Segmentation, tracking and feature extraction

International Journal on Computational Sciences & Applications (IJCSA) Vol.4, No.2, April 2014
DOI:10.5121/ijcsa.2014.4207 57
Segmentation, Tracking And Feature Extraction
For Indian Sign Language Recognition
Divya S , Kiruthika ,S Nivin Anton A L and Padmavathi S
Student, Department of Computer Science & Engineering, Amrita University
ABSTRACT
Sign Language is a means of communication between audibly challenged people. To provide an interface
between the audibly challenged community and the rest of the world we need Sign Language translators. A
sign language recognition system computerizes the work of a sign language translator. Every Sign
Language Recognition (SLR) System is trained to recognize specific sets of signs and they correspondingly
output the sign in the required format. These SLR systems are built with powerful image processing
techniques. The sign language recognition systems are capable of recognizing a specific set of signing
gestures and output the corresponding text/audio. Most of these systems involve the techniques of detection,
segmentation, tracking, gesture recognition and classification. This paper proposes a design for a SLR
System.
KEYWORDS
Indian Sign Language (ISL), Sign Language Recognition Systems (SLR Systems), Skin Based Segmentation,
RGB, HSV, YCbCr, Kalman Filter, SIFT.
1. INTRODUCTION
Sign Language Translators act an interface of communication between the audibly challenged and
the rest of the world. Providing an interface between the communities in Indian Sign Language
(ISL) is very challenging issue because of the following reasons
(1) The ISL Signs have not been standardized as of date.
(2) The ISL Signs vary from region to region and hence we have various dialects of ISL.
(3) Every Signer does the same gesture in a different ways.
(4) Information regarding the signs and gestures are multichannel.
The Central Institute ISL Society is currently working in collaboration with Ramakrishna Mission
to standardize the ISL Signs.
ISL words are categorized into 4 types as- (1) Feelings (2) Descriptions (3) Actions and (4) Non-
Manual Actions. ISL grammar omits the usage of articles such as (a, an, the) and also does not
include tense forms. The sentence structure of an ISL sentence (SOV) – Subject Object Verb-
very much different from the sentence structure of English Language (SVO) – Subject Verb
Object and hence ISL and English Language aren’t verbatim convertible. The term sign and
gesture are used interchangeably throughout the paper. The Signs are represented by the
HamNoSys* System of Notation for Sign Language. Most of the signs in ISL involve dynamic
movement of both the hands and non-manual gestures. SLR systems are simple yet trained
intelligent systems used for converting sign language into text by recognizing the head and hand
gestures. SLR systems have been classified into two types based on the approach- (1) Data Glove

58
Based Method and (2) Vision Based Method. Data Glove Based Approach simplifies the
recognition of the gestures but involves complicated hardware. The Vision Based Approach is a
very user friendly and does not involve complicated hardware usage and hence its most widely
used method in SLR Systems
Figure: 1 – Taxonomy of ISL Signs [1]
The paper is organized as follows; Section II provides the Survey of the various SLR Systems.
Section III gives a detail description of the proposed SLR System. The Experimental Results are
described in the Section IV. Finally, Section V provides a few concluding remarks and lists out
the acknowledgments.
2. LITERATURE SURVEY
Most of the SLR systems today use the Vision Based – Skin Colour Approach since the gestures
to be identified depend gesturing of the hands and face. The skin based filtering help to extract
the necessary components from the other coloured pixels and also helped to extract objects from
their background. [2-10]. Most of the skin based methods use the pixel by pixel method and these
methods help to determine whether the given pixel intensity is a skin pixel or not. Prior to these
methods, statistical models like Gaussian Mixture Model [8], Single Gaussian Model [9] and
Histogram Based Approaches [10] were used. Many researchers also made use of Coloured
Gloves to simplify the process of segmentation [12].
Paulraj et al [2] built an SLR System on a Skin colour based approach. After segmentation the
frames were converted into binary images. During feature extraction, the areas of the three
segmented areas were calculated and noted down as discrete events. Since each gesture involves
different segmented areas, the DCT coefficients of the three segmented regions were taken as the
features. These features were given as input to the Neural Network (NN) Classifier. The NN does
the gesture classification and plays the corresponding audio signal. The system has a minimum
and maximum classification rate of 88% and 95% respectively.
ISL SIGNS
One Handed
Eg: Sign for
Moon
Non-Manual
Eg: Facial Expression
(Confusion- raising
eye brows in doubt,
Anger, etc.)
Two Handed
Eg: Sign for Air
Movement StaticStatic Movement
Manual
Manual
Non-
Manual
Non-
Manual
TYPE - 0 TYPE - 1

