Visual classification with multitask joint sparse representation

Distributed Jointly Sparse Multitask Learning Over Networks

Distributed data processing over networks has received a lot of attention due to its wide applicability. In this paper, we consider the multitask problem of in-network distributed estimation. For the multitask problem, the unknown parameter vectors (tasks) for different nodes can be different. Moreover, considering some real application scenarios, it is also assumed that there are some similarities among the tasks. Thus, the intertask cooperation is helpful to enhance the estimation performance. In this paper, we exploit an additional special characteristic of the vectors of interest, namely, joint sparsity, aiming to further enhance the estimation performance. A distributed jointly sparse multitask algorithm for the collaborative sparse estimation problem is derived. In addition, an adaptive intertask cooperation strategy is adopted to improve the robustness against the degree of difference among the tasks. The performance of the proposed algorithm is analyzed theoretically, and its effectiveness is verified by some simulations.

Multi-View Multi-Instance Learning Based on Joint Sparse Representation and Multi-View Dictionary Learning

In multi-instance learning (MIL), the relations among instances in a bag convey important contextual information in many applications. Previous studies on MIL either ignore such relations or simply model them with a fixed graph structure so that the overall performance inevitably degrades in complex environments. To address this problem, this paper proposes a novel multi-view multi-instance learning algorithm (MIL) that combines multiple context structures in a bag into a unified framework. The novel aspects are: (i) we propose a sparse -graph model that can generate different graphs with different parameters to represent various context relations in a bag, (ii) we propose a multi-view joint sparse representation that integrates these graphs into a unified framework for bag classification, and (iii) we propose a multi-view dictionary learning algorithm to obtain a multi-view graph dictionary that considers cues from all views simultaneously to improve the discrimination of the MIL. Experiments and analyses in many practical applications prove the effectiveness of the M IL.

An Advanced Hybrid Technique of DCS and JSRC for Telemonitoring of Multi-Sensor Gait Pattern

The jointly quantitative analysis of multi-sensor gait data for the best gait-classification performance has been a challenging endeavor in wireless body area networks (WBANs)-based gait telemonitoring applications. In this study, based on the joint sparsity of data, we proposed an advanced hybrid technique of distributed compressed sensing (DCS) and joint sparse representation classification (JSRC) for multi-sensor gait classification. Firstly, the DCS technique is utilized to simultaneously compress multi-sensor gait data for capturing spatio-temporal correlation information about gait while the energy efficiency of the sensors is available. Then, the jointly compressed gait data are directly used to develop a novel neighboring sample-based JSRC model by defining the sparse representation coefficients-inducing criterion (SRCC), in order to yield the best classification performance as well as a lower computational time cost. The multi-sensor gait data were selected from an open wearable action recognition database (WARD) to validate the feasibility of our proposed method. The results showed that when the comparison ratio and the number of neighboring samples are selected as 70% and 40%, respectively, the best accuracy (95%) can be reached while the lowest computational time spends only 60 ms. Moreover, the best accuracy and the computational time can increase by 5% and decrease by 40 ms, respectively, when compared with the traditional JSRC techniques. Our proposed hybrid technique can take advantage of the joint sparsity of data for jointly processing multi-sensor gait data, which greatly contributes to the best gait-classification performance. This has great potential for energy-efficient telemonitoring of multi-sensor gait.

Promoting Similarity of Sparsity Structures in Integrative Analysis with Penalization

For data with high-dimensional covariates but small sample sizes, the analysis of single datasets often generates unsatisfactory results. The integrative analysis of multiple independent datasets provides an effective way of pooling information and outperforms single-dataset and several alternative multi-datasets methods. Under many scenarios, multiple datasets are expected to share common important covariates, that is, the corresponding models have similarity in their sparsity structures. However, the existing methods do not have a mechanism to promote the similarity in sparsity structures in integrative analysis. In this study, we consider penalized variable selection and estimation in integrative analysis. We develop an L₀-penalty based method, which explicitly promotes the similarity in sparsity structures. Computationally it is realized using a coordinate descent algorithm. Theoretically it has the selection and estimation consistency properties. Under a wide spectrum of simulation scenarios, it has identification and estimation performance comparable to or better than the alternatives. In the analysis of three lung cancer datasets with gene expression measurements, it identifies genes with sound biological implications and satisfactory prediction performance.

