Optimal Pixel-to-Shift Standard Deviation Ratio for Training 2-Layer Perceptron on Shifted 60x80 Images with Pixel Distortion in Classifying Shifting-Distorted Objects

Applied Computer Systems 2016
Vadim V. Romanuke

An optimization problem of classifying shiftingdistorted 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 shiftingdistorted 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.

Keywords
2-layer perceptron, classification error percentage minimisation, monochrome images, object classification, optimal training, shifting-distorted objects
DOI
10.1515/acss-2016-0008
Hyperlink
https://content.sciendo.com/view/journals/acss/19/1/article-p61.xml

Romanuke, V. Optimal Pixel-to-Shift Standard Deviation Ratio for Training 2-Layer Perceptron on Shifted 60x80 Images with Pixel Distortion in Classifying Shifting-Distorted Objects. Applied Computer Systems, 2016, Vol.19, pp.61-70. ISSN 2255-8683. e-ISSN 2255-8691. Available from: doi:10.1515/acss-2016-0008

Publication language
English (en)