59
Joyeeta Singha and Karen Das [3] developed a system to recognize alphabets. The regions of
interest were cropped and the Eigen values and vectors of these regions were used as features and
also as input to the classification system. A novel approach called the Eigen Value Weighted
Euclidean Distance was used to classify the gestures. The system has a success rate of 97%.
An SLR System was proposed by Kishore Kumar et al [4] to automatically recognize gestures of
words and convert them to text or audio format. A combination of wavelet transforms and image
fusion techniques was used during the process of segmentation. Edge Based tracking methods
was used to track the gesture movements. Elliptical Fourier descriptors were taken as features and
it is given as input to the fuzzy system, which was used to classify and recognize the gestures.
The system has a success rate of 91%.
Deepika Tewari and Sanjay Kumar Srivastava proposed a method for the recognition of Indian
Sign Language [5] in which gesture frames were taken with a digital camera. Features were
extracted using 2D Discrete Cosine Transform (2D-DCT) for each detected region, and feature
vectors were formed from the DCT coefficients. Self-organizing map (SOM) using an
unsupervised learning technique in Artificial Neural Network (ANN) was used to classify DCT-
based feature vectors into groups and to decide if the gesture performed is either present or absent
in the ISL database. The recognition rate achieved was 80%.
Joe Naoum-Sawaya et al proposed a system for American Sign Language Recognition [6]. The
hands were detected by performing motion detection over a static background. After background
subtraction, the image is segmented using skin colour based thresholding methods. Morphological
operations were done to improve the robustness of the segmentation results. The CAMSHIFT
(Continuously Adaptive Mean- SHIFT) algorithm is used to draw a box about the region of the
hand to simplify template matching. The gesture is recognized by the template with the highest
matching metric. Each of the dynamic gestures is coded as a series of directions and static
gestures. The accuracy for this system is 96% in daylight with distinct backgrounds.
Jaspreet Kaur et al uses modified SIFT algorithm for American Sign Language[7].A modified
method of comparability measurement is introduced to improve the efficiency of the SIFT
algorithm. This system is highly robust to scale difference, rotation by any angle and reflection
and is 98.7% accurate for recognizing gestures. Typically every SLR system involves various
techniques in the following categories
i. Segmentation or Detection
ii. Tracking the Gestures
iii. Feature Extraction and Gesture Recognition
iv. Gesture Classification
We have provided a detailed survey of the methods that can used for the above categories in
[28][29][30].The presence or absence of any of the above mentioned categories depends on the
input dataset. The successive section provides a detailed account of our proposed system designed
to recognize ISL signs.
3. PROPOSED SLR SYSTEM
The section elucidates the detailed description of our proposed system to recognize Indian Sign
Language words. The dataset chosen involves mostly two handed movement gestures without any
non-manual markers. The only regions of interest are the two hands and the face region. The
system requires a constant background and also uniform lighting conditions. Like every other
SLR system, our system also involves the stages of Detection or Segmentation, Morphological
operations to remove noise, Tracking the motion of the regions, Feature Extraction, Gesture
Recognition, Gesture Classification and System Learning. The input video is taken from a digital