HD-MTL: Hierarchical Deep Multi-Task Learning for Large-Scale Visual Recognition

In this paper, a hierarchical deep multi-task learning (HD-MTL) algorithm is developed to support large-scale visual recognition (e.g., recognizing thousands or even tens of thousands of atomic object classes automatically). First, multiple sets of multi-level deep features are extracted from different layers of deep convolutional neural networks (deep CNNs), and they are used to achieve more effective accomplishment of the coarseto- fine tasks for hierarchical visual recognition. A visual tree is then learned by assigning the visually-similar atomic object classes with similar learning complexities into the same group, which can provide a good environment for determining the interrelated learning tasks automatically. By leveraging the inter-task relatedness (inter-class similarities) to learn more discriminative group-specific deep representations, our deep multi-task learning algorithm can train more discriminative node classifiers for distinguishing the visually-similar atomic object classes effectively. Our hierarchical deep multi-task learning (HD-MTL) algorithm can integrate two discriminative regularization terms to control the inter-level error propagation effectively, and it can provide an end-to-end approach for jointly learning more representative deep CNNs (for image representation) and more discriminative tree classifier (for large-scale visual recognition) and updating them simultaneously. Our incremental deep learning algorithms can effectively adapt both the deep CNNs and the tree classifier to the new training images and the new object classes. Our experimental results have demonstrated that our HD-MTL algorithm can achieve very competitive results on improving the accuracy rates for large-scale visual recognition.

Plant species classification using flower images-A comparative study of local feature representations

Steady improvements of image description methods induced a growing interest in image-based plant species classification, a task vital to the study of biodiversity and ecological sensitivity. Various techniques have been proposed for general object classification over the past years and several of them have already been studied for plant species classification. However, results of these studies are selective in the evaluated steps of a classification pipeline, in the utilized datasets for evaluation, and in the compared baseline methods. No study is available that evaluates the main competing methods for building an image representation on the same datasets allowing for generalized findings regarding flower-based plant species classification. The aim of this paper is to comparatively evaluate methods, method combinations, and their parameters towards classification accuracy. The investigated methods span from detection, extraction, fusion, pooling, to encoding of local features for quantifying shape and color information of flower images. We selected the flower image datasets Oxford Flower 17 and Oxford Flower 102 as well as our own Jena Flower 30 dataset for our experiments. Findings show large differences among the various studied techniques and that their wisely chosen orchestration allows for high accuracies in species classification. We further found that true local feature detectors in combination with advanced encoding methods yield higher classification results at lower computational costs compared to commonly used dense sampling and spatial pooling methods. Color was found to be an indispensable feature for high classification results, especially while preserving spatial correspondence to gray-level features. In result, our study provides a comprehensive overview of competing techniques and the implications of their main parameters for flower-based plant species classification.

Half-Face Dictionary Integration for Representation-Based Classification

This paper presents a half-face dictionary integration (HFDI) algorithm for representation-based classification. The proposed HFDI algorithm measures residuals between an input signal and the reconstructed one, using both the original and the synthesized dual-column (row) half-face training samples. More specifically, we first generate a set of virtual half-face samples for the purpose of training data augmentation. The aim is to obtain high-fidelity collaborative representation of a test sample. In this half-face integrated dictionary, each original training vector is replaced by an integrated dual-column (row) half-face matrix. Second, to reduce the redundancy between the original dictionary and the extended half-face dictionary, we propose an elimination strategy to gain the most robust training atoms. The last contribution of the proposed HFDI method is the use of a competitive fusion method weighting the reconstruction residuals from different dictionaries for robust face classification. Experimental results obtained from the Facial Recognition Technology, Aleix and Robert, Georgia Tech, ORL, and Carnegie Mellon University-pose, illumination and expression data sets demonstrate the effectiveness of the proposed method, especially in the case of the small sample size problem.

