Iris recognition algorithm based on point covering of high-dimensional space and neural network

In this paper, we constructed a Iris recognition algorithm based on point covering of high-dimensional space and Multi-weighted neuron of point covering of high-dimensional space, and proposed a new method for iris recognition based on point covering theory of high-dimensional space. In this method, irises are trained as "cognition" one class by one class, and it doesn't influence the original recognition knowledge for samples of the new added class. The results of experiments show the rejection rate is 98.9%, the correct cognition rate and the error rate are 95.71% and 3.5% respectively. The experimental results demonstrate that the rejection rate of test samples excluded in the training samples class is very high. It proves the proposed method for iris recognition is effective.

A novel face recognition method based on hypersausage neural networks

In this paper, we firstly give the nature of 'hypersausages', study its structure and training of the network, then discuss the nature of it by way of experimenting with ORL face database, and finally, verify its unsurpassable advantages compared with other means.

Hypersausage neural networks and its application in face recognition

In this paper, we firstly give the nature of 'hypersausages', study its structure and training of the network, then discuss the nature of it by way of experimenting with ORL face database, and finally, verify its unsurpassable advantages compared with other means.

Molecular cloning and mRNA expression of peptidoglycan recognition protein (PGRP) gene in bay scallop (Argopecten irradians, Lamarck 1819)

Peptidoglycan recognition proteins (PGRPs) are a type of pattern recognition molecules (PRM) that recognize the unique cell wall component peptidoglycan (PGN) of bacteria and are involved in innate immunity. The first bivalve PGRP cDNA sequence was cloned from bay scallop Argopecten irradians by expressed sequence tag (EST) and PCR technique. The full-length cDNA of bay scallop PGRP (designated AiPGRP) gene contained 10 18 bp with a 615-bp open reading frame that encoded a polypeptide of 205 amino acids. The predicted amino acid sequence of AiPGRP shared high identity with PGRP in other organisms, such as PGRP precursor in Trichoplusia ni and PGRP SC2 in Drosophila melanogaster. A quantitative reverse transcriptase Real-Time PCR (qRT-PCR) assay was developed to assess the mRNA expression of AiPGRP in different tissues and the temporal expression of AiPGRP in the mixed primary cultured hemocytes challenged by microbial components lipopolyssacharide (LPS) from Escherichia coli and PGN from Micrococcus luteus. Higher-level mRNA expression of AiPGRP was detected in the tissues of hemocytes, gonad and kidney. The expression of AiPGRP in the mixed primary cultured hemocytes was up regulated after stimulated by PGN, while LPS from E. coli did not induce AiPGRP expression. The results indicated that AiPGRP was a constitutive and inducible expressed protein that was mainly induced by PGN and could be involved in scallop immune response against Gram-positive bacteria infection. (c) 2006 Elsevier Ltd. All rights reserved.

Molecular cloning and characterization of a short type peptidoglycan recognition protein (CfPGRP-S1) cDNA from Zhikong scallop Chlamys farreri

Peptidoglycan recognition protein (PGRP) specifically binds to peptidoglycan and plays a crucial role in the innate immune responses as a pattern recognition receptor (PRR). The cDNA of a short type PGRP was cloned from scallop Chlamys farreri (named CfPGRP-SI) by homology cloning with degenerate primers, and confirmed by virtual Northern blots. The full length of CfPGRP-SI cDNA was 1073 bp in length, including a 5 ' untranslated region (UTR) of 59 bp, a 3 ' UTR of 255 bp, and an open reading frame (ORF) of 759 bp encoding a polypeptide of 252 amino acids with an estimated molecular mass of 27.88 kDa and a predicted isoelectric point of 8.69. BLAST analysis revealed that CfPGRP-S1 shared high identities with other known PGRPs. A conserved PGRP domain and three zinc-binding sites were present at its C-terminus. The temporal expression of QPGRP-S1 gene in healthy, Vibrio anguillarum-challenged and Micrococcus lysodeikticus-challenged scallops was measured by RT-PCR analysis. The expression of CfPGRP-S1 was upregulated initially in the first 12 h or 24 h either by M. lysodeikticus or V. anguillarum challenge and reached the maximum level at 24 h or 36 h, then dropped progressively, and recovered to the original level as the stimulation decreased at 72 h. There was no significant difference between V. anguillarum and M. lysodeikticus challenge. The results indicated that the CfPGRP-S1 was a constitutive and inducible acute-phase protein which was involved in the immune response against bacterial infection. (c) 2007 Elsevier Ltd. All rights reserved.