60
camera and converted into frames. The technique of segmentation here uses the skin colour based
method and hence extracts the skin colour regions.
Figure 2: Flow Diagram for the Proposed System
The system requires the signer to wear a dark long sleeved shirt except shades of skin colour. The
skin colour based segmentation is a fairly simple method with the only decision to be made on
which colour space to use. The result of this method depends dominantly on the chosen colour
space. The RGB colour space is an additive colour space and also used one of the most
commonly used colour space. The RGB space has high correlation between channels, lot of non-
uniformity and also there is a dominant mixing of the chromaticity and the luminance
information. [14] Hence the use of the RGB space alone is not suitable for colour based
recognition [15]. To overcome this problem the normalized RGB has been introduced to obtain
the chromaticity information for more robust results. [16][17][18][19][28].
Eq. (1)
Eq. (2)
Eq. (3)
In the above equations, represent the normalized values of R, G and B
respectively. These normalized values will satisfy the Eq. (4).
Eq. (4)
The following are the equations used for the conversion of pixel intensities from RGB to HSV.
Eq. (5)
Eq. (6)
INPUT VIDEO
CONVERT INPUT
VIDEO TO FRAMES
SKIN COLOR BASED
SEGMENATION
KALMAN FILTER
BASED TRACKING
SIFT BASED GESTURE
RECOGNITION
DTW BASED
CLASSFICATION

61
0 If Max = Min
If Max =
H = Eq. (7)
If Max =
If Max =
0 If Max = 0
S = Eq. (8)
Otherwise
Eq. (9)
The following matrix is used to convert intensities from RGB colour space to YCbCr Colour
Space.
= + Eq. (10)
In this chosen method [20] for skin colour segmentation the pixel intensity if tested for skin
colour in HSV, RGB and YCbCr Colour space. Only if the pixel is found to be a skin colour pixel
in all the colour spaces it is taken as a skin colour pixel or else it is identified as background pixel.
The thresholding conditions for the skin colour classification in the various colour spaces are as
follows:
In the RGB space, the following rule put forward by Peer et al [21], determines the skin colour
under uniform daylight.
AND
AND Eq. (11)
For skin colour under flashlight, a lateral rule for detection is given by
AND
Eq.(12)

62
To take note of both the conditions, the above two rules are combined using the logical operator,
OR.
In YCbCr space, the following thresholding conditions are applied.
Eq. (13)
In [21] the thresholds for the YCbCr was improved by including the parameters for Y and Cb.
Eq. (14)
In the HSV space, the conditions for skin colour are:
Eq.(15)
The above two condition are combined using a Logical operator OR. If the pixel intensity falls
under all the above threshold conditions, then the pixel intensity will be classified as a skin colour
intensity.
The results obtained from the segmentation are further acted upon by morphological operations
are used to eliminate the presence of noise in the segmentation results. The operations like erode,
dilate, open and close are done to obtain needed results.
The contours of the segmented regions are obtained and the smaller contours are eliminated by
the sorting the areas of the contours and taking the contours whose areas are significantly the
largest three. Taking into the consideration that the largest contour will the head, we fix the
position of the head. Based on the position of the head, the other two contours can be identified as
left and right hand. After the process of segmentation, bounding boxes are drawn around the three
segmented regions, obtained by the above mentioned process.
The flow diagram for the segmentation process is as follows:
Yes Yes
Yes
Figure 3: Steps in Segmentation
INPUT
FRAME
(PIXEL
BY
PIXEL)
CHECK IF
THE PIXEL
IS SKIN
COLOR IN
RGB SPACE
CHECK IF
THE PIXEL
IS SKIN
COLOR IN
HSV SPACE
CHECK IF
THE PIXEL
IS SKIN
COLOR IN
YCBCR
THE PIXEL
INTENSITY IS
RETAINED
Yes