Elastic Net Hypergraph Learning for Image Clustering and Semi-Supervised Classification

Graph model is emerging as a very effective tool for learning the complex structures and relationships hidden in data. In general, the critical purpose of graph-oriented learning algorithms is to construct an informative graph for image clustering and classification tasks. In addition to the classical K-nearest-neighbor and r-neighborhood methods for graph construction, l₁-graph and its variants are emerging methods for finding the neighboring samples of a center datum, where the corresponding ingoing edge weights are simultaneously derived by the sparse reconstruction coefficients of the remaining samples. However, the pairwise links of l₁-graph are not capable of capturing the high-order relationships between the center datum and its prominent data in sparse reconstruction. Meanwhile, from the perspective of variable selection, the l₁ norm sparse constraint, regarded as a LASSO model, tends to select only one datum from a group of data that are highly correlated and ignore the others. To simultaneously cope with these drawbacks, we propose a new elastic net hypergraph learning model, which consists of two steps. In the first step, the robust matrix elastic net model is constructed to find the canonically related samples in a somewhat greedy way, achieving the grouping effect by adding the l₂ penalty to the l₁ constraint. In the second step, hypergraph is used to represent the high order relationships between each datum and its prominent samples by regarding them as a hyperedge. Subsequently, hypergraph Laplacian matrix is constructed for further analysis. New hypergraph learning algorithms, including unsupervised clustering and multi-class semi-supervised classification, are then derived. Extensive experiments on face and handwriting databases demonstrate the effectiveness of the proposed method.

Image and Video Restoration and Enhancement via Sparse Representation

The chapter provides a survey of recent advances in image/video restoration and enhancement via spare representation. Images/videos usually unavoidably suffer from noises due to sensor imperfection or poor illumination. Numerous contributions have addressed this problem from diverse points of view. Recently, the use of sparse and redundant representations over learned dictionaries has become one specific approach. One goal here is to provide a survey of advances in image/video denoising via sparse representation. Moreover, to consider more general types of noise, this chapter also addresses the problems about removals of structured/unstructured components (e.g., rain streaks or blocking artifacts) from image/video. Moreover, image/video quality may be degraded from low-resolution due to low-cost acquisition. Hence, this chapter also provides a survey of recently advances in super-resolution via sparse representation. Finally, the conclusion can be drawn that sparse representation techniques have been reliable solutions in several problems of image/video restoration and enhancement.

Hyperspectral Image Classification via Multitask Joint Sparse Representation and Stepwise MRF Optimization

Hyperspectral image (HSI) classification is a crucial issue in remote sensing. Accurate classification benefits a large number of applications such as land use analysis and marine resource utilization. But high data correlation brings difficulty to reliable classification, especially for HSI with abundant spectral information. Furthermore, the traditional methods often fail to well consider the spatial coherency of HSI that also limits the classification performance. To address these inherent obstacles, a novel spectral-spatial classification scheme is proposed in this paper. The proposed method mainly focuses on multitask joint sparse representation (MJSR) and a stepwise Markov random filed framework, which are claimed to be two main contributions in this procedure. First, the MJSR not only reduces the spectral redundancy, but also retains necessary correlation in spectral field during classification. Second, the stepwise optimization further explores the spatial correlation that significantly enhances the classification accuracy and robustness. As far as several universal quality evaluation indexes are concerned, the experimental results on Indian Pines and Pavia University demonstrate the superiority of our method compared with the state-of-the-art competitors.