An ancient C-type lectin in Chlamys farreri (CfLec-2) that mediate pathogen recognition and cellular adhesion

C-type lectins are a superfamily of Ca2+ dependent carbohydrate-recognition proteins which play significant diverse roles in nonself-recognition and clearance of invaders. In the present study, a C-type lectin (CfLec-2) from Zhikong scallop Chlamys farreri was selected to investigate its functions in innate immunity. The mRNA expression of CfLec-2 in hemocytes was significantly up-regulated (P < 0.01) after scallops were stimulated by LPS. PGN or beta-glucan, and reached the highest expression level at 12h post-stimulation, which was 72.5-, 23.6- or 43.8-fold compared with blank group, respectively. The recombinant Cflec-2 (designated as rCfLec-2) could bind LPS, PGN, mannan and zymosan in vitro, but it could not bind beta-glucan. Immunofluorescence assay with polyclonal antibody specific for Cflec-2 revealed that CfLec-2 was mainly located in the mantle, kidney and gonad. Furthermore, rCfLec-2 could bind to the surface of scallop hemocytes, and then initiated cellular adhesion and recruited hemocytes to enhance their encapsulation in vitro, and this process could be specifically blocked by anti-rCfLec-2 serum. These results collectively suggested that CfLec-2 from the primitive deuterostome C. farreri could perform two distinct immune functions, pathogen recognition and cellular adhesion synchronously, while these functions were performed by collectins and selectins in vertebrates, respectively. The synchronous functions of pathogen recognition and cellular adhesion performed by CfLec-2 tempted us to suspect that CfLec-2 was an ancient form of C-type lectin, and apparently the differentiation of these two functions mediated by C-type lectins occurred after mollusk in phylogeny. (C) 2010 Elsevier Ltd. All rights reserved.

Peptidoglycan recognition protein of Chlamys farreri (CfPGRP-S1) mediates immune defenses against bacterial infection

Peptidoglycan recognition protein (PGRP) is an essential molecule in innate immunity for both invertebrates and vertebrates, owing to its prominent ability in detecting and eliminating the invading bacteria. Several PGRPs have been identified from mollusk, but their functions and the underlined mechanism are still unclear. In the present study, the mRNA expression profiles, location, and possible functions of PGRP-S1 from Zhikong scallop Chlamys farreri (CfPG RP-St) were analyzed. The CfPGRP-S1 protein located in the mantle, gill, kidney and gonad of the scallops. Its mRNA expression in hemocytes was up-regulated extremely after PGN stimulation (P < 0.01), while moderately after the stimulations of LPS (P < 0.01) and beta-glucan (P < 0.05). The recombinant protein of CfPGRP-S1 (designated as rCfPGRP-S1) exhibited high affinity to PGN and moderate affinity to LPS, but it did not bind beta-glucan. Meanwhile, rCfPGRP-S1 also exhibited strong agglutination activity to Gram-positive bacteria Micrococcus luteus and Bacillus subtilis and weak activity to Gram-negative bacteria Escherichia coli. More importantly, rCfPGRP-S1 functioned as a bactericidal amidase to degrade PGN and strongly inhibit the growth of E. coli and Staphyloccocus aureus in the presence of Zn2+. These results indicated that CfPGRP-S1 could not only serve as a pattern recognition receptor recognizing bacterial PGN and LPS, but also function as a scavenger involved in eliminating response against the invaders. (C) 2010 Elsevier Ltd. All rights reserved.

Face Recognition Under Varying Pose

While researchers in computer vision and pattern recognition have worked on automatic techniques for recognizing faces for the last 20 years, most systems specialize on frontal views of the face. We present a face recognizer that works under varying pose, the difficult part of which is to handle face rotations in depth. Building on successful template-based systems, our basic approach is to represent faces with templates from multiple model views that cover different poses from the viewing sphere. Our system has achieved a recognition rate of 98% on a data base of 62 people containing 10 testing and 15 modelling views per person.

Learning Embeddings for Indexing, Retrieval, and Classification, with Applications to Object and Shape Recognition in Image Databases

