A semantic RBM-based model for image set classification

Discrete aggregation hashing for image set classification

Image set–based classification has attracted substantial research interest because of its broad applications. Recently, lots of methods based on feature learning or dictionary learning have been developed to solve this problem, and some of them have made gratifying achievements. However, most of them transform the image set into a 2D matrix or use 2D convolutional neural networks (CNNs) for feature learning, so the spatial and temporal information is missing. At the same time, these methods extract features from original images in which there may exist huge intra-class diversity. To explore a possible solution to these issues, we propose a simultaneous image reconstruction with deep learning and feature learning with 3D-CNNs (SIRFL) for image set classification. The proposed SIRFL approach consists of a deep image reconstruction network and a 3D-CNN-based feature learning network. The deep image reconstruction network is used to reduce the diversity of images from the same set, and the feature learning network can effectively retain spatial and temporal information by using 3D-CNNs. Extensive experimental results on five widely used datasets show that our SIRFL approach is a strong competitor for the state-of-the-art image set classification methods.

In this paper, we propose a novel image set representation and classification method by maximizing the margin of image sets. The margin of an image set is defined as the difference of the distance to its nearest image set from different classes and the distance to its nearest image set of the same class. By modeling the image sets by using both their image samples and their affine hull models, and maximizing the margins of the images sets, the image set representation parameter learning problem is formulated as an minimization problem, which is further optimized by an expectation -maximization (EM) strategy with accelerated proximal gradient (APG) optimization in an iterative algorithm. To classify a given test image set, we assign it to the class which could provide the largest margin. Experiments on two applications of video-sequence-based face recognition demonstrate that the proposed method significantly outperforms state-of-the-art image set classification methods in terms of both effectiveness and efficiency.

Joint dimensionality reduction and metric learning for image set classification

Sparse and collaborative representation based kernel pairwise linear regression for image set classification

Cooperative linear regression model for image set classification

We propose a black-box optimization method to generate functional test patterns for AI inferencing accelerators. Functional testing is faster than structural testing as scan chains are not used for shifting in patterns and shifting out test responses. Moreover, functional testing reduces "over-testing" by targeting the detection of functionally critical faults for a given application workload. We use Bayesian Optimization for targeted test-image generation for stuck-at faults in a systolic array-based accelerator. Our framework supports test-pattern compaction and leverages various types of error regularization for enforcing functional-likeness of the generated test images. We achieve high fault coverage using a small set of test images for pin-level faults in 16-bit and 32-bit floating-point processing elements of the systolic array achieves high fault coverage with a small set of test images.

We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object's appearance due to changing camera pose and lighting conditions. Canonical Correlations (also known as principal or canonical angles), which can be thought of as the angles between two d-dimensional subspaces, have recently attracted attention for image set matching. Canonical correlations offer many benefits in accuracy, efficiency, and robustness compared to the two main classical methods: parametric distribution-based and nonparametric sample-based matching of sets. Here, this is first demonstrated experimentally for reasonably sized data sets using existing methods exploiting canonical correlations. Motivated by their proven effectiveness, a novel discriminative learning method over sets is proposed for set classification. Specifically, inspired by classical Linear Discriminant Analysis (LDA), we develop a linear discriminant function that maximizes the canonical correlations of within-class sets and minimizes the canonical correlations of between-class sets. Image sets transformed by the discriminant function are then compared by the canonical correlations. Classical orthogonal subspace method (OSM) is also investigated for the similar purpose and compared with the proposed method. The proposed method is evaluated on various object recognition problems using face image sets with arbitrary motion captured under different illuminations and image sets of 500 general objects taken at different views. The method is also applied to object category recognition using ETH-80 database. The proposed method is shown to outperform the state-of-the-art methods in terms of accuracy and efficiency.