Efficient $\chi ^{2}$ Kernel Linearization via Random Feature Maps

Explicit feature mapping is an appealing way to linearize additive kernels, such as χ² kernel for training large-scale support vector machines (SVMs). Although accurate in approximation, feature mapping could pose computational challenges in high-dimensional settings as it expands the original features to a higher dimensional space. To handle this issue in the context of χ² kernel SVMs learning, we introduce a simple yet efficient method to approximately linearize χ² kernel through random feature maps. The main idea is to use sparse random projection to reduce the dimensionality of feature maps while preserving their approximation capability to the original kernel. We provide approximation error bound for the proposed method. Furthermore, we extend our method to χ² multiple kernel SVMs learning. Extensive experiments on large-scale image classification tasks confirm that the proposed approach is able to significantly speed up the training process of the χ² kernel SVMs at almost no cost of testing accuracy.

Robust Visual Knowledge Transfer via Extreme Learning Machine Based Domain Adaptation

We address the problem of visual knowledge adaptation by leveraging labeled patterns from source domain and a very limited number of labeled instances in target domain to learn a robust classifier for visual categorization. This paper proposes a new extreme learning machine based cross-domain network learning framework, that is called Extreme Learning Machine (ELM) based Domain Adaptation (EDA). It allows us to learn a category transformation and an ELM classifier with random projection by minimizing the -norm of the network output weights and the learning error simultaneously. The unlabeled target data, as useful knowledge, is also integrated as a fidelity term to guarantee the stability during cross domain learning. It minimizes the matching error between the learned classifier and a base classifier, such that many existing classifiers can be readily incorporated as base classifiers. The network output weights cannot only be analytically determined, but also transferrable. Additionally, a manifold regularization with Laplacian graph is incorporated, such that it is beneficial to semi-supervised learning. Extensively, we also propose a model of multiple views, referred as MvEDA. Experiments on benchmark visual datasets for video event recognition and object recognition, demonstrate that our EDA methods outperform existing cross-domain learning methods.

Multimodal Multipart Learning for Action Recognition in Depth Videos

The articulated and complex nature of human actions makes the task of action recognition difficult. One approach to handle this complexity is dividing it to the kinetics of body parts and analyzing the actions based on these partial descriptors. We propose a joint sparse regression based learning method which utilizes the structured sparsity to model each action as a combination of multimodal features from a sparse set of body parts. To represent dynamics and appearance of parts, we employ a heterogeneous set of depth and skeleton based features. The proper structure of multimodal multipart features are formulated into the learning framework via the proposed hierarchical mixed norm, to regularize the structured features of each part and to apply sparsity between them, in favor of a group feature selection. Our experimental results expose the effectiveness of the proposed learning method in which it outperforms other methods in all three tested datasets while saturating one of them by achieving perfect accuracy.

Robust Multi-Focus Image Fusion Using Multi-Task Sparse Representation and Spatial Context

We present a novel fusion method based on a multi-task robust sparse representation (MRSR) model and spatial context information to address the fusion of multi-focus gray-level images with misregistration. First, we present a robust sparse representation (RSR) model by replacing the conventional least-squared reconstruction error by a sparse reconstruction error. We then propose a multi-task version of the RSR model, viz., the MRSR model. The latter is then applied to multi-focus image fusion by employing the detailed information regarding each image patch and its spatial neighbors to collaboratively determine both the focused and defocused regions in the input images. To achieve this, we formulate the problem of extracting details from multiple image patches as a joint multi-task sparsity pursuit based on the MRSR model. Experimental results demonstrate that the suggested algorithm is competitive with the current state-of-the-art and superior to some approaches that use traditional sparse representation methods when input images are misregistered.

