<abstract xmlns="http://www.w3.org/1999/xhtml"><p>An optimization problem of classifying shifting-distorted objects is studied. The classifier is 2-layer perceptron, and the object model is monochrome 60 × 80 image. Based on the fact that previously the perceptron has successfully been attempted to classify shifted objects with a pixel-to-shift standard deviation ratio for training, the ratio is optimized. The optimization criterion is minimization of classification error percentage. A classifier trained under the found optimal ratio is optimized additionally. Then it effectively classifies shifting-distorted images, erring only in one case from eight takings at the maximal shift distortion. On average, classification error percentage appears less than 2.5 %. Thus, the optimized 2-layer perceptron outruns much slower neocognitron. And the found optimal ratio shall be nearly the same for other object classification problems, when the number of object features varies about 4800, and the number of classes is between two and three tens.</p></abstract>

An optimization problem of classifying shifting-distorted objects is studied. The classifier is 2-layer perceptron, and the object model is monochrome 60 × 80 image. Based on the fact that previously the perceptron has successfully been attempted to classify shifted objects with a pixel-to-shift standard deviation ratio for training, the ratio is optimized. The optimization criterion is minimization of classification error percentage. A classifier trained under the found optimal ratio is optimized additionally. Then it effectively classifies shifting-distorted images, erring only in one case from eight takings at the maximal shift distortion. On average, classification error percentage appears less than 2.5 %. Thus, the optimized 2-layer perceptron outruns much slower neocognitron. And the found optimal ratio shall be nearly the same for other object classification problems, when the number of object features varies about 4800, and the number of classes is between two and three tens.

Optimal Pixel-to-Shift Standard Deviation Ratio for Training 2-Layer Perceptron on Shifted 60 × 80 Images with Pixel Distortion in Classifying Shifting-Distorted Objects

Khmelnitskiy National University, Ukraine

Applied Computer Systems

This work is licensed under the Creative Commons Attribution 4.0 Public License.

An optimization problem of classifying shifting-distorted objects is studied. The classifier is 2-layer perceptron, and the object model is monochrome 60 × 80...

Optimal Pixel-to-Shift Standard Deviation Ratio for Training 2-Layer Perceptron on Shifted 60 × 80 Images with Pixel Distortion in Classifying Shifting-Distorted Objects

Pubblicato online: 28 mag 2016

Pagine: 61 - 70

DOI: https://doi.org/10.1515/acss-2016-0008

Parole chiave
2-layer perceptron, classification error percentage minimisation, monochrome images, object classification, optimal training, shifting-distorted objects

© 2016 Riga Technical University

This work is licensed under the Creative Commons Attribution 4.0 Public License.

Optimal Pixel-to-Shift Standard Deviation Ratio for Training 2-Layer Perceptron on Shifted 60 × 80 Images with Pixel Distortion in Classifying Shifting-Distorted Objects

Pubblicato online: 28 mag 2016

Pagine: 61 - 70

DOI: https://doi.org/10.1515/acss-2016-0008

Parole chiave2-layer perceptron, classification error percentage minimisation, monochrome images, object classification, optimal training, shifting-distorted objects

© 2016 Riga Technical University

This work is licensed under the Creative Commons Attribution 4.0 Public License.

Parole chiave
2-layer perceptron, classification error percentage minimisation, monochrome images, object classification, optimal training, shifting-distorted objects