No description available.

This work aims on missing handwritten signature authentication in Windows. Result of this work is standalone software that allow users to log into Windows by writing signature. We focus on security of signature authentification and best overall user experience. We implemented signature authentification service that accept signature and return user access token if signature is genuine. Signature authentification is done by comparing given signature to signature patterns by their similarity. Signatures similarity is calculated by dynamic time warp on dynamic signature features such as speed, acceleration and pressure. User access token is used by our Windows login plugin called signature credential provider to decrypt user credentials and perform log in. Result of this work is solution that allow user log to windows by handwritten signatures, with equal error rate of 4.17\%.

Background: To preserve valuable sources and cultural heritage, digitization of handwritten characters is crucial. For this, Optical Character Recognition (OCR) systems were introduced and most widely used to recognize digital characters. Incase of ancient or historical characters, automatic transcription is more challenging due to lack of data, high complexity and low quality of the resource. To solve these problems, multiple image based handwritten dataset were collected from historicaland modern document images. But these dataset also have some limitations. To overcome the limitations, we were inspired to create a new image-based historical handwritten character and word dataset and evaluate it’s performance using machine learning algorithms. Objectives: The main objective of this thesis is to create a first ever Swedish historical handwritten character and word dataset named CArDIS (Character Arkiv Digital Sweden) which will be publicly available for further research. In addition,verify the correctness of the dataset and perform a quantitative analysis using different machine learning methods. Methods: Initially we searched for existing character dataset to know how modern character dataset differs from the historical handwritten dataset. We have performed literature review to learn about most commonly used dataset for OCR. On the other hand, we have also studied different machine learning algorithms and their applica-tions. Finally, we have trained six different machine learning methods namely Support Vector Machine, k-Nearest Neighbor, Convolutional Neural Network, Recurrent Neural Network, Random Forest, SVM-HOG with existing dataset and newly created dataset to evaluate the performance and efficiency of recognizing ancient handwritten characters. Results: The performance/evaluation results show that the machine learning classifiers struggle to recognise the ancient handwritten characters with less recognition accuracy. Out of which CNN outperforms with highest recognition accuracy. Conclusions: The current thesis introduces first ever newly created historical hand-written character and word dataset in Swedish named CArDIS. The character dataset contains 1,01,500 Latin and Swedish character images belonging to 29 classes while the word dataset contains 10,000 word images containing ten popular Swedish names belonging to 10 classes in RGB color space. Also, the performance of six machine learning classifiers on CArDIS and existing datasets have been reported. The thesis concludes that classifiers when trained on existing dataset and tested on CArDIS dataset show low recognition accuracy proving that, the CArDIS dataset have unique characteristics and features over the existing handwritten datasets. Finally, this re-search provided a first Swedish character and word dataset, which is robust with a proven accuracy; also it is publicly available for further research.

No description available.

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. Then, a digit recognition module is employed to classify each segmented digit completing the handwritten digit string recognition task. In this study, different machine learning methods, which are SVM, ANN and CNN architectures are used to achieve high performance on the digit string recognition problem. In these methods, images of digit strings are trained with the SVM, ANN and CNN model with HOG feature vectors and Deep learning methods structure by sliding a fixed size window through the images labeling each sub-image as a part of a digit or not. After the completion of the segmentation, to achieve the complete recognition of handwritten digits.Objective: The main purpose of this thesis is to find out the recognition performance of the methods. In order to analyze the performance of the methods, data is needed to be used for training using machine learning methods. Then digit data is tested on the desired machine learning technique. In this thesis, the following methods are performed: Implementation of HOG Feature extraction method with SVM Implementation of HOG Feature extraction method with ANN Implementation of Deep Learning methods with CNN Methods: This research will be carried out using two methods. The first research method is the ¨Literature Review¨ and the second ¨Experiment¨. Initially, a literature review is conducted to get a clear knowledge on the algorithms and techniques which will be used to answer the first research question i.e., to know which type of data is required for the machine learning methods and the data analysis is performed. Later on, with the knowledge of RQ1, Experimentation is conducted to answer the RQ2, RQ3, RQ4. Quantitative data is used to perform the experimentation because qualitative data which obtains from case-study and survey cannot be used for this experiment method as it contains non-numerical data. In this research, an experiment is conducted to find the best suitable machine learning method from the existing methods. As mentioned above in the objectives, an experiment is conducted using SVM, ANN, and CNN. By considering the results obtained from the experiment, a comparison is made on the metrics considered which results in CNN as the best method suitable for Documents Images. Results: Compare the results for SVM, ANN with HOG Feature extraction and the CNN method by using segmented results. Based on the Experiment results it is found that SVM and ANN have some drawbacks like low accuracy and low performance in the recognition of documented images. So, the other method i.e., CNN has greater performance with high accuracy. The following are the results of the recognition rates of each method. SVM performance - 39% ANN performance - 37% CNN performance - 71%. Conclusion: This research concentrates on providing an efficient method for recognition of automatic handwritten digits recognition. Here a sample training data is treated with existing machine learning and deep learning methods like SVM, ANN, and CNN. By the results obtained from the experimentation, it clearly is shown that the CNN method is much efficient with 71% performance when compared to ANN and SVM methods. Keywords: Handwritten Digit Recognition, Handwritten Digit Segmentation, Handwritten Digit Classification, Machine Learning Methods, Deep Learning, Image processing on document images, Support Vector Machine, Conventional Neural Networks, Artificial Neural Networks

