Learning Geometry

IntuiScript
Script And Labs
Kaligo

We have designed in collaboration with LEARN&GO company, a digital workbook (KALIGO). The goal is to help teachers and children from three to seven years old during the handwriting learning process, by giving direct on-line and off-line feedback. The main objective is to offer an advanced digital writing experience at school by using tablet and tactile digital devices (with finger touch and stylus pen). This project:

• allows children to work in autonomy with online and real time feedback;
• proposes pedagogical exercises that are adapted to the level of the children based on the automatic analysis
  of their handwriting;
• provides precise off-line analysis of children’s writing (i.e., order, direction, shape) to help teachers to
  understand children’s writing skills and difficulties.
  

TV France 3 Bretagne (12/10/2015)
TV 12h45- M6 (28/09/2015)

Vscript: Android tablet application based on Evolve++/EvolveTouch

Vscript is a free Android application (available on Android’s Play Store)  based on Evolve++/EvolveTouch recognition system.
Vscript is a handwriting learning application for children.  In this application the children are following a series of exercises of increasing challenge from identifying shapes for reproducing symbols (shapes, letters, numbers) and ultimately composing pictures and words. EvolveTouch recognition system is used to automatically interpret the handwriting by giving feedbacks of quality. This work is supported by a development fund from SATT Ouest Valorisation.

Varchitect : Windows Store application based on Evolve++/EvolveTouch

Varchitect is a Windows Store application that was developped based on the EvolveTouch. It is available for free at windows store.

With Varchitect, users can define their own set of gesture commands to insert furniture or architectural
elements in a plan, and then design their interior with a stylus. The users can use a picture (taken from the tablet’s builtin camera) as a base and set the scale of their plan.

(see video : http://vimeo.com/76251288)

Evolve Showcase

Evolve Shocase is a gesture-based interaction system for multitouch surfaces. The main feature of our system is its personalization capacity so that user can define his set of gesture and add new gestures at any moment. The system is based on our evolving recognition engine, Evolve++ that can be trained incrementally, starting from few data samples. Evolve-Touch includes a complete mechanism to allow user to manage his gesture sets for different application contexts in simple and user-friendly manner. An intuitive mechanism is adopted to get user feedback on recognizer answers, which allows the latter to continuously enhance its performance.  Moreover, we integrate into the global system a multi-touch object manipulation modality with a simple mode switching. The showcase application presented in this video demonstrates the main features of Evolve-Touch system. Evolve-Touch is protected by a patent.

Mobisketch (ANR project)

MobiSketch deals with Interactive document analysis of complex handwritten documents (diagrams, sketches, architectural plans, historical documents, etc.).

DALI

DALI is the results of Sébastien Macé PhD. It is a framework for the design of pen-based software for structured document composition. DALI is based on a grammatical formalism making it possible to describe such document composition rules. This framework has been transferred to the Evodia society and resulted in the Script&Go “electric diagrams” software.

RESIF

RESIF technology is today composed of three main softwares to analyze, model and recognize handwritten characters and words:

• RESIFCar is the software specialized to recognize handwritten characters: latin alphabet, digits and special symbols.
• RESIFMot is the software for unconstrained cursive handwritten words recognition.
• RESIFApp is the automatic learning process that generates from a handwritten character database the hierarchical fuzzy models used by the recognition systems: RESIFCar and RESIFMot.