63
In cases of occlusion of hands or head & hand, there might be only one or two contours visible
depending on the sign and when occlusion occurs, the Kalman Filter begins to predict the position
of the regions.
For each of the regions, the following sequence is done.
Figure 4: Steps in Tracking
The parameters of the bounding box are used to give input to the Kalman Filter [22] for initiating
the tracking process.
The principle of the Kalman Filter [23] involves the prediction of the location of the head and
hand regions in the consecutive frames based on the current state and previous state estimates.
Kalman Filter takes as input - the measurements of the present state and does a prediction of the
consecutive states.
Kalman Filter is optimal estimator of the successive states which has two main methods predict
and correct methods. The predict method does an estimate of the next state and the correct
method optimizes the system taking into consideration the actual measurements of the regions.
The prediction step uses the state model to predict the next state of the system [13]
Eq. (16)
Eq. (17)
and are the state and covariance prediction at time t. D represents the state transition
matrix which define the relationship between the state variable at time t and t-1. The matrix Q is
the covariance of the white noise W.
The correction step uses the actual observations of the object’s current position to update the
state of the object.
Eq. (18)
CENTRE OF MASS IS
COMPUTED
KALMAN FILTER IS
INITIAILIZED
PREDICTS THE BLOB IN
THE NEXT FRAME
CORRECTS BASED ON
ACTUAL
MEASUREMENTS

64
+ Eq. (19)
M Eq. (20)
K is the Kalman Gain and Eq. (17) is the Ricatti equation used for the propagation of the state
models. is the update state. In Eq. (18), the term is called the innovation.
The three regions are capable of movement in the 2D space and hence each region at the (x, y)
position with velocities follow the equations:
Eq. (21)
Eq. (22)
Eq. (23)
Eq. (24)
represent the change in the positions in the X and Y directions respectively. The terms
and represent the ‘x’ and ‘y’ velocities at time (t-1). The regions are represented by
the state vector which holds information about the x position, y position, horizontal and vertical
velocities. represent the velocities in the x and y direction at time‘t’.
The state vector is represented as follows
, ) Eq. (25)
Since we use a only a four dimensional vector for representing the state, the transition matrix can
be simply given by
1 0 1 0
0 1 0 1 Eq. (26)
D =0 0 1 0
0 0 0 1
The three regions can be easily tracked by computing the Centre of Mass.[29] The Centre of Mass
of the three regions are the initial parameters given to the three objects of Kalman Filter. The
initial detections of the regions are used to initialize the Kalman Filters for the three regions. The
next step involves predicting the new locations of the three regions based on the previous state
parameters. The predict and correct methods of the Kalman Filter are used in sequence help
reduce the noise in the system. The predict method by itself is used to estimate the location of a
region when it is occluded by another region. The correct method which corrects and optimizes
the prediction mechanism is based on the actual measurements. The steps of the Filter are
recursive till required. This method provides the trajectory of motion of the hands and head. The
Kalman Filter Based Multiple Object Tracking is robust to occlusions and movements involving
rotation and scaling. The tracking step is very essential when the occlusion of the two or three
regions occurs, since the tracker continues to track the regions even if region is not in the field of
view.
The next step in the process of sign language recognition is the Gesture Recognition. For this
process, we are using Scale Invariant Feature Transform (SIFT), to find the gestures and its
invariant to translation, rotation, scaling and its partially invariant to illumination. The image

65
feature recognition is performed through four phases [6] of which the various phases are (1) Scale
space local extrema detection (2) Key Point Localization (3) Orientation Assignment (4) Key
Point Descriptor. In the first phase the key points from various orientations are obtained. The
Scale Space Function is available for this phase. [24]
Eq. (27)
where is the Input Image, is the variable Gaussian Scale. Scale Space Extrema
is found by difference between two images, one with k times the other.
Figure 5: Difference of Gaussian (DoG)[25]
To obtain the local minima and maxima we compare each key point with eight neighbours on the
same scale and nine neighbours on scales above and below it. The next phase involves fitting of
the key points in the three degree quadratic functions. This function is obtained from the second
order Taylor Expansion. The local extrema with lower contrasts will not take into consideration
because they are sensitive to noise. The key points below the threshold level are also not taken in
account by the system.
The next phase involves the orientation assignment where the main orientation is assigned to
each feature based on local image gradient. For each pixel around the key point the gradient
magnitude and the orientation are computed. The following equations are used to find the
magnitude and orientation [25]
Eq. (28)
The above equation is used to calculate the magnitude of the detected key points.
ϴ(x, y) = Eq. (29)
In the above equation, ϴ(x, y) gives the orientation of the key point. Eq (28) is to calculate the
orientation of the detected key points. The orientation and magnitude of the key points
are stored and used in the further process of Gesture Classification.
The next phase of gesture recognition is the key point descriptor phase. In this the local
image gradients are measured at a selected scale around each key point.
The following diagram [30] specifies the steps in the gesture recognition process.

