SRS - Sign2Speech - Revision history

Reatha.Tith: /* Gesture translation */

2016-04-05T11:41:26Z

Gesture translation

← Older revision		Revision as of 11:41, 5 April 2016
Line 80:		Line 80:

	=== Gesture translation ===		=== Gesture translation ===
	'''Description''':		'''Description''': This part implements all the translation of the project

	'''Inputs''': The gesture encoding returned by the gesture recognization step		'''Inputs''': The gesture encoding returned by the gesture recognization step
Line 90:		Line 90:
	'''Destination''': WebSocket channel		'''Destination''': WebSocket channel

			'''Action''': : Given a word, the program looks for its translation in the dictionary and sends it on the websocket channel if there is a match
	'''Action''':

	'''Non functional requirements''': Real-time search in the dictionary (< 1 second)		'''Non functional requirements''': Real-time search in the dictionary (< 1 second)

Reatha.Tith: /* Gesture recognition */

2016-04-05T11:29:37Z

Gesture recognition

← Older revision		Revision as of 11:29, 5 April 2016
Line 59:		Line 59:

	=== Gesture recognition ===		=== Gesture recognition ===
	'''Description''':		'''Description''': This module does all the tracking process and the encoding

	'''Inputs''': Hand and finger data returned by the camera stream		'''Inputs''': Hand and finger data returned by the camera stream
Line 65:		Line 65:
	'''Source''': Intel's Real Sense camera		'''Source''': Intel's Real Sense camera

	'''Outputs''': The encoding corresponding to the gesture (fingers+~~trajectorie~~)		'''Outputs''': The encoding corresponding to the gesture (fingers+trajectories)

	'''Destination''': Computer's memory		'''Destination''': Computer's memory

			'''Action''': The signing person has to make the gestures in front of the camera (between 20cm and 1m away from the camera). The camera tracks the fingers and the hand and we gather the information in order to calculate averages to encode the gesture as accurately as possible.
	'''Action''':

	'''Non functional requirements''': Real-time tracking (< 1 second) and margin of error (error scoring result < 8)		'''Non functional requirements''': Real-time tracking (< 1 second) and margin of error (error scoring result < 8)

Reatha.Tith: /* Learning mode */

2016-04-05T11:14:34Z

Learning mode

← Older revision		Revision as of 11:14, 5 April 2016
Line 101:		Line 101:

	=== Learning mode ===		=== Learning mode ===
			'''Description''': The function of this mode is to allow the user to add as many gestures (with their translations) as he wants to the dictionary
	'''Description''':

	'''Inputs''': Hand and finger data returned by the camera stream and the meaning of the gesture		'''Inputs''': Hand and finger data returned by the camera stream and the meaning of the gesture
Line 111:		Line 111:
	'''Destination''': Computer's memory		'''Destination''': Computer's memory

			'''Action''': The user has to select the learning mode when launching the application and enter the number of gestures that he wants to record. Guidelines are printed on the screen so that the user knows what to do and when to do it. Basically, he will have to repeat each gesture 3 times in a row (so that the program can compute the average of the 3 repeated gestures to minimize the errors). At the end of the record, the user can chooose whether he wants to add a new word (and stay in the learning mode) or not (in this case, the normal recognition mode will be activated).
	'''Action''':

	'''Non functional requirements''': Real-time tracking (< 1 second)		'''Non functional requirements''': Real-time tracking (< 1 second)

	'''Pre-condition''': Optimal conditions of use (good light, monochrom top that constrats with the color of the skin, no rings, no bracelets, ...)		'''Pre-condition''': Optimal conditions of use (good light, monochrom top that constrats with the color of the skin, no rings, no bracelets, ...). The user must also have divided his gesture into basic gestures to record.

	'''Post-condition''': The new entry in the dictionary must correspond to the gesture that the user intended to do		'''Post-condition''': The new entry in the dictionary must correspond to the gesture that the user intended to do

	'''Side-effects''': If the gesture was not well recognized, the encoding in the dictionary will be wrong		'''Side-effects''': The lack of precision of the camera: if the gesture was not well recognized, the encoding in the dictionary will be wrong

	= Product Evolution =		= Product Evolution =

Edwin.Niogret: /* Product Evolution */

2016-04-05T11:10:37Z

Product Evolution

← Older revision		Revision as of 11:10, 5 April 2016
Line 122:		Line 122:

	= Product Evolution =		= Product Evolution =

			* “Real-time” windows that could show a representation of the hand that the camera is currently analyzing. It could allow the user to know if the camera is able to correctly recognize his hand. It could be done with QT Creator. Our application is not at this time really “friendly-user”.

