Edge-SiamNet and Edge-TripleNet: New Deep Learning Models for Handwritten Numeral Recognition
Weiwei Jiang, Le Zhang
Abstract
Handwritten numeral recognition is a classical and important task in the computer vision area. We propose two novel deep learning models for this task, which combine the edge extraction method and Siamese/Triple network structures. We evaluate the models on seven handwritten numeral datasets and the results demonstrate both the simplicity and effectiveness of our models, comparing to baseline methods.
Topics & Concepts
Numeral systemComputer scienceEnhanced Data Rates for GSM EvolutionArtificial intelligenceTask (project management)Deep learningPattern recognition (psychology)Baseline (sea)Speech recognitionGeologyOceanographyManagementEconomicsHandwritten Text Recognition TechniquesVehicle License Plate RecognitionAdvanced Neural Network Applications