Medical image registration using sparse coding of image patches

Image registration is a basic task in medical image processing applications like group analysis and atlas construction. Similarity measure is a critical ingredient of image registration. Intensity distortion of medical images is not considered in most previous similarity measures. Therefore, in the presence of bias field distortions, they do not generate an acceptable registration. In this paper, we propose a sparse based similarity measure for mono-modal images that considers non-stationary intensity and spatially-varying distortions. The main idea behind this measure is that the aligned image is constructed by an analysis dictionary trained using the image patches. For this purpose, we use "Analysis K-SVD" to train the dictionary and find the sparse coefficients. We utilize image patches to construct the analysis dictionary and then we employ the proposed sparse similarity measure to find a non-rigid transformation using free form deformation (FFD). Experimental results show that the proposed approach is able to robustly register 2D and 3D images in both simulated and real cases. The proposed method outperforms other state-of-the-art similarity measures and decreases the transformation error compared to the previous methods. Even in the presence of bias field distortion, the proposed method aligns images without any preprocessing.

Discriminative sparse subspace learning and its application to unsupervised feature selection

In order to efficiently use the intrinsic data information, in this study a Discriminative Sparse Subspace Learning (DSSL) model has been investigated for unsupervised feature selection. First, the feature selection problem is formulated as a subspace learning problem. In order to efficiently learn the discriminative subspace, we investigate the discriminative information in the subspace learning process. Second, a two-step TDSSL algorithm and a joint modeling JDSSL algorithm are developed to incorporate the clusters׳ assignment as the discriminative information. Then, a convergence analysis of these two algorithms is provided. A kernelized discriminative sparse subspace learning (KDSSL) method is proposed to handle the nonlinear subspace learning problem. Finally, extensive experiments are conducted on real-world datasets to show the superiority of the proposed approaches over several state-of-the-art approaches.

Joint Sparse Representation and Robust Feature-Level Fusion for Multi-Cue Visual Tracking

Visual tracking using multiple features has been proved as a robust approach because features could complement each other. Since different types of variations such as illumination, occlusion, and pose may occur in a video sequence, especially long sequence videos, how to properly select and fuse appropriate features has become one of the key problems in this approach. To address this issue, this paper proposes a new joint sparse representation model for robust feature-level fusion. The proposed method dynamically removes unreliable features to be fused for tracking by using the advantages of sparse representation. In order to capture the non-linear similarity of features, we extend the proposed method into a general kernelized framework, which is able to perform feature fusion on various kernel spaces. As a result, robust tracking performance is obtained. Both the qualitative and quantitative experimental results on publicly available videos show that the proposed method outperforms both sparse representation-based and fusion based-trackers.

Multi-channel EEG-based sleep stage classification with joint collaborative representation and multiple kernel learning

BACKGROUND

Electroencephalography (EEG) based sleep staging is commonly used in clinical routine. Feature extraction and representation plays a crucial role in EEG-based automatic classification of sleep stages. Sparse representation (SR) is a state-of-the-art unsupervised feature learning method suitable for EEG feature representation.

NEW METHOD

Collaborative representation (CR) is an effective data coding method used as a classifier. Here we use CR as a data representation method to learn features from the EEG signal. A joint collaboration model is established to develop a multi-view learning algorithm, and generate joint CR (JCR) codes to fuse and represent multi-channel EEG signals. A two-stage multi-view learning-based sleep staging framework is then constructed, in which JCR and joint sparse representation (JSR) algorithms first fuse and learning the feature representation from multi-channel EEG signals, respectively. Multi-view JCR and JSR features are then integrated and sleep stages recognized by a multiple kernel extreme learning machine (MK-ELM) algorithm with grid search.

RESULTS

The proposed two-stage multi-view learning algorithm achieves superior performance for sleep staging. With a K-means clustering based dictionary, the mean classification accuracy, sensitivity and specificity are 81.10 ± 0.15%, 71.42 ± 0.66% and 94.57 ± 0.07%, respectively; while with the dictionary learned using the submodular optimization method, they are 80.29 ± 0.22%, 71.26 ± 0.78% and 94.38 ± 0.10%, respectively.

COMPARISON WITH EXISTING METHODS

The two-stage multi-view learning based sleep staging framework outperforms all other classification methods compared in this work, while JCR is superior to JSR.

CONCLUSIONS

The proposed multi-view learning framework has the potential for sleep staging based on multi-channel or multi-modality polysomnography signals.

