uiux
Regular
http://www.itiv.kit.edu/english/343_7093.php
Background
There are numerous situations in daily life where we take notes and afterwards realize that we need the content in a digital form (like meeting notes, protocols, forms or lecture notes). But how to digitize your handwritten notes? There are different products like document scanners, tablets with a stylus or smart pens. All of these solutions require additional equipment or special paper to work correctly. With this thesis we will explore thepossibilities of improving a system that is able to digitize handwriting with a pen that writes on regular paper. Within this work there will be a strong cooperation with the STABILO International GmbH. A prototype of the DigiPen, a recording system, data sets, developed machine learning methods andevaluation boards will be provided by STABILO.
Tasks
The primary goal of this thesis is the adaptation of an existing neural network on various Neural Processing computing devices for Edge AI devices and systems, such as Google Coral or BrainChip Akida. The different Neural Processing computing devices shall be evaluated with respect to power consumption and compared with a central data processing system. Based on the results, a tradeoff between performance and power consumption should be identified in detail.
https://stabilodigital.com/digipen/
What is the Digipen?
The innovative and multi-talented STABILO Digipen combines analogue and digital media: handwriting can be transformed seamlessly into machine readable clear text and thus saved so that it can be further processed in a variety of ways on tablets, smartphones or PCs. The Digipen understands handwriting and also scores highly with other intelligent features that offer real added value to every user in their everyday life, at work, while studying or at school.
www.geeky-gadgets.com
Stabilo Digipen Does Not Need A Special Paper To Function (video)
---
https://ieeexplore.ieee.org/abstract/document/9257740
Digitizing Handwriting with a Sensor Pen: A Writer-Independent Recognizer
Abstract
Online handwriting recognition has been studied for a long time with only few practicable results when writing on normal paper. Previous approaches using sensor-based devices encountered problems that limited the usage of the developed systems in real-world applications. This paper presents a writer-independent system that recognizes characters written on plain paper with the use of a sensor-equipped pen. This system is applicable in real-world applications and requires no user-specific training for recognition. The pen provides linear acceleration, angular velocity, magnetic field, and force applied by the user, and acts as a digitizer that transforms the analogue signals of the sensors into timeseries data while writing on regular paper. The dataset we collected with this pen consists of Latin lower-case and upper-case alphabets. We present the results of a convolutional neural network model for letter classification and show that this approach is practical and achieves promising results for writer-independent character recognition. This work aims at providing a real-time handwriting recognition system to be used for writing on normal paper.
---
https://www.itiv.kit.edu/201.php
KIHT - Kaligo-based Intelligent Handwriting Teacher
Handwriting and digital media exist without much overlap. The development of numerous digital pens has not changed that much. Studies repeatedly show that handwritten drafts lead to a higher quality result compared to typing a text. That means without handwriting a knowledge society loses one of its most potent tools. Up until now, the learning of handwriting had to be continuously monitored and controlled by a teacher or parents. By using suitable computer programs and an electronic pen, it is possible to accompany this learning process automatically. The aim of the joint project "KIHT" is the development of an intelligent learning device that supports learning handwriting. The learning device should be equivalent to a normal pen in all important properties, so that the greatest possible success is achieved. It is important to use paper and pen as writing utensils in order to optimally reproduce the normal writing process. An electronic pen is used as a writing instrument, which hasInertial sensors . The use of a tablet computer makes it possible to customize the exercises for each student and to automatically synchronize and save the data. The electronic pen developed in this project should be connected to all common mobile devices and interact with an app. While the French side is mainly devoted to software and AI algorithms, the German side will deal with the integration of suitable AI concepts into the embedded hardware. This distributes the complexity of the overall system to both the software and hardware, which enables fast and efficient AI execution. The planned, intelligent learning device should be made available to the largest possible group of users.
https://www.itiv.kit.edu/english/343_7093.php
The primary goal of this thesis is the adaptation of an existing neural network on various Neural Processing computing devices for Edge AI devices and systems, such as Google Coral or BrainChip Akida. The different Neural Processing computing devices shall be evaluated with respect to power consumption and compared with a central data processing system. Based on the results, a tradeoff between performance and power consumption should be identified in detail.