66
Figure 6: Steps in Gesture Recognition
The final phase of the Sign Language Recognition System is the classifier system. The
Classification System uses the concept for classifying the gestures. A number of
Classification Systems have been used extensively used.
4. EXPERIMENTAL RESULTS
The designed system has been tested on 25 different signs of ISL. The domain words are
restricted to child learning. The signs have been performed under varying conditions with 15
different signers. Each of these test cases have been performed at varying lighting and under
complex background. A sample of our dataset is shown in Fig - 7.
Figure 8: Gestures for the word (Girl)
The Segmentation algorithm is applied on the input signs are the results obtained the Fig.9 (a) &
(b) are the skin colour representations of the segmentation results. The binary skin color
segmentation is shown in the Fig- 10 (a) & (b).
TRACKED REGIONS ARE CROPPED
FEATURE EXTRACTION USING SIFT
ORIENTATION DETECTION
GESTURE RECOGNITION

67
(a) (b)
Figure 9: Skin Colour Regions – Segmentation Results
(a) (b)
Figure 10: Skin Colour Segmentation – Binary Threshold Results
Skin colour segmentation fails to produce proper segmentation results when the signer
wears dresses of shades similar to skin colour. The results obtained in the presence of
other skin colour objects in the scenario and also when the signer is clothed in shades of
skin colour are shown in Fig – 11(a) & (b). Hence it can be inferred that system produces
erroneous results in the presence of other skin coloured objects.
(a) (b)
Figure 11: (a) Input Frame (b) Erroneous Results
The results of segmentation, tracking and gesture recognition also varies in the presence of
variable lighting conditions. When the signing of the word is done under variable lighting
conditions, the algorithm fails to find the necessary results as show in the Fig – 12(a) & (b).

68
(a) (b)
Figure 12: Results – Non-Uniform Lighting Conditions (a) Input Frame (b) Output
The system works perfectly well under uniform lighting condition. The system constraints also
require the signer to wear long sleeved dark clothing for the algorithm to produce the required
results. The results are as shown in figure in Fig-13(a) & (b). The Fig-14(a) & (b) represent the
input frame and the output where the system handles the occlusion of the hands.
(a) (b)
Figure 13: Results – Uniform Lighting (a) Input Frame (b) Output
(a) (b)
Figure 14: Results – Occlusion under Uniform Lighting (a) Input Frame (b) Output

69
(a) (b)
Figure 15: Results (a) Input Frame (b) Output
Real time sign language recognition under varying conditions of lighting causes errors in the
segmentation of the regions and hence it is inferred that the further processes of tracking, gesture
recognition and classification depend on the results of segmentation. The results of segmentation
are refined using morphological operations.
The segmentation results for the three colour spaces are shown below separately. Figure-16
represents the HSV component separately. Figure-17 shows the output for RGB component.
Figure-17 represents the YCbCr.
(a) (b)
Figure -16 (a) Input (b) HSV component
(a) (b)

70
Figure: 17 (a) Input (b) RGB Component
(a) (b)
Figure: 18 (a) Input (b) YCbCr Component
Figure-19 represents the result of tracking using Particle Filter and Keypoints plotting using SIFT
Algorithm. The red dots represents the tracking points of Hands and head separately. The other
colour dots shows the key points.
(a) (b)
Figure: 19(a) Input (b) Tracking and SIFT