Structured sparse priors for image classification

Model-based compressive sensing (CS) exploits the structure inherent in sparse signals for the design of better signal recovery algorithms. This information about structure is often captured in the form of a prior on the sparse coefficients, with the Laplacian being the most common such choice (leading to l1 -norm minimization). Recent work has exploited the discriminative capability of sparse representations for image classification by employing class-specific dictionaries in the CS framework. Our contribution is a logical extension of these ideas into structured sparsity for classification. We introduce the notion of discriminative class-specific priors in conjunction with class specific dictionaries, specifically the spike-and-slab prior widely applied in Bayesian sparse regression. Significantly, the proposed framework takes the burden off the demand for abundant training image samples necessary for the success of sparsity-based classification schemes. We demonstrate this practical benefit of our approach in important applications, such as face recognition and object categorization.

Scene text deblurring using text-specific multiscale dictionaries

Texts in natural scenes carry critical semantic clues for understanding images. When capturing natural scene images, especially by handheld cameras, a common artifact, i.e., blur, frequently happens. To improve the visual quality of such images, deblurring techniques are desired, which also play an important role in character recognition and image understanding. In this paper, we study the problem of recovering the clear scene text by exploiting the text field characteristics. A series of text-specific multiscale dictionaries (TMD) and a natural scene dictionary is learned for separately modeling the priors on the text and nontext fields. The TMD-based text field reconstruction helps to deal with the different scales of strings in a blurry image effectively. Furthermore, an adaptive version of nonuniform deblurring method is proposed to efficiently solve the real-world spatially varying problem. Dictionary learning allows more flexible modeling with respect to the text field property, and the combination with the nonuniform method is more appropriate in real situations where blur kernel sizes are depth dependent. Experimental results show that the proposed method achieves the deblurring results with better visual quality than the state-of-the-art methods.

Data uncertainty in face recognition

The image of a face varies with the illumination, pose, and facial expression, thus we say that a single face image is of high uncertainty for representing the face. In this sense, a face image is just an observation and it should not be considered as the absolutely accurate representation of the face. As more face images from the same person provide more observations of the face, more face images may be useful for reducing the uncertainty of the representation of the face and improving the accuracy of face recognition. However, in a real world face recognition system, a subject usually has only a limited number of available face images and thus there is high uncertainty. In this paper, we attempt to improve the face recognition accuracy by reducing the uncertainty. First, we reduce the uncertainty of the face representation by synthesizing the virtual training samples. Then, we select useful training samples that are similar to the test sample from the set of all the original and synthesized virtual training samples. Moreover, we state a theorem that determines the upper bound of the number of useful training samples. Finally, we devise a representation approach based on the selected useful training samples to perform face recognition. Experimental results on five widely used face databases demonstrate that our proposed approach can not only obtain a high face recognition accuracy, but also has a lower computational complexity than the other state-of-the-art approaches.

Resolution enhancement of lung 4D-CT via group-sparsity

PURPOSE

4D-CT typically delivers more accurate information about anatomical structures in the lung, over 3D-CT, due to its ability to capture visual information of the lung motion across different respiratory phases. This helps to better determine the dose during radiation therapy for lung cancer. However, a critical concern with 4D-CT that substantially compromises this advantage is the low superior-inferior resolution due to less number of acquired slices, in order to control the CT radiation dose. To address this limitation, the authors propose an approach to reconstruct missing intermediate slices, so as to improve the superior-inferior resolution.

METHODS

In this method the authors exploit the observation that sampling information across respiratory phases in 4D-CT can be complimentary due to lung motion. The authors' approach uses this locally complimentary information across phases in a patch-based sparse-representation framework. Moreover, unlike some recent approaches that treat local patches independently, the authors' approach employs the group-sparsity framework that imposes neighborhood and similarity constraints between patches. This helps in mitigating the trade-off between noise robustness and structure preservation, which is an important consideration in resolution enhancement. The authors discuss the regularizing ability of group-sparsity, which helps in reducing the effect of noise and enables better structural localization and enhancement.

