number of thresholds. Consequently, every pixel in color image is included in a cluster by means of the codebook. Color reduction is performed by assigning the average values of pixels in the same cluster. A cluster-based one-dimensional histogram (CBH) is created with the numbers of pixels in every cluster represented with a single color. Then the cluster-based feature vectors with histogram are extracted from original image and gradient image. Accordingly, relevant features are combined. The developed feature vector is called as combined feature vector (CFV). The most important advantages of CFV are that it performs an effective color reduction technique and feature presentation by processing texture information with gradient operator. Therefore, the main contribution of the combined feature vector suggested is its high accuracy and stability for image retrieval. The proposed method has been tested with Corel-1K, Corel-5K Corel-10K and GHIM-10K datasets. In addition, performances of different image histogram similarity techniques such as cosine, histogram intersection and Euclidean distance have been verified with the developed algorithm. Experimental results have been analyzed in two categories. Initially, CBIR results produced with combined feature vectors which are generated by Otsu, Kapur and center of gravity of histogram (CGH) procedures have been evaluated. Then, the CBIR strategy based on CGH method has been compared with CBIR systems with local binary pattern (LBP) and gradient-structures histogram (GSH). It was observed that CBIR approach based on CGH technique has significantly outperformed.

show abstract

Section: Introductionmentioning

confidence: 99%

Content-Based Image Retrieval with Combined Features: Color and Gradient

Kılıçaslan

Demi̇rci̇

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…It is shown that the LPOG descriptor with WPCA is robust against illumination, expression, occlusion, pose, time‐lapse variations and low resolution. In another study, local directional gradient pattern (LDGP) is proposed [27]. LDGP computes high order derivatives in four distinct directions for a reference pixel and encodes the relationship between them to obtain the local feature.…”

Section: Introductionmentioning

confidence: 99%

Use of gradient and normal vectors for face recognition

et al. 2020

View full text Add to dashboard Cite

“…There are two kinds of order based descriptors, one using LBP framework in high-order derivative space and another using intensity order among neighboring values for local region matching. Some examples of former approach are LDP [26] and LDGP [34]. Recently, the intensity order based descriptors have been introduced for feature description and applied mainly to the local region matching [40], [41], [42], [43].…”

Section: Introductionmentioning

confidence: 99%

LDOP: local directional order pattern for robust face retrieval

Dubey

Mukherjee

2019

Multimed Tools Appl

View full text Add to dashboard Cite

The local descriptors have gained wide range of attention due to their enhanced discriminative abilities. It has been proved that the consideration of multi-scale local neighborhood improves the performance of the descriptor, though at the cost of increased dimension. This paper proposes a novel method to construct a local descriptor using multi-scale neighborhood by finding the local directional order among the intensity values at different scales in a particular direction. Local directional order is the multi-radius relationship factor in a particular direction. The proposed local directional order pattern (LDOP) for a particular pixel is computed by finding the relationship between the center pixel and local directional order indexes. It is required to transform the center value into the range of neighboring orders. Finally, the histogram of LDOP is computed over whole image to construct the descriptor. In contrast to the state-of-the-art descriptors, the dimension of the proposed descriptor does not depend upon the number of neighbors involved to compute the order; it only depends upon the number of directions. The introduced descriptor is evaluated over the image retrieval framework and compared with the state-of-the-art descriptors over challenging face databases such as PaSC, LFW, PubFig, FERET, AR, AT&T, and ExtendedYale. The experimental results confirm the superiority and robustness of the LDOP descriptor.Face description is required to make the face recognition approaches robust to intra-class variations and discriminative to inter-class similarities. The face image-descriptor based methods [10], [11], [12], [13], and deep learning based methods [14], [15], are the two major approaches widely adapted in the research community, for face retrieval. The advantages of former methods are data independence, ease of use, no complex computation facility needed and robustness to realsituation variations like rotation, scale, expression and illumination differences.The image-descriptor based methods can be further classified into two categories, i.e., hand-crafted descriptor and learning based descriptor. The designing of hand-crafted image descriptors are the mostly followed research area for the face representation. The local binary pattern (LBP) is proved as a very efficient and simple feature descriptor to capture the micro information of the image [16], [17]. The LBP based approaches have shown promising performance for different computer vision applications such as texture classification and retrieval [18], [19], [20], [21]. Ahonen et al. investigated the suitability of LBP for the face recognition task [10]. They computed the LBP descriptor over several blocks and concatenated to form a single descriptor. This approach outperformed the classical methods such as PCA, Bayesian Classifier and Elastic Bunch Graph Matching. Recently, Huang et al. surveyed the LBP based approaches for face recognition [22] and Yang and Chen [23] have presented a comparative study over LBP based face recognition techniques. Seve...

show abstract

Local directional gradient pattern: a local descriptor for face recognition

Cited by 70 publications

References 24 publications

Content-Based Image Retrieval with Combined Features: Color and Gradient

Content-Based Image Retrieval with Combined Features: Color and Gradient

Use of gradient and normal vectors for face recognition

LDOP: local directional order pattern for robust face retrieval

Contact Info

Product

Resources

About