In this paper, we propose an analysis mechanism-based structured analysis discriminative dictionary learning analysis discriminative dictionary learning, framework. The ADDL seamlessly integrates ADDL, analysis representation, and analysis classifier training into a unified model. The applied analysis mechanism can make sure that the learned dictionaries, representations, and linear classifiers over different classes are independent and discriminating as much as possible. The dictionary is obtained by minimizing a reconstruction error and an analytical incoherence promoting term that encourages the subdictionaries associated with different classes to be independent. To obtain the representation coefficients, ADDL imposes a sparse $l_{2,1}$ -norm constraint on the coding coefficients instead of using $l_{0}$ or $l_{1}$ norm, since the $l_{0}$ - or $l_{1}$ -norm constraint applied in most existing DL criteria makes the training phase time consuming. The code-extraction projection that bridges data with the sparse codes by extracting special features from the given samples is calculated via minimizing a sparse code approximation term. Then we compute a linear classifier based on the approximated sparse codes by an analysis mechanism to simultaneously consider the classification and representation powers. Thus, the classification approach of our model is very efficient, because it can avoid the extra time-consuming sparse reconstruction process with trained dictionary for each new test data as most existing DL algorithms. Simulations on real image databases demonstrate that our ADDL model can obtain superior performance over other state of the arts.

Jointly Learning Structured Analysis Discriminative Dictionary and Analysis Multiclass Classifier

The ever-growing development of sensor technology has led to the use of multimodal sensors to develop robotics and automation systems. It is therefore highly expected to develop methodologies capable of integrating information from multimodal sensors with the goal of improving the performance of surveillance, diagnosis, prediction, and so on. However, real multimodal data often suffer from significant weak-pairing characteristics, i.e., the full pairing between data samples may not be known, while pairing of a group of samples from one modality to a group of samples in another modality is known. In this paper, we establish a novel projective dictionary learning framework for weakly paired multimodal data fusion. By introducing a latent pairing matrix, we realize the simultaneous dictionary learning and the pairing matrix estimation, and therefore improve the fusion effect. In addition, the kernelized version and the optimization algorithms are also addressed. Extensive experimental validations on some existing data sets are performed to show the advantages of the proposed method. Note to Practitioners —In many industrial environments, we usually use multiple heterogeneous sensors, which provide multimodal information. Such multimodal data usually lead to two technical challenges. First, different sensors may provide different patterns of data. Second, the full-pairing information between modalities may not be known. In this paper, we develop a unified model to tackle such problems. This model is based on a projective dictionary learning method, which efficiently produces the representation vector for the original data by an explicit form. In addition, the latent pairing relation between samples can be learned automatically and be used to improve the classification performance. Such a method can be flexibly used for multimodal fusion with full-pairing, partial-pairing and weak-pairing cases.

Weakly Paired Multimodal Fusion for Object Recognition

Pairwise prediction-error expansion (pairwise PEE) is a recent technique for the high-dimensional reversible data hiding However, in the absence of adaptive embedding, its potential has not been fully exploited In this paper, we propose the adaptive pixel pairing (APP) and the adaptive mapping selection for the enhancement of pairwise PEE Our motivation is twofold: building a sharper 2D histogram and designing the effective 2D mapping for it In APP, we consider to increase the similarity between pixels in a pair, by excluding the rough pixels from pairing and only putting the smooth pixels into pairs In this way, the pixels in a pair have a larger possibility of being equal, and thus the resulted 2D prediction-error histogram (PEH) has lower entropy Next, the adaptive mapping selection mechanism is introduced to properly determine the optimal modification, based on “whether it fits for the resulted PEH” rather than heuristic experience The experimental results show that the proposed method has a significant improvement over the pairwise PEE

Improving Pairwise PEE via Hybrid-Dimensional Histogram Generation and Adaptive Mapping Selection

Robust, discriminative and comprehensive dictionary learning for face recognition

Unsupervised feature selection has shown significant potential in distance-based clustering tasks. This paper proposes a novel triplet induced method. Firstly, a triplet-based loss function is introduced to enforce the selected feature groups to preserve ordinal locality of original data, which contributes to distance-based clustering tasks. Secondly, we simplify the orthogonal basis clustering by imposing an orthogonal constraint on the feature projection matrix. Consequently, a general framework for simultaneous feature selection and clustering is discussed. Thirdly, an alternating minimization algorithm is employed to efficiently optimize the proposed model together with rapid convergence. Extensive comparison experiments on several benchmark datasets well validate the encouraging gain in clustering from our proposed method.

