A gender recognition algorithm based on VLBP (volume localbinarypatterns) and LBP-TOP (localbinarypatterns from three orthogonal panels) of human shadow sequences motion feature in complex scene was proposed. Firs...
详细信息
A gender recognition algorithm based on VLBP (volume localbinarypatterns) and LBP-TOP (localbinarypatterns from three orthogonal panels) of human shadow sequences motion feature in complex scene was proposed. Firstly, VLBP and LBP-TOP were adopted with image sequences preprocessing namely image sequence blocks blocking and three-dimensional filtering to extract dynamic behavior characteristics. Secondly, the support vector machine (SVM) was trained to predict motion human gender with various samples. Finally the influences of blocks, time radius and filtering on recognition accuracy were analyzed. Experiments indicate that this algorithm can extract dynamic features effectively, especially in complex scenes with large illumination variation and background changes. On our database, the SVM with VLBP achieves the recognition accuracy of 83.33%, and the SVM with LBP-TOP achieves 94.44%, respectively.
As an effective texture description operator, localbinarypatterns (LBP) has the advantages of low computation complexity, low memory consumption and clear principle. Damper-Shafter evidence theory satisfies the cond...
详细信息
An efficient texture-based method is presented to identify the stars in the sensor field. Each star is modeled as a group of extensions to local binary pattern (LBP) that is calculated over a circular region around th...
详细信息
ISBN:
(纸本)9781424480364
An efficient texture-based method is presented to identify the stars in the sensor field. Each star is modeled as a group of extensions to local binary pattern (LBP) that is calculated over a circular region around the star. The approach provides us with many advantages compared to the state-of-the-art. Experimental results clearly justify our model.
Facial expression recognition (FER) plays a vital role in human computer interaction and has become important filed of choice for researchers in computer vision and artificial intelligence over the last two decades. I...
详细信息
ISBN:
(纸本)9781538628430;9781538628423
Facial expression recognition (FER) plays a vital role in human computer interaction and has become important filed of choice for researchers in computer vision and artificial intelligence over the last two decades. Illumination, pose, zoom level are major obstacles in the classification of FER. A good preprocessing and feature extraction algorithm would improve the performance of FER. In this paper, two models are proposed for FER using Gabor wavelets and local binary pattern (LBP) for feature extraction using kirsch edge detection algorithm for preprocessing in these methods. Support vector machine (SVM) classifier gives good recognition accuracies on benchmark datasets Cohn Kanade, JAFFE, MMI and KDEF.
In Biometric fingerprints are most promising technology for identification and verification in various applications. The general fingerprint matching algorithms perform poorly in case of partial prints and may discard...
详细信息
ISBN:
(纸本)9781479939152
In Biometric fingerprints are most promising technology for identification and verification in various applications. The general fingerprint matching algorithms perform poorly in case of partial prints and may discard these prints during matching. The major problems with partial prints is the lack of level 1 and level 2 features which makes them distinguishable. Therefore, we can utilize level 3 features such as pores corresponding LBP ectraction in combination with level 2 features based radon transform. Pores are one of the discriminative level 3 feature and with the advancement in the technology they can be successively employed using Automatic Fingerprint (AFIS) identification systems. In this paper, Our main aim is to provide a method to increase accuracy of partial fingerprint matching in order to estimate Equal error rate(ERR) based on False Acceptance Rate and False Rejection Rate. In proposed method, score level fusion of minutiae based radon transform and pores based LBP matching is *** method can surpasses the results of other matching approach which uses single matching *** performance can be evaluated by calculating ERR based on False Acceptance Rate (FAR) and False Rejection Rate (FRR).
ABSTRACTThe rapid development in computer technology plays an essential role in the research works for performing fast and accurate identification of flower species through the processing of flower images with the sup...
详细信息
ABSTRACTThe rapid development in computer technology plays an essential role in the research works for performing fast and accurate identification of flower species through the processing of flower images with the support of mobile devices that seeks more attention in the research areas. It is highly significant for maintaining the sensitivity of ecological balance, and therefore, the image-processing approaches have provided improved outcomes in recent days. To rectify these existing problems and improve the accuracy attains the flower classification, the CNN variants of ensemble techniques can be used for the dynamic ensemble selection of the CNN networks. This paper develops an enhanced ensemble deep learning-based flower classification model to get efficient classification results with optimal models. The pre-processing is done through the Contrast Limited Adaptive Histogram Equalization (CLAHE) and filtering techniques. The pre-processed images are considered for the optimal pattern extraction phase, where optimal hybrid patterns are extracted from the local binary pattern (LBP) and local Vector pattern (LVP). Here, the optimal hybrid pattern extraction phase contains the optimization in it using the enhanced heuristic algorithm named Improved Rat Swarm Optimizer (IRSO). The flower classification is performed with an Adaptive Dynamic Ensemble Transfer learning-based Convolutional Neural Network (ADET-CNN). Here, the optimal models are selected with the support of the same RSO algorithm. The experimental results show a better efficacy of the developed flower classification framework.
ABSTRACTIn information and security, the personal identification of individuals becomes much more important. For improving security, several biometric recognition techniques are implemented. However, in finger vein re...
详细信息
ABSTRACTIn information and security, the personal identification of individuals becomes much more important. For improving security, several biometric recognition techniques are implemented. However, in finger vein recognition, it faces the critical problem of fake finger vein images, security and less accuracy. To conquer this problem, Hybrid Feature Extraction with Linear local Tangent Space Alignment-based dimension reduction and Support Vector Machine classifier (HFE–LLTSA–SVM) is proposed. In this hybrid, FE is considered as the combination of histogram of oriented gradients (HOG), grey-level co-occurrence matrix (GLCM), stationary wavelet transform (SWT), and local binary pattern (LBP) for extracting the hybrid feature. LLTSA perform dimension reduction in the outputs of HFE from HOG, GLCM, and LBP. Furthermore, SVM is used for classification which gives authentication based on error-correcting code. Finally, the performance parameters were calculated and the proposed method achieved better accuracy of 99.75%, when compared with existing methods.
暂无评论