Background
There are numerous situations in daily life where we take notes and afterwards realize that we need the content in a digital form (like meeting notes, protocols, forms or lecture notes). But how to digitize your handwritten notes? There are different products like document scanners, tablets with a stylus or smart pens. All of these solutions require additional equipment or special paper to work correctly. With this thesis we will explore thepossibilities of improving a system that is able to digitize handwriting with a pen that writes on regular paper. Within this work there will be a strong cooperation with the STABILO International GmbH. A prototype of the DigiPen, a recording system, data sets, developed machine learning methods andevaluation boards will be provided by STABILO.
Tasks
The primary goal of this thesis is the adaptation of an existing neural network on various Neural Processing computing devices for Edge AI devices and systems, such as Google Coral or BrainChip Akida. The different Neural Processing computing devices shall be evaluated with respect to power consumption and compared with a central data processing system. Based on the results, a tradeoff between performance and power consumption should be identified in detail.
https://stabilodigital.com/digipen/
What is the Digipen?
The innovative and multi-talented STABILO Digipen combines analogue and digital media: handwriting can be transformed seamlessly into machine readable clear text and thus saved so that it can be further processed in a variety of ways on tablets, smartphones or PCs. The Digipen understands handwriting and also scores highly with other intelligent features that offer real added value to every user in their everyday life, at work, while studying or at school.
Stabilo Digipen Does Not Need A Special Paper To Function (video)
Pen manufacturer Stabilo has created a new digital pen aptly named the Stabilo Digipen, which was showcased at the recent CES 2015 technology show and
---
https://ieeexplore.ieee.org/abstract/document/9257740
Digitizing Handwriting with a Sensor Pen: A Writer-Independent Recognizer
Abstract
Online handwriting recognition has been studied for a long time with only few practicable results when writing on normal paper. Previous approaches using sensor-based devices encountered problems that limited the usage of the developed systems in real-world applications. This paper presents a writer-independent system that recognizes characters written on plain paper with the use of a sensor-equipped pen. This system is applicable in real-world applications and requires no user-specific training for recognition. The pen provides linear acceleration, angular velocity, magnetic field, and force applied by the user, and acts as a digitizer that transforms the analogue signals of the sensors into timeseries data while writing on regular paper. The dataset we collected with this pen consists of Latin lower-case and upper-case alphabets. We present the results of a convolutional neural network model for letter classification and show that this approach is practical and achieves promising results for writer-independent character recognition. This work aims at providing a real-time handwriting recognition system to be used for writing on normal paper.
---
https://www.itiv.kit.edu/201.php
KIHT - Kaligo-based Intelligent Handwriting Teacher
Handwriting and digital media exist without much overlap. The development of numerous digital pens has not changed that much. Studies repeatedly show that handwritten drafts lead to a higher quality result compared to typing a text. That means without handwriting a knowledge society loses one of its most potent tools. Up until now, the learning of handwriting had to be continuously monitored and controlled by a teacher or parents. By using suitable computer programs and an electronic pen, it is possible to accompany this learning process automatically. The aim of the joint project "KIHT" is the development of an intelligent learning device that supports learning handwriting. The learning device should be equivalent to a normal pen in all important properties, so that the greatest possible success is achieved. It is important to use paper and pen as writing utensils in order to optimally reproduce the normal writing process. An electronic pen is used as a writing instrument, which hasInertial sensors . The use of a tablet computer makes it possible to customize the exercises for each student and to automatically synchronize and save the data. The electronic pen developed in this project should be connected to all common mobile devices and interact with an app. While the French side is mainly devoted to software and AI algorithms, the German side will deal with the integration of suitable AI concepts into the embedded hardware. This distributes the complexity of the overall system to both the software and hardware, which enables fast and efficient AI execution. The planned, intelligent learning device should be made available to the largest possible group of users.
https://www.itiv.kit.edu/english/343_7093.php
The primary goal of this thesis is the adaptation of an existing neural network on various Neural Processing computing devices for Edge AI devices and systems, such as Google Coral or BrainChip Akida. The different Neural Processing computing devices shall be evaluated with respect to power consumption and compared with a central data processing system. Based on the results, a tradeoff between performance and power consumption should be identified in detail.
