Sökning: "Handwritten Digit Recognition"
Hittade 5 uppsatser innehållade orden Handwritten Digit Recognition.
1. A Comparison of Advanced DeepLearning Algorithms for Multi-digit Detection in Historical Documents
Master-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskapSammanfattning : Background: Historical handwritten documents are assets for future generations and should be appropriately secured, so handwritten digit detection plays an important role to preserve them. Handwritten digit detection is a fundamental problem and has been studied extensively for many years. LÄS MER
2. Hyperparameter Optimization for Convolutional Neural Networks
Magister-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Training algorithms for artificial neural networks depend on parameters called the hyperparameters. They can have a strong influence on the trained model but are often chosen manually with trial and error experiments. LÄS MER
3. Handwritten digit recognition based on segmentation-free method
Master-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskapSammanfattning : This thesis aims to implement a segmentation-free strategy in the context of handwritten multi-digit string recognition. Three models namely VGG-16, CRNN and 4C are built to be evaluated and benchmarked, also research about the effect of the different training set on model performance is carried out. .. LÄS MER
4. Multivariate analysis of the parameters in a handwritten digit recognition LSTM system
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Throughout this project, we perform a multivariate analysis of the parameters of a long short-term memory (LSTM) system for handwritten digit recognition in order to understand the model’s behaviour. In particular, we are interested in explaining how this behaviour precipitate from its parameters, and what in the network is responsible for the model arriving at a certain decision. LÄS MER
5. Automatic Handwritten Digit Recognition On Document Images Using Machine Learning Methods
Master-uppsats, Blekinge Tekniska HögskolaSammanfattning : Context: The main purpose of this thesis is to build an automatic handwritten digit recognition method for the recognition of connected handwritten digit strings. To accomplish the recognition task, first, the digits were segmented into individual digits. LÄS MER