RESULTS

The authors perform extensive experiments on the publicly available DIR-Lab Lung 4D-CT dataset [R. Castillo, E. Castillo, R. Guerra, V. Johnson, T. McPhail, A. Garg, and T. Guerrero, "A framework for evaluation of deformable image registration spatial accuracy using large landmark point sets," Phys. Med. Biol. 54, 1849-1870 (2009)]. First, the authors carry out empirical parametric analysis of some important parameters in their approach. The authors then demonstrate, qualitatively as well as quantitatively, the ability of their approach to achieve more accurate and better localized results over bicubic interpolation as well as a related state-of-the-art approach. The authors also show results on some datasets with tumor, to further emphasize the clinical importance of their method.

CONCLUSIONS

The authors have proposed to improve the superior-inferior resolution of 4D-CT by estimating intermediate slices. The authors' approach exploits neighboring constraints in the group-sparsity framework, toward the goal of achieving better localization and noise robustness. The authors' results are encouraging, and positively demonstrate the role of group-sparsity for 4D-CT resolution enhancement.

Joint sparse coding based spatial pyramid matching for classification of color medical image

Although color medical images are important in clinical practice, they are usually converted to grayscale for further processing in pattern recognition, resulting in loss of rich color information. The sparse coding based linear spatial pyramid matching (ScSPM) and its variants are popular for grayscale image classification, but cannot extract color information. In this paper, we propose a joint sparse coding based SPM (JScSPM) method for the classification of color medical images. A joint dictionary can represent both the color information in each color channel and the correlation between channels. Consequently, the joint sparse codes calculated from a joint dictionary can carry color information, and therefore this method can easily transform a feature descriptor originally designed for grayscale images to a color descriptor. A color hepatocellular carcinoma histological image dataset was used to evaluate the performance of the proposed JScSPM algorithm. Experimental results show that JScSPM provides significant improvements as compared with the majority voting based ScSPM and the original ScSPM for color medical image classification.

Simultaneous sparsity model for histopathological image representation and classification

The multi-channel nature of digital histopathological images presents an opportunity to exploit the correlated color channel information for better image modeling. Inspired by recent work in sparsity for single channel image classification, we propose a new simultaneous sparsity model for multi-channel histopathological image representation and classification (SHIRC). Essentially, we represent a histopathological image as a sparse linear combination of training examples under suitable channel-wise constraints. Classification is performed by solving a newly formulated simultaneous sparsity-based optimization problem. A practical challenge is the correspondence of image objects (cellular and nuclear structures) at different spatial locations in the image. We propose a robust locally adaptive variant of SHIRC (LA-SHIRC) to tackle this issue. Experiments on two challenging real-world image data sets: 1) mammalian tissue images acquired by pathologists of the animal diagnostics lab (ADL) at Pennsylvania State University, and 2) human intraductal breast lesions, reveal the merits of our proposal over state-of-the-art alternatives. Further, we demonstrate that LA-SHIRC exhibits a more graceful decay in classification accuracy against the number of training images which is highly desirable in practice where generous training per class is often not available.

Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization

This paper targets fine-grained image categorization by learning a category-specific dictionary for each category and a shared dictionary for all the categories. Such category-specific dictionaries encode subtle visual differences among different categories, while the shared dictionary encodes common visual patterns among all the categories. To this end, we impose incoherence constraints among the different dictionaries in the objective of feature coding. In addition, to make the learnt dictionary stable, we also impose the constraint that each dictionary should be self-incoherent. Our proposed dictionary learning formulation not only applies to fine-grained classification, but also improves conventional basic-level object categorization and other tasks such as event recognition. Experimental results on five data sets show that our method can outperform the state-of-the-art fine-grained image categorization frameworks as well as sparse coding based dictionary learning frameworks. All these results demonstrate the effectiveness of our method.