Recognition of handwritten digits by image processing and neural network

Abstract

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

An Artificial Neural Network Approach for Generating High-Resolution Designs From Low-Resolution Input in Topology Optimization

“…Our proposed method uses 20 images partitioned down to a range of 1,198 to 3,486 observations depending on the model selected, thus requiring significantly less data than what is common in deep CNN applications. ANNs similar to our proposed models have successfully been used for pattern recognition of grayscale handwritten numbers [17] and interpolation of grayscale source images for conversion to color [18].…”

An expert system for general symbol recognition

“…A system by Burel et al [10] uses a combination of statistical and morphological features and has proved to be successful in handwritten digit recognition. There are 20 regions.…”

An Adaptive Modular Neural Network With Application to Unconstrained Character Recognition

“…Routines, such as those described in [7], can improve the generalization ability up to a certain point. But, if the number of input patterns classes is very large or if the patterns are spread very unevenly in the input space, the generalization ability breaks down.…”