We present an image set classification algorithm based on unsupervised clustering of labeled training and unlabeled test data where labels are only used in the stopping criterion. The probability distribution of each class over the set of clusters is used to define a true set based similarity measure. To this end, we propose an iterative sparse spectral clustering algorithm. In each iteration, a proximity matrix is efficiently recomputed to better represent the local subspace structure. Initial clusters capture the global data structure and finer clusters at the later stages capture the subtle class differences not visible at the global scale. Image sets are compactly represented with multiple Grassmannian manifolds which are subsequently embedded in Euclidean space with the proposed spectral clustering algorithm. We also propose an efficient eigenvector solver which not only reduces the computational cost of spectral clustering by many folds but also improves the clustering quality and final classification results. Experiments on five standard datasets and comparison with seven existing techniques show the efficacy of our algorithm.

Neighborhood preserving embedding on Grassmann manifold for image-set analysis

As the development of human genomic project, the life science research has entered the post-genome era. The study of the function of the encoded proteins is one of the hotspots in life-science research and protein subcellular localization is an important basis for functional study of the protein. The most common method used for determining subcellular localization of protein in cell is fluorescence microscopy. Image feature calculation has proven invaluable in the automated cell phenotype image classification. This article proposes a novel method for cell phenotype image classification which is to count the local difference features of the fluorescence images. The novel method is tested on two image sets called LOCATE Endogenous and LOCATE Transfected. A support vector machine was trained and tested for each image set and better classification accuracies were obtained on the two image sets.

Directed forgetting paradigms assess cognitive control by determining whether memory accuracy is superior in trials on which subjects were instructed to remember compared with accuracy in trials on which they were instructed to forget. We used a directed forgetting paradigm to compare the extent to which working memory and familiarity are subject to rehearsal-like cognitive control in rhesus monkeys. Monkeys studied a sample image, then saw one of two distinctive cues during a retention interval. The remember cue typically predicted a four-choice match to sample test, for which memory of the sample was critical. The forget cue typically predicted one of five perceptual discrimination tests, matched for accuracy to the memory tests, for which memory of the sample was irrelevant. On rare probe trials, the test type other than the type typically predicted by the cue was presented. When cognitive control of memory was possible, accuracy should have been higher on memory tests following the remember cue than on those following the forget cue. We found that accuracy was higher following the remember cue under conditions that favored working memory (small image set) but was not higher under conditions that favored matching on the basis of relative familiarity (large image set). Working memory, but not familiarity, is subject to cognitive control in rhesus monkeys.

This paper presents a graphical model for de-formable face matching and landmark localization under an unknown non-rigid warp. The proposed model learns and combines statistics of both appearance and shape variations of facial images (learnt purely from a set of frontal training images) in a complex objective function in an unsupervised manner. Local and global shape variations are included in the objective function as binary and higher order clique potentials. The proposed approach exploits the sparseness of facial features to reduce the complexity of inference over the probabilistic model. Besides presenting a method for face feature localization, the paper proposes a framework for incorporation of statistical shape priors as higher order cliques into MRFs. The problem of optimizing the objective function is performed using the dual decomposition approach in which the higher order subproblems based on point distribution models are formulated as instances of convex quadratic programs. The evaluation of the approach for feature localization is performed both on the frontal and rotated images of the XM2VTS dataset images as well as images collected from Google. The method shows high robustness to partial occlusion, pose changes etc. The method is then applied as an initialization step for a more costly matching method and is shown to be instrumental in improving performance and reducing runtime.

With the emergent of biometric technology, people are no longer afraid to keep their important things in the safe box or room or even facility. This is because; human beings have unique features that distinguish them with other people. The scheme is based on an information theory approach that decomposes face images into a small set of characteristic feature images called ‘Eigenfaces’, which are actually the principal components of the initial training set of face images. In this report, thorough explanation on design process of face recognition on bags locking mechanism will be elucidated. The results and analysis of the proposed design prototype also presented and explained. The platform for executing the algorithm is on the Raspberry Pi. There are two artificial intelligent techniques applied to manipulate and processing data which is fuzzy logic and neural networks. Both systems are interdependent with each other, so that it can calculate and analyse data precisely. The receive image from the camera is analysed through the Eigenfaces algorithm. The algorithm is using Principal Component Analysis (PCA) method which comprise of artificial neural network paradigm and also statistical paradigm.

The binding problem.