Unsupervised feature selection with ordinal locality

Dictionary learning (DL) has been successfully applied to various pattern classification tasks in recent years. However, analysis dictionary learning (ADL), as a major branch of DL, has not yet been fully exploited in classification due to its poor discriminability. This paper presents a novel DL method, namely Discriminative Analysis Dictionary Learning (DADL), to improve the classification performance of ADL. First, a code consistent term is integrated into the basic analysis model to improve discriminability. Second, a triplet-constraint-based local topology preserving loss function is introduced to capture the discriminative geometrical structures embedded in data. Third, correntropy induced metric is employed as a robust measure to better control outliers for classification. Then, half-quadratic minimization and alternate search strategy are used to speed up the optimization process so that there exist closed-form solutions in each alternating minimization stage. Experiments on several commonly used databases show that our proposed method not only significantly improves the discriminative ability of ADL, but also outperforms state-of-the-art synthesis DL methods.

/pdf/discriminative-analysis-dictionary-learning-3jj2y8om0e.pdf

Discriminative analysis dictionary learning

The invention discloses a behavior identification method based on an integrated linear classifier and an analytic dictionary; and with the method, the behavior identification accuracy rate and the operating speed can be increased. Pretreatment is carried out on a training set sample and a testing set sample, a high-level expression way is employed for a behavior video sample, and each sample corresponds to a feature column vector with the semantic enrichment characteristic; optimized learning is carried out to obtain an analytic dictionary omega and an integrated linear classifier R; a coding coefficient of the testing sample is obtained; and the coding coefficient of the testing sample and the integrated linear classifier R are inputted into the classifier, thereby obtaining a final classification result.

Behavior identification method based on integrated linear classifier and analytic dictionary

Conventional additive spread-spectrum (SS) data embedding has a dangerous security flaw that unauthorized receivers can blindly extract hidden information without the knowledge of carrier(s). In this paper, pseudo-noise (PN) masking technique is adopted as an efficient security measure against illegitimate data extraction. The proposed PN-sequence masked SS embedding can offer efficient security against current SS embedding analysis without inducing any additional distortion to host nor notable recovery performance loss. To further improve recovery performance, optimal carrier design for PN-masked SS embedding is also developed. With any given host distortion budget, we aim at designing a carrier to maximize the output signal-to-interference-plus-noise ratio (SINR) of the corresponding maximum-SINR linear filter. Then, we present jointly optimal carrier and linear processor designs for PN-masked SS embedding in linearly modified transform domain host data. Finally, PN-masked multi-carrier/multi-message SS embedding is studied as well. The extensive experimental studies confirm our analytical performance predictions and illustrate the benefits of the designed PN masked optimal SS embedding. HighlightsPN masked SS embedding can offer efficient security against current SS embedding analysis.Optimal carrier designs can further improve recovery performance.PN-masked multi-carrier/multi-message SS embedding is also studied.Experimental studies confirm the benefits of the PN-masked optimal SS embedding.

/pdf/secure-spread-spectrum-data-embedding-with-pn-sequence-57bz0fmnsw.pdf

Secure spread-spectrum data embedding with PN-sequence masking

In recent years, dictionary learning (DL) has shown significant potential in various classification tasks. However, most of previous works aim to learn a synthesis dictionary. The other major category of DL-analysis dictionary learning has not been fully exploited yet. This paper proposes a novel DL method, named Topology Preserving Dictionary Learning (TPDL). First, we propose a triplet-constraint-based topology preserving loss function to capture the underlying local topological structures of data in a supervised manner. Second, a sparse-label-matrix-based function is integrated into the basic analysis model to improve discriminative ability. Third, Huber M-estimator is employed as a robust metric to handle the errors (e.g., outliers and noise) that possibly exist in data. Then, an alternating optimization algorithm is developed based on half-quadratic minimization and alternate search strategy. Closed-form solutions in each alternating optimization stage speed up the minimization process. Experiments on four commonly used datasets show that our proposed TPDL achieves competitive performance in contrast to state-of-the-art DL methods.

Topology preserving dictionary learning for pattern classification

Rapid popularization of smart cell phone equipped with camera has led to a number of new legal and criminal problems related to multimedia such as digital image, which makes cell phone source identification an important branch of digital image forensics. This paper proposes a classifier combination based source identification strategy for cell phone images. To identify the outlier cell phone models of the training sets in multi-class classifier, a one-class classifier is orderly used in the framework. Feature vectors including color filter array (CFA) interpolation coefficients estimation and multi-feature fusion is employed to verify the effectiveness of the classifier combination strategy. Experimental results demonstrate that for different feature sets, our method presents high accuracy of source identification both for the cell phone in the training sets and the outliers.

/pdf/classifier-combination-based-source-identification-for-cell-2sg60q7pi9.pdf

Yanqing Guo

Papers

Discriminative analysis dictionary learning

Behavior identification method based on integrated linear classifier and analytic dictionary

Secure spread-spectrum data embedding with PN-sequence masking

Topology preserving dictionary learning for pattern classification

Classifier Combination Based Source Identification for Cell Phone Images