This thesis presents and analyses a corpus of some seventy manuscripts which can be identified at the Dominican monastery of Saint-Louis de Poissy between its foundation in 1304 and its dissolution in 1792. The majority were owned by the nuns and most are illuminated; a small number come from the library of the friars resident at the house. By means of a parallel assessment of surviving documentation the manuscripts are considered throughout in the context of the needs of a well-endowed royal foundation intended for noble women, and in terms of monastic and Dominican history and changing requirements. The fate of the volumes is traced form the time of their production through successive alterations and refurbishments (or damage) in order to assess how the nuns acquired their handwritten books, kept them relevant both textually and artistically, or disposed of them when no longer wanted.

This thesis presents and analyses a corpus of some seventy manuscripts which can be identified at the Dominican monastery of Saint-Louis de Poissy between its foundation in 1304 and its dissolution in 1792. The majority were owned by the nuns and most are illuminated; a small number come from the library of the friars resident at the house. By means of a parallel assessment of surviving documentation the manuscripts are considered throughout in the context of the needs of a well-endowed royal foundation intended for noble women, and in terms of monastic and Dominican history and changing requirements. The fate of the volumes is traced form the time of their production through successive alterations and refurbishments (or damage) in order to assess how the nuns acquired their handwritten books, kept them relevant both textually and artistically, or disposed of them when no longer wanted.

Context: In this thesis subimage matching in historical handwritten documents using SIFT (Scale-Invariant Feature Transform) keypoints was tested. SIFT features are invariant to scale and rotation and have gained a lot of interest in the research community. The historical documents used in this thesis orignates from 16th century and forward. The following steps have been executed; binarization, word segmentation, feature identification and clustering. The binarization step converts the images into binary images. The word segmentation separates the different words into individual subimages. In the feature identification SIFT keypoints was found and descriptors was computed. The last step was to cluster the images based on the distances between the set of image features identified. Objectives: The main objectives are to find a good configuration for the binarization step, implement a good word segmentation, identify image features and lastly to cluster the images based on their similarity. The context from subimages are matched to each other rather than trying to predict what the context of a subimage is, simply because the data that has been used is unlabeled. Methods: Implementation were the main methodology used combined with experimentation. Measurements were taken throughout the development and accuracy of word segmentation and the clustering is measured. Results: The word segmentation got an average accuracy of 89\% correct segmentation which is comparable to other word segmentating results. The clustering however matched 0% correctly.Conclusions: The conclusions that have been drawn from this study is that SIFT keypoints are not very well suited for this type of problem which includes a lot of handwritten text. The descriptors were not discriminative enough and different keypoints were found in different images with the same handwritten text, which lead to the bad clustering results.

The aim of this thesis is to build and evaluate how a word segmentation algorithm performs when extracting words from historical handwritten documents. Since historical documents often consist of background noise, the aim will also be to investigate whether applying a background removal algorithm will affect the final result or not. Three different types of historical handwritten documents are used to be able to compare the output when applying two different word segmentation algorithms. The result attained indicates that the background removal algorithm increases the accuracy obtained when using the word segmentation algorithm. The word segmentation algorithm developed successfully manages to extract a majority of the words while the obtained algorithm has difficulties for some documents. A conclusion made was that the type of document plays the key role in whether a poor result will be obtained or not. Hence, different algorithms may be needed rather than using one for all types of documents.

The need to preserve and exchange written information is central to the human society, with handwriting satisfying such need for several past millenia. Unlike optical character recognition of typeset fonts, which has been throughly studied in the last few decades, the task of handwritten text recognition, being considerably harder, lacks such attention. In this work, we study the capabilities of deep convolutional and recurrent neural networks to solve handwritten text extraction. To mitigate the need for large quantity of real ground truth data, we propose a suitable synthetic data generator for model pre-training, and carry out extensive set of experiments to devise a self-training strategy to adapt the model to unnanotated real handwritten letterings. The proposed approach is compared to supervised approaches and state-of-the-art results on both established and novel datasets, achieving satisfactory performance. 1