21-06-2013, 03:25 PM
HAND GESTURE RECOGNITION: A LITERATURE REVIEW
HAND GESTURE.pdf (Size: 456.12 KB / Downloads: 143)
ABSTRACT
Hand gesture recognition system received great attention in the recent few years because of its
manifoldness applications and the ability to interact with machine efficiently through human computer
interaction. In this paper a survey of recent hand gesture recognition systems is presented. Key issues of
hand gesture recognition system are presented with challenges of gesture system. Review methods of recent
postures and gestures recognition system presented as well. Summary of research results of hand gesture
methods, databases, and comparison between main gesture recognition phases are also given. Advantages
and drawbacks of the discussed systems are explained finally.
The essential aim of building hand gesture recognition system is to create a natural interaction
between human and computer where the recognized gestures can be used for controlling a robot
or conveying meaningful information [1]. How to form the resulted hand gestures to be
understood and well interpreted by the computer considered as the problem of gesture interaction
[2].
Human computer interaction (HCI) also named Man-Machine Interaction (MMI) [3][4] refers to
the relation between the human and the computer or more precisely the machine, and since the
machine is insignificant without suitable utilize by the human [3]. There are two main
characteristics should be deemed when designing a HCI system as mentioned in [3]: functionality
and usability. System functionality referred to the set of functions or services that the system
equips to the users [3], while system usability referred to the level and scope that the system can
operate and perform specific user purposes efficiently [3]. The system that attains a suitable
balance between these concepts considered as influential performance and powerful system [3].
Gestures used for communicating between human and machines as well as between people using
sign language [5].
Extraction Method and image pre-processing
Segmentation process is the first process for recognizing hand gestures. It is the process of
dividing the input image (in this case hand gesture image) into regions separated by boundaries
[12]. The segmentation process depends on the type of gesture, if it is dynamic gesture then the
hand gesture need to be located and tracked [12], if it is static gesture (posture) the input image
have to be segmented only. The hand should be located firstly, generally a bounding box is used
to specify the depending on the skin color [13] and secondly, the hand have to be tracked, for
tracking the hand there are two main approaches; either the video is divided into frames and each
frame have to be processed alone, in this case the hand frame is treated as a posture and
segmented [12], or using some tracking information such as shape, skin color using some tools
such as Kalman filter[12].
Gestures Classification
After modeling and analysis of the input hand image, gesture classification method is used to
recognize the gesture. Recognition process affected with the proper selection of features
parameters and suitable classification algorithm [7]. For example edge detection or contour
operators [9] cannot be used for gesture recognition since many hand postures are generated and
could produce misclassification [9]. Euclidean distance metric used to classify the gestures
[19][5][17]. Statistical tools used for gesture classification, HMM tool has shown its ability to
recognize dynamic gestures [20][13]besides, Finite State Machine (FSM) [21], Learning Vector
Quantization [22], and Principal Component Analysis (PCA) [23]. Neural network has been
widely applied in the field of extracted the hand shape [14], and for hand gesture recognition
[24][25][26].
DRAWBACKS
In this section, drawbacks of some discussed methods are explained: Orientation histogram
method applied in [19] have some problems which are; similar gestures might have different
orientation histograms and different gestures could have similar orientation histograms, besides
that, the proposed method achieved well for any objects that dominate the image even if it is not
the hand gesture [19]. Neural Network classifier has been applied for gestures classification
[28][8] but it is time consuming and when the number of training data increase, the time needed
for classification are increased too [8]. In [28] the NN required several hours for learning 42
characters and four days to learn ten words [28]. Fuzzy c-means clustering algorithm applied in
[6] has some disadvantages; wrong object extraction problem raised if the objects larger than the
hand. The performance of recognition algorithm decreases when the distance greater than 1.5
meters between the user and the camera. Besides that, its variation to lighting condition changes
and unwanted objects might overlap with the hand gesture. In [16] the system is variation to
environment lighting changes which produces erroneous segmentation of the hand region. HMM
tools are perfect for recognition dynamic gestures [13] but it is computational consuming.
CONCLUSIONS
In this paper various methods are discussed for gesture recognition, these methods include from
Neural Network, HMM, fuzzy c-means clustering, besides using orientation histogram for
features representation. For dynamic gestures HMM tools are perfect and have shown its
efficiency especially for robot control [20][16]. NNs are used as classifier [8][25] and for
capturing hand shape in [14]. For features extraction, some methods and algorithms are required
even to capture the shape of the hand as in [15][17][18], [17] applied Gaussian bivariate function
for fitting the segmented hand which used to minimize the rotation affection [17][18]. The
selection of specific algorithm for recognition depends on the application needed. In this work
application areas for the gestures system are presented. Explanation of gesture recognition issues,
detail discussion of recent r