ABSTRACT
Image set matching (ISM) has attracted increasing attention in the field of computer vision and pattern recognition. Some studies attempt to model query and gallery sets under a joint or collaborative representation framework, achieving impressive performance. However, existing models consider only the competition and collaboration among gallery sets, neglecting the inter-instance relationships within the query set which are also regarded as one important clue for ISM. In this paper, inter-instance relationships within the query set are explored for robust image set matching. Specifically, we propose to represent the query set instances jointly via a combined dictionary learned from the gallery sets. To explore the commonality and variations within the query set simultaneously to benefit the matching, both low rank and class-level sparsity constraints are imposed on the representation coefficients. Then, to deal with nonlinear data in real scenarios, the'kernelized version is also proposed. Moreover, to tackle the gross corruptions mixed in the query set, the proposed model is extended for robust ISM. The optimization problems are solved efficiently by employing singular value thresholding and block soft thresholding operators in an alternating direction manner. Experiments on five public datasets demonstrate the effectiveness of the proposed method, comparing favorably with state-of-the-art methods.
ABSTRACT
BACKGROUND: Massively parallel genetic sequencing allows rapid testing of known intellectual disability (ID) genes. However, the discovery of novel syndromic ID genes requires molecular confirmation in at least a second or a cluster of individuals with an overlapping phenotype or similar facial gestalt. Using computer face-matching technology we report an automated approach to matching the faces of non-identical individuals with the same genetic syndrome within a database of 3681 images [1600 images of one of 10 genetic syndrome subgroups together with 2081 control images]. Using the leave-one-out method, two research questions were specified: 1) Using two-dimensional (2D) photographs of individuals with one of 10 genetic syndromes within a database of images, did the technology correctly identify more than expected by chance: i) a top match? ii) at least one match within the top five matches? or iii) at least one in the top 10 with an individual from the same syndrome subgroup? 2) Was there concordance between correct technology-based matches and whether two out of three clinical geneticists would have considered the diagnosis based on the image alone? RESULTS: The computer face-matching technology correctly identifies a top match, at least one correct match in the top five and at least one in the top 10 more than expected by chance (P < 0.00001). There was low agreement between the technology and clinicians, with higher accuracy of the technology when results were discordant (P < 0.01) for all syndromes except Kabuki syndrome. CONCLUSIONS: Although the accuracy of the computer face-matching technology was tested on images of individuals with known syndromic forms of intellectual disability, the results of this pilot study illustrate the potential utility of face-matching technology within deep phenotyping platforms to facilitate the interpretation of DNA sequencing data for individuals who remain undiagnosed despite testing the known developmental disorder genes.
Subject(s)
Congenital Abnormalities , Face/abnormalities , Facies , Image Processing, Computer-Assisted/methods , Intellectual Disability , Adult , Algorithms , Child , Congenital Abnormalities/classification , Congenital Abnormalities/diagnosis , Congenital Abnormalities/genetics , Congenital Abnormalities/pathology , Databases, Factual , Female , Humans , Intellectual Disability/classification , Intellectual Disability/diagnosis , Intellectual Disability/genetics , Intellectual Disability/pathology , Male , Photography , SyndromeABSTRACT
The antinuclear antibody (ANA) test via indirect immunofluorescence applied on Human Epithelial type 2 (HEp-2) cells is a pathology test commonly used to identify connective tissue diseases (CTDs). Despite its effectiveness, the test is still considered labor intensive and time consuming. Applying image-based computer aided diagnosis (CAD) systems is one of the possible ways to address these issues. Ideally, a CAD system should be able to classify ANA HEp-2 images taken by a camera fitted to a fluorescence microscope. Unfortunately, most prior works have primarily focused on the HEp-2 cell image classification problem which is one of the early essential steps in the system pipeline. In this work we directly tackle the specimen image classification problem. We aim to develop a system that can be easily scaled and has competitive accuracy. ANA HEp-2 images or ANA images are generally comprised of a number of cells. Patterns exhibiting in the cells are then used to make inference on the ANA image pattern. To that end, we adapted a popular approach for general image classification problems, namely a bag of visual words approach. Each specimen is considered as a visual document containing visual vocabularies represented by its cells. A specimen image is then represented by a histogram of visual vocabulary occurrences. We name this approach as the Bag of Cells approach. We studied the performance of the proposed approach on a set of images taken from 262 ANA positive patient sera. The results show the proposed approach has competitive performance compared to the recent state-of-the-art approaches. Our proposal can also be expanded to other tests involving examining patterns of human cells to make inferences.