71
5. CONCLUSIONS
Our SLR requires the signer to perform the signing under constant illumination and also requires
the signer to wear a long sleeved attire which can be constraint to a signer to do the same under
natural constraints. The system developed uses a simple parametric pixel based segmentation
method which can be further improved using system training methods. The performance of
tracking has a lot of scope of improvement. The Gesture Recognition mechanism can be replaced
by Advanced SIFT for improved accuracy. The input dataset can be further extended and the
classifying system can be further trained by providing more positive and negative samples.
ACKNOWLEDGEMENTS
We take this opportunity to express our sincere thanks to “Ramakrishna Mission Vivekananda
University, Coimbatore Campus FDMSE- Indian Sign Language” for providing us valuable
information regarding the Signs of Indian Sign Language. We also express our deepest gratitude
to Ms. Poongothai, ISL Interpreter for helping us with our dataset.
REFERENCES
[1] Tirthankar Dasgupta, Sambit Shukla, Sandeep Kumar, Synny Diwakar, Anupam Basu.”A
Multilingual Multimedia Indian Sign Language Dictionary Tool”, the 6th Workshop on Asian
Language Resources, 2008.
[2] Paulraj M P, Sazali Yaacob, Hazry Desa, Hema C.R., “Extraction of Head & Hand Gesture
Feature for Recognition of sign language”, International Conference on Electronic Design, Penang,
Malaysia, December 1-3, 2008.
[3] Joyeeta Singha & Karen Das, “Indian Sign Language Recognition Using Eigen Value Weighted
Euclidean Distance Based Classification Technique”, International Journal of Advanced Computer
Science and Applications, Vol. 4, No. 2, 2013.
[4] P.V.V Kishore, P.Rajesh Kumar , E. Kiran Kumar & S.R.C Kishore , “Video Audio Interface for
Recognizing Gestures of Indian Sign Language”, International Journal of Image Processing , Volume
5, Issue 4, 2011, pp. 479-503.
[5] Deepika Tewari, Sanjay Kumar Srivastava, “A Visual Recognition of Static Hand Gestures in Indian
Sign Language based on Kohonen Self – Organizing Map Algorithm”, International Journal of
Engineering & Advanced Technology (IJEAT), Vol. 2, Issue-2, December 2012.
[6] Joe Naoum-Sawaya, Mazen Slim, Sami Khawam and Mohamad Adnan Al-Alaoui, ”Dynamic System
Design for American Sign Language Recognition”, Electrical and Computer Engineering Department,
American University of Beirut, Beirut, Lebanon.
[7] Jaspreet Kaur, Navjot Kaur, “Modified SIFT Algorithm for Appearance Based Recognition of
American Sign Language”, IJCSET, Vol. 2, Issue 5, May 2012.
[8] J.-C. Terrillon, M. David, and S. Akamatsu,,”Automatic Detection of Human Faces in Natural Scene
Images by use of a Skin Color Model and of Invariant Moments”,Proc.Int.Conf.AFGR’98, Nara,
Japan, pp. 112-117,1998.
[9] S.J. McKenna, S. Gong, and Y. Raja, “Modeling Facial Color and Identity with Gaussian Mixtures”,
Pattern Recognition, 31(12), pp. 1883-1892, 1998.
[10] R. Kjeldsen and J. Kender, “Finding Skin in Color Images”, Proc.Int. Conf. AFGR’96, Killington,
Vermont, pp. 312-317, 1996.
[11] A. A. Argyros, M. I. A. Lourakis: "Real-Time Tracking of Multiple Skin-Colored Objects with a
Possibly Moving Camera", ECCV, 2004.
[12] Rini Akmeliawati , Melanie Po-Leen Ooi and Ye Chow Kuang, “Real Time Malaysian Sign
Language Translation using Color Segmentation and Neural Network”,IMTC 2007- Instrumentation
and Measurement Technology Conference Warsaw , Poland ,1-3, May 2007.
[13] Yilmaz, A., Javed, O., and Shah, M. 2006. “Object tracking: A survey”. ACM Computing. Survey.
38, 4, Article 13 (Dec. 2006), 45 pages. DOI = 10.1145/1177352.1177355
http://doi.acm.org/10.1145/1177352.1177355