			*“2 hands” symbols that are currently not implemented in our application

			* Improvements of trajectories recognition

			* Language Model

			*A better camera

Reatha.Tith: /* Product perspective */

2016-04-05T11:02:21Z

Product perspective

← Older revision		Revision as of 11:02, 5 April 2016
Line 26:		Line 26:
	== Product perspective ==		== Product perspective ==

	The main aim of our project is to ~~help~~ ~~speechless~~ ~~people~~ to ~~communicate~~ ~~with~~ ~~other~~ ~~people~~. In ~~this~~ ~~case~~, we ~~develop~~ a software ~~able~~ to ~~recognize~~ and ~~analyze~~ the ~~sign language~~ to ~~retranscribing~~ it in ~~writting~~.		The main aim of our project is to improve the communication between a signing and a non-signing person. To do so, we developed a software that is capable of recognizing gestures, finding their meaning in a linked dictionary and sending the translation to a correspondent via a websocket channel.

	== Product functions ==		== Product functions ==

Reatha.Tith: /* Overview of the remainder of the document */

2016-04-05T10:56:25Z

Overview of the remainder of the document

← Older revision		Revision as of 10:56, 5 April 2016
Line 21:		Line 21:

	In the remainder of the document, the general description of the software will be exposed. The requirements (functional and non-functional) will be specified in another part.		In the remainder of the document, the general description of the software will be exposed. The requirements (functional and non-functional) will be specified in another part.
	The document will end with the product evolution~~, the appendices and the index~~.		The document will end with the product evolution.

	= General Description=		= General Description=

Reatha.Tith at 10:54, 5 April 2016

2016-04-05T10:54:11Z

← Older revision		Revision as of 10:54, 5 April 2016
Line 122:		Line 122:

	= Product Evolution =		= Product Evolution =


	= Appendices =


	= Index =

Reatha.Tith: /* Learning mode */

2016-04-05T10:51:52Z

Learning mode

← Older revision		Revision as of 10:51, 5 April 2016
Line 119:		Line 119:
	'''Post-condition''': The new entry in the dictionary must correspond to the gesture that the user intended to do		'''Post-condition''': The new entry in the dictionary must correspond to the gesture that the user intended to do

			'''Side-effects''': If the gesture was not well recognized, the encoding in the dictionary will be wrong
	'''Side-effects''':

	= Product Evolution =		= Product Evolution =

Reatha.Tith: /* Gesture recognition */

2016-04-05T10:50:36Z

Gesture recognition

← Older revision		Revision as of 10:50, 5 April 2016
Line 73:		Line 73:
	'''Non functional requirements''': Real-time tracking (< 1 second) and margin of error (error scoring result < 8)		'''Non functional requirements''': Real-time tracking (< 1 second) and margin of error (error scoring result < 8)

	'''Pre-condition''': Optimal conditions of use (~~goog~~ light, monochrom top that constrats with the color of the skin, no rings, no bracelets, ...)		'''Pre-condition''': Optimal conditions of use (good light, monochrom top that constrats with the color of the skin, no rings, no bracelets, ...)

	'''Post-condition''': The gesture must have been well recognized by the camera in order to be well encoded		'''Post-condition''': The gesture must have been well recognized by the camera in order to be well encoded

Reatha.Tith: /* Requirement X.Y.Z (in Structured Natural Language) */

2016-04-05T10:49:52Z

Requirement X.Y.Z (in Structured Natural Language)

← Older revision		Revision as of 10:49, 5 April 2016
Line 73:		Line 73:
	'''Non functional requirements''': Real-time tracking (< 1 second) and margin of error (error scoring result < 8)		'''Non functional requirements''': Real-time tracking (< 1 second) and margin of error (error scoring result < 8)

			'''Pre-condition''': Optimal conditions of use (goog light, monochrom top that constrats with the color of the skin, no rings, no bracelets, ...)
	'''Pre-condition''':

	'''Post-condition''': The gesture must have been well recognized by the camera in order to be well encoded		'''Post-condition''': The gesture must have been well recognized by the camera in order to be well encoded
Line 101:		Line 101:

	=== Learning mode ===		=== Learning mode ===
	'''Function''':

	'''Description''':		'''Description''':

			'''Inputs''': Hand and finger data returned by the camera stream and the meaning of the gesture
	'''Inputs''':

	'''Source''':		'''Source''': Intel's Real Sense camera

			'''Outputs''': New dictionary (JSON file) containing the new gestures and their meaning
	'''Outputs''':

	'''Destination''':		'''Destination''': Computer's memory

	'''Action''':		'''Action''':

	'''Non functional requirements''':		'''Non functional requirements''': Real-time tracking (< 1 second)

			'''Pre-condition''': Optimal conditions of use (good light, monochrom top that constrats with the color of the skin, no rings, no bracelets, ...)
	'''Pre-condition''':

			'''Post-condition''': The new entry in the dictionary must correspond to the gesture that the user intended to do
	'''Post-condition''':

	'''Side-effects''':		'''Side-effects''':