Subject(s)
Antibodies, Antinuclear/immunology , Cell Nucleus/immunology , Connective Tissue Diseases/diagnosis , Image Processing, Computer-Assisted/methods , Microscopy, Fluorescence/methods , Cell Cycle , Cell Line , Computational Biology/methods , Epithelial Cells/immunology , Fluorescent Antibody Technique, Indirect/methods , HumansABSTRACT
Microbial bioelectrochemical systems (BESs) use microorganisms as catalysts for electrode reactions. They have emerging applications in bioenergy, bioproduction, and bioremediation. BESs can be scaled up as a linked series of units or cells; however, this may lead to so-called cell reversal. Here, we demonstrate a cell balance system (CBS) that controls individual BES cells connected electrically in series by dynamically adapting the applied potential in the kilohertz frequency range relative to the performance of the bioanode. The CBS maintains the cell voltage of individual BES cells at or below a maximum set point by bypassing a portion of applied current with a high-frequency metal oxide semiconductor field-effect transistor switch control system. We demonstrate (i) multiple serially connected BES cells started simultaneously and rapidly from a single power source, as the CBS imparts no current limitation, (ii) continuous, stable, and independent performance of each stacked BES cell, and (iii) stable BES cell and stack performance under excessive applied currents. This control system has applications for not only serially stacked BESs in scaled-up stacks but also rapidly starting individual- and/or lab-scale BESs.
Subject(s)
Biotechnology , Electrochemical Techniques/instrumentation , Electrodes , Bioelectric Energy SourcesABSTRACT
Utilizing multiple descriptions/views of an object is often useful in image clustering tasks. Despite many works that have been proposed to effectively cluster multi-view data, there are still unaddressed problems such as the errors introduced by the traditional spectral-based clustering methods due to the two disjoint stages: 1) eigendecomposition and 2) the discretization of new representations. In this paper, we propose a unified clustering framework which jointly learns the two stages together as well as utilizing multiple descriptions of the data. More specifically, two learning methods from this framework are proposed: 1) through a graph construction from different views and 2) through combining multiple graphs. Furthermore, benefiting from the separability and local graph preserving properties of the proposed methods, a novel unsupervised automatic attribute discovery method is proposed. We validate the efficacy of our methods on five data sets, showing that the proposed joint learning clustering methods outperform the recent state-of-the-art methods. We also show that it is possible to derive a novel method to address the unsupervised automatic attribute discovery tasks.
ABSTRACT
OBJECTIVE: This paper presents benchmarking results of human epithelial type 2 (HEp-2) interphase cell image classification methods on a very large dataset. The indirect immunofluorescence method applied on HEp-2 cells has been the gold standard to identify connective tissue diseases such as systemic lupus erythematosus and Sjögren's syndrome. However, the method suffers from numerous issues such as being subjective, time consuming and labor intensive. This has been the main motivation for the development of various computer-aided diagnosis systems whose main task is to automatically classify a given cell image into one of the predefined classes. METHODS AND MATERIAL: The benchmarking was performed in the form of an international competition held in conjunction with the International Conference of Image Processing in 2013: fourteen teams, composed of practitioners and researchers in this area, took part in the initiative. The system developed by each team was trained and tested on a very large HEp-2 cell dataset comprising over 68,000 images of HEp-2 cell. The dataset contains cells with six different staining patterns and two levels of fluorescence intensity. For each method we provide a brief description highlighting the design choices and an in-depth analysis on the benchmarking results. RESULTS: The staining pattern recognition accuracy attained by the methods varies between 47.91% and slightly above 83.65%. However, the difference between the top performing method and the seventh ranked method is only 5%. In the paper, we also study the performance achieved by fusing the best methods, finding that a recognition rate of 85.60% is reached when the top seven methods are employed. CONCLUSIONS: We found that highest performance is obtained when using a strong classifier (typically a kernelised support vector machine) in conjunction with features extracted from local statistics. Furthermore, the misclassification profiles of the different methods highlight that some staining patterns are intrinsically more difficult to recognize. We also noted that performance is strongly affected by the fluorescence intensity level. Thus, low accuracy is to be expected when analyzing low contrasted images.
Subject(s)
Connective Tissue Diseases/diagnosis , Diagnosis, Computer-Assisted/methods , Epithelial Cells/classification , Image Processing, Computer-Assisted/methods , Pattern Recognition, Automated/methods , Support Vector Machine , Algorithms , Fluorescent Antibody Technique, Indirect , Humans , Interphase , Sensitivity and SpecificityABSTRACT
Low-dimensional representations are key to the success of many video classification algorithms. However, the commonly-used dimensionality reduction techniques fail to account for the fact that only part of the signal is shared across all the videos in one class. As a consequence, the resulting representations contain instance-specific information, which introduces noise in the classification process. In this paper, we introduce non-linear stationary subspace analysis: a method that overcomes this issue by explicitly separating the stationary parts of the video signal (i.e., the parts shared across all videos in one class), from its non-stationary parts (i.e., the parts specific to individual videos). Our method also encourages the new representation to be discriminative, thus accounting for the underlying classification problem. We demonstrate the effectiveness of our approach on dynamic texture recognition, scene classification and action recognition.