Network For Image Recognition Research Articles

Application of Artificial Neural Networks in Image Recognition

This paper presents aaplication of two-layer Kohonen networ for the grouping of machine elements to automatically recognition by the robots. This technology is very important for robotic assembly process of a large group of different parts.

Text Matching as Image Recognition

Matching two texts is a fundamental problem in many natural language processing tasks. An effective way is to extract meaningful matching patterns from words, phrases, and sentences to produce the matching score. Inspired by the success of convolutional neural network in image recognition, where neurons can capture many complicated patterns based on the extracted elementary visual patterns such as oriented edges and corners, we propose to model text matching as the problem of image recognition. Firstly, a matching matrix whose entries represent the similarities between words is constructed and viewed as an image. Then a convolutional neural network is utilized to capture rich matching patterns in a layer-by-layer way. We show that by resembling the compositional hierarchies of patterns in image recognition, our model can successfully identify salient signals such as n-gram and n-term matchings. Experimental results demonstrate its superiority against the baselines.

A novel biologically inspired ELM-based network for image recognition

In this paper, a novel biologically inspired network for image recognition has been introduced. The Hierarchical model and X (HMAX) model and the extreme learning machine (ELM) are combined, to construct a five-layer feed-forward network: S1–C1–S2–C2–H. The previous four layers, originating from HMAX, provide robust feature representation of specific object, and the feature classification stage in the H layer is implemented with ELM. The HMAX model simulates the hierarchical processing mechanism in primate visual cortex, to calculate complex features representation. As a biological learning algorithm for generalized SLFNs, ELM learns much faster with good generalization performance, and performs well in classification applications. Four groups of experiments are performed on three datasets, and the results are compared with state-of-the-art techniques. Experimental results show that our proposed network has good performance with fast learning speed.

A novel algorithm of extended neural networks for image recognition

As a class of important classifiers, feedforward neural networks (FNNs) have been used considerably in the study of pattern recognition. Since the inputs to FNNs are usually vectors, and many data are usually presented in the form of matrices, the matrices have to be decomposed into vectors before FNNs are employed. A drawback to this approach is that important information regarding correlations of elements within the original matrices are lost. Unlike traditional vector input based FNNs, a new algorithm of extended FNN with matrix inputs, called two-dimensional back-propagation (2D-BP), is proposed in this paper to classify matrix data directly, which utilizes the technique of incremental gradient descent to fully train the extended FNNs. These kinds of FNNs help to maintain the matrix structure of the 2D input features, which helps with image recognition. Promising experimental results of handwritten digits and face-image classification are provided to demonstrate the effectiveness of the proposed method.

Algorithm of study neural network for image recognition

Algorithm of study neural network for image recognition

Evolutionary structure optimization of hierarchical neural network for image recognition

AbstractThe purpose of this paper is to optimize the structure of hierarchical neural networks. In this paper, structure optimization is used to represent a neural network by the minimum number of nodes and connections, and is performed by eliminating unnecessary connections from a trained neural network by means of a genetic algorithm. We focus on a neural network specialized for image recognition problems. The flow of the proposed method is as follows. First, the Walsh–Hadamard transform is applied to images for feature extraction. Second, the neural network is trained with the extracted features based on a back‐propagation algorithm. After neural network training, unnecessary connections are eliminated from the trained neural network by means of a genetic algorithm. Finally, the neural network is retrained to recover from the degradation caused by connection elimination. In order to validate the usefulness of the proposed method, face recognition and texture classification examples are used. The experimental results indicate that a compact neural network was generated, maintaining the generalization performance by the proposed method. © 2012 Wiley Periodicals, Inc. Electron Comm Jpn, 95(3): 28–36, 2012; Published online in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/ecj.10384

A method of organization of a parallel-hierarchical network for image recognition

An explicit formula of a multivariate B-spline, some useful investigations in the field of linear transformations of independent exponentially distributed random variables, representation of theirs density functions with the help of multivariate exponential spline functions, and their usage are considered. The consideration is illustrated by an appropriate example.

A new optimization algorithm based on the principle of evolution

A new genetic algorithm is proposed for the optimization problem of real-valued variable functions. A new robust and adaptive fitness scaling is presented by introducing the median of the population in exponential transformation. For float-point represented chromosomes, crossover and mutation operators are given. Convergence of the algorithm is proved. The performance is tested by two generally used functions. Hybrid algorithm which takes the BP algorithm as a mutation operator is used to train a neural network for image recognition. Experimental results show that the proposed algorithm is an efficient global optimization algorithm.

Basic Concepts of Artificial Neural Networks (ANN) Modeling in the Application to Pharmaceutical Development

ABSTRACTArtificial neural networks (ANN) methodology is a new modeling method that has not been broadly applied to pharmaceutical sciences up to now. The aim of this paper is to give a detailed description of the associating networks as well as a description of less well-known networks (i.e., feature-extracting and nonadaptive networks) and their scope of application in pharmaceutical sciences. The descriptions include the historical origin and the basic concepts behind the computing. ANN are based on the attempt to model the neural networks of the brain. Learning algorithms for associating ANN use mathematical procedures usually derived from the gradient descent method whereas feature-extracting ANN map multidimensional input data sets onto two-dimensional spaces. Nonadaptive ANN map data sets and are able to reconstruct their patterns when presented with corrupted or noisy samples. Associating networks can typically be applied in the pharmaceutical field as an alternative to traditional response surface methodology, feature-extracting networks as alternative to principal component analysis, and nonadaptive networks for image recognition. Based on these abilities, the potential application fields of the ANN methodology in the pharmaceutical sciences is broad, ranging from clinical pharmacy through biopharmacy, drug and dosage form design, to interpretation of analytical data. The few applications presented in the pharmaceutical technology area seem promising and should be investigated in more detail.

Constraint satisfaction neural networks for image recognition

Constraint satisfaction neural networks (CSNNs) are proposed for image recognition which is the process to identify objects of interest in an image. The image recognition problem is formulated as a constraint satisfaction problem (CSP). The regions resulting from a signal-based image segmentation algorithm can be considered as objects and their entities as labels in the CSP. The proposed neural network is multi-layered and the function of each layer is to identify one physical entity (label) from the input regions (objects). Through cascading these layers, each label can be assigned to the corresponding region(s). Attention is focused on recognizing X-ray CT (computed tomography) images of human heads (e.g. anatomic structure in a medical image). The proposed CSNN is capable of identifying the components of a brain in a preliminarily segmented image. The major components in a human head include bone, ventricle and gyrus. Therefore, three layers are needed for this task. Each layer is constructed based on the principles proposed in Kohonen's self-organizing feature maps and the optimal linear associative memories and their weights are trained by the features of each entity in the prestored model. The experimental results show that the proposed approach is very promising.