Palmprint Recognition Using Gabor Feature-Based Bidirectional 2DLDA

Feng, Du; Yu, Pengfei; Li, Hongsong; Zhu, Li

doi:10.1007/978-3-642-22691-5_40

Cited by 17 publications

(7 citation statements)

References 6 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different palm print distinguishing proof techniques, for example, coding based strategies (Kong and Zhang, 2004) and guideline bend techniques (Huang et al, 2008) have been proposed in past decades. Notwithstanding these techniques, "subspace-based strategies" (Du et al, 2011) can likewise perform well for palm print recognizable proof. For instance, Eigen palm and Fisher palm (Ribaric and Fratric, 2005) are two understood subspace based palm print recognizable proof techniques.…”

Section: Literature Surveymentioning

confidence: 99%

“…For instance, Eigen palm and Fisher palm (Ribaric and Fratric, 2005) are two understood subspace based palm print recognizable proof techniques. As of late, 2D appearance based techniques, for example, 2D Linear Discriminant Analysis (2DLDA) (Du et al, 2011) have likewise been utilized for palm print acknowledgment. Assist, the Representation Based Classification (RBC) technique additionally demonstrates great execution in palm print recognizable proof.…”

Section: Literature Surveymentioning

confidence: 99%

See 1 more Smart Citation

A combined score level fusion approach for multi model biometric system using left and right palm print

Sam¹,

Saravanan

2018

Int. j. adv. appl. sci.

View full text Add to dashboard Cite

Biometrics is the art of setting up the character of an individual in view of the physical, concoction or behavioral properties of the individual. Palm Print recognizable proof is an imperative individual ID innovation and it has pulled in much consideration. The palm print contains standard bends and wrinkles as well as rich surface and miniscule focuses, so the palm print ID can accomplish a high exactness. We propose a novel structure of joining the left with right palm print at the coordinating (matching) score level. In the system, three sorts of coordinating (matching) scores, which are separately acquired by the left palm print coordinating, right palm print coordinating and crossing coordinating between the left query and right training palm print, are fused to make the final decision. The structure not only combines the left and right palm print images for identification, additionally appropriately abuses the comparability between the left and right palm print of a similar subject. The proposed strategy accurately takes the method for the left and right palm print pictures into record, and plans estimation to survey the relation between them. In additament, by using this nearness, the proposed weighted cumulation scheme uses a system to facilitate the three sorts of scores incited from the left and right palm print pictures.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Section: Literature Surveymentioning

confidence: 99%

A combined score level fusion approach for multi model biometric system using left and right palm print

Sam¹,

Saravanan

2018

Int. j. adv. appl. sci.

View full text Add to dashboard Cite

show abstract

“…Similarly, some studies have applied both vertical and horizontal two-dimensional LDA (2DLDA) for extracting the Gabor features. After that, a distance-based adaptive strategy was used to combine the vertical and horizontal features [ 21 ].…”

Section: Introductionmentioning

confidence: 99%

An Effective Palmprint Recognition Approach for Visible and Multispectral Sensor Images

Gumaei

Sammouda

Al-Salman

et al. 2018

Sensors

View full text Add to dashboard Cite

Among several palmprint feature extraction methods the HOG-based method is attractive and performs well against changes in illumination and shadowing of palmprint images. However, it still lacks the robustness to extract the palmprint features at different rotation angles. To solve this problem, this paper presents a hybrid feature extraction method, named HOG-SGF that combines the histogram of oriented gradients (HOG) with a steerable Gaussian filter (SGF) to develop an effective palmprint recognition approach. The approach starts by processing all palmprint images by David Zhang’s method to segment only the region of interests. Next, we extracted palmprint features based on the hybrid HOG-SGF feature extraction method. Then, an optimized auto-encoder (AE) was utilized to reduce the dimensionality of the extracted features. Finally, a fast and robust regularized extreme learning machine (RELM) was applied for the classification task. In the evaluation phase of the proposed approach, a number of experiments were conducted on three publicly available palmprint databases, namely MS-PolyU of multispectral palmprint images and CASIA and Tongji of contactless palmprint images. Experimentally, the results reveal that the proposed approach outperforms the existing state-of-the-art approaches even when a small number of training samples are used.

show abstract

“…Wu et al [8] proposed the "FisherPalm" method by applying dimension reduction of Linear Discriminant Analysis (LDA) based on the Principal Component Analysis (PCA). Du et al [9] used the horizontal and vertical Two-Dimensional LDA (2DLDA) to extract the Gabor features of the palmprint images, and used distance-based adaptive strategy to combine these two features. The resulting high recognition rate confirms the validity of subspace-based methods; however, this method usually requires many training samples for each category and the selection of the training samples has significant impact on the recognition results.…”

Section: Introductionmentioning

confidence: 99%

A Palmprint Recognition Method Based on Gabor Wavelet and Local Direction Pattern

Yu¹,

Xie²

2015

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

Abstract. Palmprint recognition is an emerging biometric technology that identifies a person based on the hand image. In this paper, a novel palmprint identification method based on Gabor wavelets and Local Direction Pattern (LDP) techniques has been proposed. The Gabor response images at different scales and directions are obtained by convolving the multi-channel Gabor wavelet and palmprint images, which are further divided into non-overlapping sub-blocks. The LDP characteristics are extracted from each sub-block and the feature vector of palmprint image is then produced by combining them using the LDP operator. Finally, the palmprint images are identified using the nearest neighbor classification method. The proposed method has been verified on the public PolyU palmprint database, and the experimental results have shown that the proposed method is effective.

show abstract

Palmprint Recognition Using Gabor Feature-Based Bidirectional 2DLDA

Cited by 17 publications

References 6 publications

A combined score level fusion approach for multi model biometric system using left and right palm print

A combined score level fusion approach for multi model biometric system using left and right palm print

An Effective Palmprint Recognition Approach for Visible and Multispectral Sensor Images

A Palmprint Recognition Method Based on Gabor Wavelet and Local Direction Pattern

Contact Info

Product

Resources

About