Abstract
The research is focused on optimising two-layer perceptron for generalised scaled object classification problem. The optimisation criterion is minimisation of inaccuracy. The inaccuracy depends on training parameters and hidden layer neuron number. After its statistics is accumulated, minimisation is executed by a numerical search. Perceptron is optimised additionally by extra training. As it is done, the classification error percentage does not exceed 3 % in case of the worst scale distortion.
Highlights
A problem of classifying scaled object issues partially appears due to the impossibility to avoid distortions
The stated 2LP optimisation technique lies in minimising the classification error percentage (CEP) on 5DLL and extra pass training
The CEP statistics in multidimensional matrices is accumulated
Summary
A problem of classifying scaled object issues partially appears due to the impossibility to avoid distortions. They are treated as scaled ones regarding the average dimensions. This is a problem of image recognition [1], [2]. Objects appear closer and farther in front of the cam. Scaling of multidimensional objects can be comprehended as scaled coloured images with metadata [4]. Classifiers must perform reliably through streams of scaled objects. Desired classifiers’ characteristics are speed of classification, quick resetting, saving of disk space and memory. It is important to provide these characteristics along with increasing classification accuracy
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have