Nearest neighbor retrieval is the task of identifying, given a database of objects and a query object, the objects in the database that are the most similar to the query. Retrieving nearest neighbors is a necessary component of many practical applications, in fields as diverse as computer vision, pattern recognition, multimedia databases, bioinformatics, and computer networks. At the same time, finding nearest neighbors accurately and efficiently can be challenging, especially when the database contains a large number of objects, and when the underlying distance measure is computationally expensive. This thesis proposes new methods for improving the efficiency and accuracy of nearest neighbor retrieval and classification in spaces with computationally expensive distance measures. The proposed methods are domain-independent, and can be applied in arbitrary spaces, including non-Euclidean and non-metric spaces. In this thesis particular emphasis is given to computer vision applications related to object and shape recognition, where expensive non-Euclidean distance measures are often needed to achieve high accuracy. The first contribution of this thesis is the BoostMap algorithm for embedding arbitrary spaces into a vector space with a computationally efficient distance measure. Using this approach, an approximate set of nearest neighbors can be retrieved efficiently - often orders of magnitude faster than retrieval using the exact distance measure in the original space. The BoostMap algorithm has two key distinguishing features with respect to existing embedding methods. First, embedding construction explicitly maximizes the amount of nearest neighbor information preserved by the embedding. Second, embedding construction is treated as a machine learning problem, in contrast to existing methods that are based on geometric considerations. The second contribution is a method for constructing query-sensitive distance measures for the purposes of nearest neighbor retrieval and classification. In high-dimensional spaces, query-sensitive distance measures allow for automatic selection of the dimensions that are the most informative for each specific query object. It is shown theoretically and experimentally that query-sensitivity increases the modeling power of embeddings, allowing embeddings to capture a larger amount of the nearest neighbor structure of the original space. The third contribution is a method for speeding up nearest neighbor classification by combining multiple embedding-based nearest neighbor classifiers in a cascade. In a cascade, computationally efficient classifiers are used to quickly classify easy cases, and classifiers that are more computationally expensive and also more accurate are only applied to objects that are harder to classify. An interesting property of the proposed cascade method is that, under certain conditions, classification time actually decreases as the size of the database increases, a behavior that is in stark contrast to the behavior of typical nearest neighbor classification systems. The proposed methods are evaluated experimentally in several different applications: hand shape recognition, off-line character recognition, online character recognition, and efficient retrieval of time series. In all datasets, the proposed methods lead to significant improvements in accuracy and efficiency compared to existing state-of-the-art methods. In some datasets, the general-purpose methods introduced in this thesis even outperform domain-specific methods that have been custom-designed for such datasets.

Self-Organizing Information Fusion and Hierarchical Knowledge Discovery: A New Framework Using Artmap Neural Networks

Classifying novel terrain or objects from sparse, complex data may require the resolution of conflicting information from sensors woring at different times, locations, and scales, and from sources with different goals and situations. Information fusion methods can help resolve inconsistencies, as when eveidence variously suggests that and object's class is car, truck, or airplane. The methods described her address a complementary problem, supposing that information from sensors and experts is reliable though inconsistent, as when evidence suggests that an object's class is car, vehicle, and man-made. Underlying relationships among classes are assumed to be unknown to the autonomated system or the human user. The ARTMAP information fusion system uses distributed code representations that exploit the neural network's capacity for one-to-many learning in order to produce self-organizing expert systems that discover hierachical knowlege structures. The fusion system infers multi-level relationships among groups of output classes, without any supervised labeling of these relationships. The procedure is illustrated with two image examples, but is not limited to image domain.

Large-Scale Neural Systems for Vision and Cognition

— Consideration of how people respond to the question What is this? has suggested new problem frontiers for pattern recognition and information fusion, as well as neural systems that embody the cognitive transformation of declarative information into relational knowledge. In contrast to traditional classification methods, which aim to find the single correct label for each exemplar (This is a car), the new approach discovers rules that embody coherent relationships among labels which would otherwise appear contradictory to a learning system (This is a car, that is a vehicle, over there is a sedan). This talk will describe how an individual who experiences exemplars in real time, with each exemplar trained on at most one category label, can autonomously discover a hierarchy of cognitive rules, thereby converting local information into global knowledge. Computational examples are based on the observation that sensors working at different times, locations, and spatial scales, and experts with different goals, languages, and situations, may produce apparently inconsistent image labels, which are reconciled by implicit underlying relationships that the network’s learning process discovers. The ARTMAP information fusion system can, moreover, integrate multiple separate knowledge hierarchies, by fusing independent domains into a unified structure. In the process, the system discovers cross-domain rules, inferring multilevel relationships among groups of output classes, without any supervised labeling of these relationships. In order to self-organize its expert system, the ARTMAP information fusion network features distributed code representations which exploit the model’s intrinsic capacity for one-to-many learning (This is a car and a vehicle and a sedan) as well as many-to-one learning (Each of those vehicles is a car). Fusion system software, testbed datasets, and articles are available from http://cns.bu.edu/techlab.