72
[14] V. Vezhnevets, V. Sazonov, A. Andreeva,” A survey on pixel-based skin color detection
techniques,”GRAPHICON03, 2003, pp. 85–92.
[15] Manresa, C., Varona, J., Mas, R., Perales, F.J.,”Real-time hand tracking and gesture recognition for
human-computer interaction”, ELCVIA (5), No. 3, 2005, Pages: 96-104.
[16] Beetz, M., B. Radig, and M. Wimmer. “A person and context specific approach for skin color
classification”, 18th International Conference on Pattern Recognition, 2006 (ICPR 2006). 2006. Hong
Kong.
[17] Soriano, M., et al., “Skin detection in video under changing illumination conditions”, 15th
International Conference on Pattern Recognition 2000. 2000. Barcelona.
[18] Kawato, S. and J. Ohya., “Automatic skin-color distribution extraction for face detection and
tracking”, 5th International Conference on Signal Processing Proceedings 2000 (WCCC-ICSP 2000).
2000. Beijing.
[19] Park, J., et al., “Detection of human faces using skin color and eyes”, 2000 IEEE International
Conference on Multimedia and Expo 2000 (ICME 2000). 2000. New York, NY.
[20] Nusirwan Anwar bin Abdul Rahman, Kit Chong Wei and John, “RGB-H-CbCr Skin Color Model for
Human Face Detection”, MMU International Symposium on Information & Communications
Technologies (M2USIC), 2006.
[21] G.Kukharev, A.Novosielski, “Visitor identification – elaborating real time face recognition system,”
Proceedings of the 12th Winter School on Computer Graphics (WSCG) , Plzen, Czech Republic , pp.
157-164, February , 2004.
[21] P. Peer, J. Kovac, F. Solina, “Human Skin Color Clustering for Face Detection”, EUROCON1993,
Ljubljana, Slovenia, pp. 144-148, September 2003.
[22] R.E Kalman, “A new approach to linear ﬁltering and prediction problems”, Transactions of the
ASME, Ser. D., Journal of Basic Engineering, 82, 34-45. (1960).
[23] Welch, G., Bishop, G.: “An Introduction to the Kalman Filter”, ACM SIGGRAPH 2001, Course 8,
available at http://www.cs.unc.edu/∼welch/Kalman/ (2001).
[24] Pallavi Gurjal , Kiran Kunnur, “Real Time Hand Gesture Recognition Using SIFT”, International
Journal of Electronics and Electrical Engineering, Volume 2 Issue 3 ,March 2012.
[25] Sakshi Goyal, Ishita Sharma, Shanu Sharma, “Sign Language Recognition System for Deaf and
Dumb People, “International Journal of Engineering Research &Technology, Vol. 2 Issue 4, April –
2013.
[26] Sakoe. H and Chiba, S. “Dynamic Programming Algorithm Optimization for Spoken Word
Recognition”, IEEE Trans. on Acoust Speech, and Signal Process. ASSP 26, 43-49 (1978).
[27] Bautista, M., Hernández-Vela, A., Ponce, V., Perez-Sala, X., Baro´, X., Pujol, O., Angulo, C.,
Escalera, S., “Probability-based dynamic time warping for gesture recognition on RGB-D data”. In:
International Workshop on Depth Image Analysis. Tsukuba Science City, Japan (2012)
[28] Padmavathi, S., Nivin Anton, AL., “Survey of Skin Color Segmentation Techniques”, International
Journal of Engineering Research & Technology, Vol. 3, Issue 2, February- 2014.
[29] Padmavathi, S., Divya, S., “Survey on Tracking Algorithms”, International Journal of Engineering
Research & Technology, Vol. 3, Issue 2, February- 2014.
[30] Padmavathi, S., Kiruthika, S., Navin Kumar, PI. , “Survey on Hand Gesture Recognition”,
International Journal of Engineering Research & Technology, Vol. 3, Issue 2, February- 2014.

Segmentation, tracking and feature extraction

More Related Content

What's hot (19)

Viewers also liked (8)

Similar to Segmentation, tracking and feature extraction (20)

Recently uploaded (20)

Segmentation, tracking and feature extraction