- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
An affine view and illumination invariant iterative image matching approach for face recognition
摘要： Feature detection and image matching constitutes two primary tasks in photogrammetric and have multiple applications in a number of fields. One such application is face recognition. The critical nature of this application demands that image matching algorithm used in recognition of features in facial recognition to be robust and fast. The proposed method uses affine transforms to recognize the descriptors and classified by means of Bayes theorem. This paper demonstrates the suitability of the proposed image matching algorithm for use in face recognition appli-cations. Yale facial data set is used in the validation and the results are compared with SIFT (Scale Invariant Feature Transform) based face recognition approach.
关键词： SIFT,Bayes,Iterative Approach,Yale,Face Recognition
更新于2025-09-04 15:30:14
-
[IEEE 2018 26th European Signal Processing Conference (EUSIPCO) - Roma, Italy (2018.9.3-2018.9.7)] 2018 26th European Signal Processing Conference (EUSIPCO) - On Multi-View Face Recognition Using Lytro Images
摘要： In this work, a simple and efficient approach for recognizing faces from light field images, notably from Lytro Illum camera, is proposed. The suggested method is based on light field images property of being rendered through a multi-view representation. In the preliminary analysis, feature vectors extracted from different views of the same Lytro picture are proved different enough to provide complementary information beneficial for face recognition purpose. Starting from a set of multiple views for each data, face verification problem is tackled and results are compared with those achieved with classical 2D images simulated using a single view, i.e. the central one. Two experiments are described and, in both cases, the presented method shows superior performances than standard algorithms adopted by classical imaging sensors.
关键词： Lytro camera,Multi-view,light field images,face recognition
更新于2025-09-04 15:30:14
-
An Adaptive Entropy Based Scale Invariant Face Recognition Face Altered by Plastic Surgery
摘要： Face recognition is one of the challenging problems which suffer from practical issues like the pose, expression, illumination changes, and aging. Plastic surgery is one among the issues that pose great difficulty in recognizing the faces. The literature has been reported with traditional features and classifiers for recognizing the faces after plastic surgery. This paper presents an adaptive feature descriptor and advanced classifier for plastic surgery face recognition. According to the proposed feature descriptor, firstly an adaptive Gaussian transfer function is determined to perform Adaptive Gaussian Filtering (AGF) for images. Secondly, Adaptive Entropy-based SIFT (AEV-SIFT) features are extracted from the filtered images. Unlike traditional SIFT, the proposed AEV-SIFT extracts the key points based on the entropy of the volume information of the pixel intensities. This provides the least effect on uncertain variations in the face because the entropy is the higher order statistical feature. Further, the classification is performed with variations. In the first variation, support vector machine (SVM) is used as a classifier, whereas the second variation exploits the Deep Learning Network (DLN) for recognizing the faces based on the AEV-SIFT features. The proposed method classifies the plastic surgery face images with the accuracy of 80.15%, sensitivity of 19.75% and specificity of 95%, which are obviously better than the traditional features such as SIFT, V-SIFT, and Principal Component Analysis (PCA).
关键词： plastic surgery,face recognition,adaptive Gaussian kernel,EV-SIFT feature,SVM and DLN classification
更新于2025-09-04 15:30:14
-
[Lecture Notes in Computer Science] Pattern Recognition and Computer Vision Volume 11258 (First Chinese Conference, PRCV 2018, Guangzhou, China, November 23-26, 2018, Proceedings, Part III) || Face Recognition Based on Multi-view
摘要： Face recognition is an important research area in human-computer. To solve the problem about the inaccuracy and incompleteness of feature extraction and recognition, an ensemble learning method on face recognition is proposed in this paper. This method is a combination of a variety of feature extraction and classi?cation ensemble technology. In feature extraction, wavelet transform and edge detection are used for extracting features. In classi?cation recognition, the K nearest neighbor (KNN) classi?er, wavelet neural network (WNN) and support vector machine (SVM) are used for preliminary identi?cation. Each classi?er corresponds to a feature method and then the classi?cation of the three views are constructed. The ?nal output results are integrated by voting strategy. Experimental results show that this method can improve the identi?cation rate compared with the single classi?er.
关键词： Feature extraction,Multi-view,Ensemble learning,Face recognition,Voting
更新于2025-09-04 15:30:14
-
[Studies in Computational Intelligence] Recent Advances in Computer Vision Volume 804 (Theories and Applications) || Face Recognition Using Exact Gaussian-Hermit Moments
摘要： Face recognition systems have gained more attention during the last decades. Accurate features are the corner stones in these systems where the performance of recognition and classification processes mainly depends on these features. In this chapter, a new method is proposed for a highly accurate face recognition system. Exact Gaussian-Hermit moments (EGHMs) are used to extract the features of face images where the higher order EGHMs are able to capture the higher-order nonlinear features of these images. The rotation, scaling and translation invariants of EGHMs are used to overcome the geometric distortions. The non-negative matrix factorization (NMF) is a popular image representation method that is able to avoid the drawbacks of principle component analysis (PCA) and independent component analysis (ICA) methods and is able to maintain the image variations. The NMF is used to classify the extracted features. The proposed method is assessed using three face datasets, the ORL, Ncku and UMIST which have different characteristics. The experimental results illustrate the high accuracy of the proposed method against other methods.
关键词： Feature extraction,Face recognition,Exact Gaussian-Hermit moments,Non-negative matrix factorization,Classification
更新于2025-09-04 15:30:14