Character recognition of kannada text in scene images using neural

International Journal of Graphics and Multimedia (IJGM), ISSN 0976 – 6448(Print),
ISSN 0976 – 6456(Online) Volume 4, Issue 1, January - April 2013, © IAEME
9
CHARACTER RECOGNITION OF KANNADA TEXT IN SCENE
IMAGES USING NEURAL NETWORK
M. M. Kodabagi1
, S. A. Angadi2
, Chetana. R. Shivanagi3
1
Department of Computer Science and Engineering, Basaveshwar Engineering College,
Bagalkot-587102, Karnataka, India,
2
Department of Computer Science and Engineering, Basaveshwar Engineering College,
Bagalkot-587102, Karnataka, India
3
Department of Information Science and Engineering, Basaveshwar Engineering College,
Bagalkot-587102, Karnataka
ABSTRACT
Character recognition in scene images is one of the most fascinating and challenging
areas of pattern recognition with various practical application potentials. It can contribute
immensely to the advancement of an automation process and can improve the interface
between man and machine in many applications. Some practical application potentials of
character recognition system are: reading aid for the blind, traffic guidance systems, tour
guide systems, location aware systems and many more. In this work, a novel method for
recognizing basic Kannada characters in natural scene images is proposed. The proposed
method uses zone wise horizontal and vertical profile based features of character images. The
method works in two phases. During training, zone wise vertical and horizontal profile based
features are extracted from training samples and neural network is trained. During testing, the
test image is processed to obtain features and recognized using neural network classifier. The
method has been evaluated on 490 Kannada character images captured from 2 Mega Pixels
cameras on mobile phones at various sizes 240x320, 600x800 and 900x1200, which contains
samples of different sizes, styles and with different degradations, and achieves an average
recognition accuracy of 92%. The system is efficient and insensitive to the variations in size
and font, noise, blur and other degradations.
Keywords: Character Recognition, Display Boards, Low Resolution Images, Neural
Network Classifier, Zone Wise Profile Features.
INTERNATIONAL JOURNAL OF GRAPHICS AND
MULTIMEDIA (IJGM)
ISSN 0976 - 6448 (Print)
ISSN 0976 -6456 (Online)
Volume 4, Issue 1, January - April 2013, pp. 09-19
© IAEME: www.iaeme.com/ijgm.asp
Journal Impact Factor (2013): 4.1089 (Calculated by GISI)
www.jifactor.com
IJGM
© I A E M E

10
1. INTRODUCTION
In recent years, the hand held devices with increased computing and communication
capabilities are widespread and being used for various purposes such as information access,
mobile commerce, mobile learning, multimedia streaming, and many more. One such new
application that can be integrated in such devices is a text understanding and translation
system for low resolution natural scene images of display boards.
Everyday, several people visit various places across the world for business and other
activities, often they face problem with the language where they travel. This is especially true
in countries like India, which are multilingual. For these reasons, there is a demand for an
automated system that understands text in low resolution natural scene images and provides
translated information in localized language.
Natural scene display board images contain text information which is often required to
be automatically recognized and processed. Scene text may be any textual part of the scene
images such as names of streets, institutes names, names of shops, building names, company
names, road signs, traffic information, warning signs etc. Researchers have focused their
attention on development of techniques for understanding text on such display boards. There is
a spurt of activity in the development of web based intelligent hand held systems for such
applications.
In the reported works [1-10] on intelligent systems for hand held devices, not many
works pertain to understanding of written text on display boards. Therefore, scope exists for
exploring such possibilities. The text understanding involves several processing steps; text
detection and extraction, preprocessing for line, word and character separation, script
identification, text recognition and language translation. Therefore, text recognition at
character level is one of the very important processing steps for development of such systems
prior to further analysis.
Therefore, text recognition at word/character level is premise for the later stages of text
understanding system. The recognition of text in low resolution images of display boards is a
difficult and challenging problem due to various issues such as variability in font size, style
and spacing between characters, skew, perspective distortions, viewing angle, uneven
illuminations, script specific characters and other degradations [11]. The current work aims at
investigating the use of zone wise statistical features for recognition of Kannada characters in
scene images. The proposed method uses zone wise horizontal and vertical profile based
features of character images. The method works in two phases. During training, zone wise
horizontal and vertical profile based features are extracted from training samples and neural
network is trained. During testing, the test image is processed to obtain features and
recognized using neural network classifier. The method has been evaluated on 490 Kannada
character images captured from 2 Mega Pixels cameras on mobile phones at various sizes
240x320, 600x800 and 900x1200, which contains samples of different sizes, styles and with
different degradations, and achieves an average recognition accuracy of 92%. The system is
efficient and insensitive to the variations in size and font, noise, blur and other degradations.
The rest of the paper is organized as follows; the detailed survey related to character
recognition of text in scene images is described in Section 2. The proposed method is
presented in Section 3. The experimental results and discussions are given in Section 4.
Section 5 concludes the work and lists future directions of the work.

