CNN training with graph-based sample preselection: application to handwritten character recognition
In this paper, we present a study on sample preselection in large training data set for CNN-based classification. To do so, we structure the input data set in a network representation, namely the Relative Neighbourhood Graph, and then extract some vectors of interest. The proposed preselection method is evaluated in the context of handwritten character recognition, by using two data sets, up to several hundred thousands of images. It is shown that the graph-based preselection can reduce the training data set without degrading the recognition accuracy of a non pretrained CNN shallow model.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
Preselection via Classification: A Case Study on Evolutionary Multiobjective Optimization
In evolutionary algorithms, a preselection operator aims to select the promising offspring solutions from a candidate offspring set. It is usually based on the estimated or real objective values of the candidate offsprin…
ClassificationEvolutionary AlgorithmsGeneral ClassificationMultiobjective OptimizationOne-Shot Diffusion Mimicker for Handwritten Text Generation
Existing handwritten text generation methods often require more than ten handwriting samples as style references. However, in practical applications, users tend to prefer a handwriting generation model that operates with…
Handwriting generationText GenerationGraph Neural Network based Handwritten Trajectories Recognition
The graph neural networks has been proved to be an efficient machine learning technique in real life applications. The handwritten recognition is one of the useful area in real life use where both offline and online hand…
Graph Neural NetworkHandwriting RecognitionA Large Multi-Target Dataset of Common Bengali Handwritten Graphemes
Latin has historically led the state-of-the-art in handwritten optical character recognition (OCR) research. Adapting existing systems from Latin to alpha-syllabary languages is particularly challenging due to a sharp co…
Multi-Label ClassificationOptical Character RecognitionOptical Character Recognition (OCR)Application of Quantum Pre-Processing Filter for Binary Image Classification with Small Samples
Over the past few years, there has been significant interest in Quantum Machine Learning (QML) among researchers, as it has the potential to transform the field of machine learning. Several models that exploit the proper…
Classificationimage-classificationImage ClassificationMulti-class Classification+1