Automatic face naming by learning discriminative
- 1. Automatic Face Naming by Learning Discriminative Affinity Matrices From Weakly Labeled Images ABSTRACT: Given a collection of images, where each image contains several faces and is associated with a few names in the corresponding caption, the goal of face naming is to infer the correct name for each face. In this paper, we propose two new methods to effectively solve this problem by learning two discriminative affinity matrices from these weakly labeled images. We first propose a new method called regularized low-rank representation by effectively utilizing weakly supervised information to learn a low-rank reconstruction coefficient matrix while exploring multiple subspace structures of the data. Specifically, by introducing a specially designed regularizer to the low-rank representation method, we penalize the corresponding reconstruction coefficients related to the situations where a face is reconstructed by using face images from other subjects or by using itself. With the inferred reconstruction coefficient matrix, a discriminative affinity matrix can be obtained. Moreover, we also develop a new distance metric learning method called ambiguously supervised structural metric learning by using weakly supervised information to seek a discriminative distance metric. Hence, another discriminative affinity matrix can be obtained using the similarity matrix (i.e., the kernel matrix) based on the Mahalanobis distances of the data. Observing that these two affinity
- 2. matrices contain complementary information, we further combine them to obtain a fused affinity matrix, based on which we develop a new iterative scheme to infer the name of each face. Comprehensive experiments demonstrate the effectiveness of our approach. EXISTING SYSTEM: Recently, there is an increasing research interest in developing automatic techniques for face naming in images as well as in videos. To tag faces in news photos, Berg et al. proposed to cluster the faces in the news images. Ozkan and Duygulu developed a graph-based method by constructing the similarity graph of faces and finding the densest component. Guillaumin et al.proposed the multiple-instance logistic discriminant metric learning (MildML) method. Luo and Orabona proposed a structural support vector machine (SVM)-like algorithm called maximum margin set (MMS) to solve the face naming problem. Recently, Zeng et al. proposed the low-rank SVM (LR-SVM) approach to deal with this problem based on the assumption that the feature matrix formed by faces from the same subject is low rank.
- 3. DISADVANTAGES OF EXISTING SYSTEM: Even after successfully performing these preprocessing steps, automatic face naming is still a challenging task. The faces from the same subject may have different appearances because of the variations in poses, illuminations, and expressions. The candidate name set may be noisy and incomplete, so a name may be mentioned in the caption, but the corresponding face may not appear in the image, and the correct name for a face in the image may not appear in the corresponding caption. Each detected face (including falsely detected ones) in an image can only be annotated using one of the names in the candidate name set or as null, which indicates that the ground-truth name does not appear in the caption. PROPOSED SYSTEM: In this paper, we focus on automatically annotating faces in images based on the ambiguous supervision from the associated captions. In this paper, we propose a new scheme for automatic face naming with caption-based supervision. Specifically, we develop two methods to
- 4. respectively obtain two discriminative affinity matrices by learning from weakly labeled images. The two affinity matrices are further fused to generate one fused affinity matrix, based on which an iterative scheme is developed for automatic face naming. To obtain the first affinity matrix, we propose a new method called regularized low-rank representation (rLRR) by incorporating weakly supervised information into the low-rank representation (LRR) method, so that the affinity matrix can be obtained from the resultant reconstruction coefficient matrix. To effectively infer the correspondences between the faces based on visual features and the names in the candidate name sets, we exploit the subspace structures among faces based on the following assumption: the faces from the same subject/name lie in the same subspace and the subspaces are linearly independent. We first propose a method called rLRR by introducing a new regularizer that incorporates caption-based weak supervision into the objective of LRR, in which we penalize the reconstruction coefficients when reconstructing the faces using those from different subjects.
- 5. Based on the inferred reconstruction coefficient matrix, we can compute an affinity matrix that measures the similarity values between every pair of faces. ADVANTAGES OF PROPOSED SYSTEM: Based on the caption-based weak supervision, we propose a new method rLRR by introducing a new regularizer into LRR and we can calculate the first affinity matrix using the resultant reconstruction coefficient matrix. We also propose a new distance metric learning approach ASML to learn a discriminative distance metric by effectively coping with the ambiguous labels of faces. The similarity matrix (i.e., the kernel matrix) based on the Mahalanobis distances between all faces is used as the second affinity matrix. With the fused affinity matrix by combining the two affinity matrices from rLRR and ASML, we propose an efficient scheme to infer the names of faces. Comprehensive experiments are conducted on one synthetic dataset and two real-world datasets, and the results demonstrate the effectiveness of our approaches.
- 6. SYSTEM ARCHITECTURE: SYSTEM REQUIREMENTS: HARDWARE REQUIREMENTS: System : Pentium IV 2.4 GHz. Hard Disk : 40 GB. Floppy Drive : 1.44 Mb. Monitor : 15 VGA Colour. Mouse : Logitech.
- 7. Ram : 512 Mb. SOFTWARE REQUIREMENTS: Operating system : Windows XP/7. Coding Language : C#.net Tool : Visual Studio 2010 Database : SQL SERVER 2008 REFERENCE: Shijie Xiao, Dong Xu, Senior Member, IEEE, and Jianxin Wu, Member, IEEE, “Automatic Face Naming by Learning Discriminative Affinity Matrices From Weakly Labeled Images”, IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2015.