Vector Quantization Artificial Neural Network Research Articles

The Kingdom of Saudi Arabia Vehicle License Plate Recognition using Learning Vector Quantization Artificial Neural Network

In the today scenario technological intelligence is a higher demand after commodity even in traffic-based systems. These intelligent systems do not only help in traffic monitoring but also in commuter safety, law enforcement and commercial applications. The proposed Saudi Arabia Vehicle License plate recognition system splits into three major parts, firstly extraction of a license plate region secondly segmentation of the plate characters and lastly recognition of each character. This act is quite challenging due to the multiformity of plate formats and the nonuniform outdoor illumination conditions during image collection. In this paper recognition of the license plates is achieved by the implementation of the Learning Vector Quantization artificial neural network. Their results are based upon their completeness in the Saudi Arabia Vehicle License plate character recognition and theirs have obtained encouraging results from proposed technique.

Machine fusion to enhance the topology preservation of vector quantization artificial neural networks

Artificial neural networks techniques have been successfully applied in vector quantization (VQ) encoding. The objective of VQ is to statistically preserve the topological relationships existing in a data set and to project the data to a lattice of lower dimensions, for visualization, compression, storage, or transmission purposes. However, one of the major drawbacks in the application of artificial neural networks is the difficulty to properly specify the structure of the lattice that best preserves the topology of the data. To overcome this problem, in this paper we introduce merging algorithms for machine-fusion, boosting-fusion-based and hybrid-fusion ensembles of SOM, NG and GSOM networks. In these ensembles not the output signals of the base learners are combined, but their architectures are properly merged. We empirically show the quality and robustness of the topological representation of our proposed algorithm using both synthetic and real benchmarks datasets.

A digital image analysis and neural network based system for identification of third-stage parasitic strongyle larvae from domestic animals

A competitive learning vector quantization artificial neural network (ANN) was trained to identify third-stage parasitic strongyle larvae from domestic animals on the basis of quantitative data obtained from processed digital images of larvae. For this reason, various quantitative features obtained from processed digital images of larvae were tested as to whether they are variant or invariant to the shape taken by the motile larvae during image recording. A total of 255 images of 57 individual larvae in various shapes belonging to five genera were recorded. Following image processing, 16 features were measured, of which seven were selected as invariant to larva shape. By trial and error, two of those features, ‘area’ and ‘perimeter’, along with the quantitative features used in conventional identification, ‘overall body length’, ‘width’ and ‘extension of sheath’ (tip of larva to tip of sheath), were used as an effective training data set for the ANN. This ANN coupled with an image analysis facility and a knowledge relational database became the basis for developing a computer-based larva identification system whose overall identification performance was 91.9%. The advantages of this system are its speed and objectivity. The objectivity of the system is based on the fact that it is not subject to inter- and intra-observer variability arising from the user’s profile of competency in interpreting subjective and non-quantifiable descriptions. The limitations of the system are that it cannot handle raw images but only data extracted from images, its performance depends on the reliability of the input vectors used as training data for the ANN, and its use is restricted only to well-equipped laboratories due to its requirement for expensive instrumentation.

Evaluation of artificial neural networks for fungal identification, employing morphometric data from spores of Pestalotiopsis species

The relative abilities of the multilayer perceptron, radial basis function, asymmetric radial basis function and learning vector quantization artificial neural networks (ANNs) and two non-neural methods to identify fungal spores were compared. ANNs were trained on morphometric data from spores of Pestalotiopsis spp. and a few species in the related Truncatella and Monochaetia. The optimized neural and statistical classifiers had similar identification success on an unseen data set – between 76-0 and 78-8% of a 16-species group and between 63-0 and 67-7% of a 19-species group. The relative merits of each classifier are discussed, as is the potential of ANNs in mycology.