Fast Learning VIEWNET Architectures for Recognizing 3-D Objects from Multiple 2-D Views

The recognition of 3-D objects from sequences of their 2-D views is modeled by a family of self-organizing neural architectures, called VIEWNET, that use View Information Encoded With NETworks. VIEWNET incorporates a preprocessor that generates a compressed but 2-D invariant representation of an image, a supervised incremental learning system that classifies the preprocessed representations into 2-D view categories whose outputs arc combined into 3-D invariant object categories, and a working memory that makes a 3-D object prediction by accumulating evidence from 3-D object category nodes as multiple 2-D views are experienced. The simplest VIEWNET achieves high recognition scores without the need to explicitly code the temporal order of 2-D views in working memory. Working memories are also discussed that save memory resources by implicitly coding temporal order in terms of the relative activity of 2-D view category nodes, rather than as explicit 2-D view transitions. Variants of the VIEWNET architecture may also be used for scene understanding by using a preprocessor and classifier that can determine both What objects are in a scene and Where they are located. The present VIEWNET preprocessor includes the CORT-X 2 filter, which discounts the illuminant, regularizes and completes figural boundaries, and suppresses image noise. This boundary segmentation is rendered invariant under 2-D translation, rotation, and dilation by use of a log-polar transform. The invariant spectra undergo Gaussian coarse coding to further reduce noise and 3-D foreshortening effects, and to increase generalization. These compressed codes are input into the classifier, a supervised learning system based on the fuzzy ARTMAP algorithm. Fuzzy ARTMAP learns 2-D view categories that are invariant under 2-D image translation, rotation, and dilation as well as 3-D image transformations that do not cause a predictive error. Evidence from sequence of 2-D view categories converges at 3-D object nodes that generate a response invariant under changes of 2-D view. These 3-D object nodes input to a working memory that accumulates evidence over time to improve object recognition. ln the simplest working memory, each occurrence (nonoccurrence) of a 2-D view category increases (decreases) the corresponding node's activity in working memory. The maximally active node is used to predict the 3-D object. Recognition is studied with noisy and clean image using slow and fast learning. Slow learning at the fuzzy ARTMAP map field is adapted to learn the conditional probability of the 3-D object given the selected 2-D view category. VIEWNET is demonstrated on an MIT Lincoln Laboratory database of l28x128 2-D views of aircraft with and without additive noise. A recognition rate of up to 90% is achieved with one 2-D view and of up to 98.5% correct with three 2-D views. The properties of 2-D view and 3-D object category nodes are compared with those of cells in monkey inferotemporal cortex.

Fuzzy ART

Adaptive Resonance Theory (ART) models are real-time neural networks for category learning, pattern recognition, and prediction. Unsupervised fuzzy ART and supervised fuzzy ARTMAP synthesize fuzzy logic and ART networks by exploiting the formal similarity between the computations of fuzzy subsethood and the dynamics of ART category choice, search, and learning. Fuzzy ART self-organizes stable recognition categories in response to arbitrary sequences of analog or binary input patterns. It generalizes the binary ART 1 model, replacing the set-theoretic: intersection (∩) with the fuzzy intersection (∧), or component-wise minimum. A normalization procedure called complement coding leads to a symmetric: theory in which the fuzzy inter:>ec:tion and the fuzzy union (∨), or component-wise maximum, play complementary roles. Complement coding preserves individual feature amplitudes while normalizing the input vector, and prevents a potential category proliferation problem. Adaptive weights :otart equal to one and can only decrease in time. A geometric interpretation of fuzzy AHT represents each category as a box that increases in size as weights decrease. A matching criterion controls search, determining how close an input and a learned representation must be for a category to accept the input as a new exemplar. A vigilance parameter (p) sets the matching criterion and determines how finely or coarsely an ART system will partition inputs. High vigilance creates fine categories, represented by small boxes. Learning stops when boxes cover the input space. With fast learning, fixed vigilance, and an arbitrary input set, learning stabilizes after just one presentation of each input. A fast-commit slow-recode option allows rapid learning of rare events yet buffers memories against recoding by noisy inputs. Fuzzy ARTMAP unites two fuzzy ART networks to solve supervised learning and prediction problems. A Minimax Learning Rule controls ARTMAP category structure, conjointly minimizing predictive error and maximizing code compression. Low vigilance maximizes compression but may therefore cause very different inputs to make the same prediction. When this coarse grouping strategy causes a predictive error, an internal match tracking control process increases vigilance just enough to correct the error. ARTMAP automatically constructs a minimal number of recognition categories, or "hidden units," to meet accuracy criteria. An ARTMAP voting strategy improves prediction by training the system several times using different orderings of the input set. Voting assigns confidence estimates to competing predictions given small, noisy, or incomplete training sets. ARPA benchmark simulations illustrate fuzzy ARTMAP dynamics. The chapter also compares fuzzy ARTMAP to Salzberg's Nested Generalized Exemplar (NGE) and to Simpson's Fuzzy Min-Max Classifier (FMMC); and concludes with a summary of ART and ARTMAP applications.