11
2. RELATED WORKS
The character recognition of text in low resolution natural scene images is a necessary
step for development of various tasks of text understanding system. A substantial amount of
work has gone into the research related to character recognition of text in natural scene
images. Some of the related works are summarized in the following.
A robust approach for recognition of text embedded in natural scenes is given in [11].
The proposed method extracts features from intensity of an image directly and utilizes a local
intensity normalization to effectively handle lighting variations. Then, Gabor transform is
employed to obtain local features and linear discriminant analysis (LDA) is used for selection
and classification of features. The proposed method has been applied to a Chinese sign
recognition task. This work is further extended integrating sign detection component with
recognition [12]. The extended method embeds multi-resolution and multi-scale edge
detection, adaptive searching, color analysis, and affine rectification in a hierarchical
framework for sign detection. The affine rectification recovers deformation of the text regions
caused by an inappropriate camera view angle and significantly improve text detection rate
and optical character recognition.
A framework that exploits both bottom-up and top-down cues for scene text
recognition at word level is presented in [13]. The method derives bottom-up cues from
individual character detections from the image. Then, a Conditional Random Field model is
built on these detections to jointly model the strength of the detections and the interactions
between them. It also imposes top-down cues obtained from a lexicon-based prior, i.e.
language statistics. The optimal word represented by the text image is obtained by minimizing
the energy function corresponding to the random field model. The method reports significant
improvements in accuracies on two challenging public datasets, namely Street View Text and
ICDAR 2003 compared to other methods. The test results showed that the reported accuracy is
only 73% and requires further improvement.
The hierarchical multilayered neural network recognition method described in [14]
extracts oriented edges, corners, and end points for color text characters in scene image. A
method called selective metric clustering which mainly deals with color is employed in [15].
A fast lexicon based and discriminative semi-Markov models for recognizing scene text are
presented in [16, 17]. An object categorization framework based on a bag-of-visual-words
representation for recognition of character in natural scene images is described in [18]. The
effectiveness of raw grayscale pixel intensities, shape context descriptors, and wavelet features
to recognize the characters is evaluated in [19]. A method for unconstrained handwritten
Kannada vowels recognition based upon invariant moments is described in [20].
The technique presented in [21] extracts stroke density, length, and number of strokes
for handwritten Kannada and English characters recognition. The method found in [22] uses
modified invariant moments for recognition of multi-font/size Kannada vowels and numerals
recognition. A model employed in [23] calculates features from connected components and
obtains 3k dimensional feature vectors for memory based recognition of camera-captured
characters. A character recognition method described in [24] uses local features for
recognition of multiple characters in a scene image.
After the thorough study of literature, it is noticed that, the some [18, 12, 23, 14] of
the reported methods work with limited datasets, other cited works [18, 17, 16] report low
recognition rates in the presence of noise and other degradations and very few works [18-22]
pertain to recognition of Kannada characters from scene images. Hence, more research is

12
desirable to obtain new set of discriminating features suitable for Kannada text in scene
images. In the current work, zone wise statistical features are employed for recognition of
Kannada characters in low resolution images. The detailed description of the proposed
methodology is given in the next section.
3. PROPOSED METHODOLOGY FOR CHARACTER RECOGNITION
The proposed method uses zone wise horizontal and vertical profile based features for
recognition of Kannada characters in mobile camera based images. The proposed method
contains various phases such as Preprocessing, Feature Extraction, Construction of
Knowledge Base for Training Neural Network, Training and Character Recognition with
Neural Network Classifier. The block diagram of the proposed model is given in Fig 1. The
detailed description of each phase is given in the following subsections.
3.1 Preprocessing
The input character image is preprocessed for binarization, noise removal, bounding
box generation and resized to a constant resolution of size 30x30 pixels. Further, the image is
thinned.
Fig. 1. Block Diagram of Proposed Model
3.2 Feature extraction
In this phase, each image is divided into 15 vertical zones and 15 horizontal zones,
where size of each horizontal zone is 2*30 pixels and the size of each vertical zone is 30*2
pixels. Then sum of all on pixels in every zone is determined as a feature value for the zone.
Finally, 30 features are computed from all zones and are stored in to a feature vector X as
described in the equations (1) to (5):
( )( )[ ]HFeaturesVFeaturesX = (1)
Test Sample
Preprocessing
Extraction of Zone Wise
Horizontal and Vertical
Profile Features
Construction of
Knowledge Base
Preprocessing
Character Recognition using
using Neural Network
Classifier
Extraction of Zone Wise
Horizontal and Vertical
Profile Features
Training Samples
Train Neural Network
Recognized Character

13
VFeatures = [ iVf ] 151 ≤≤ i (2)
HFeatures = [ iHf ] 151 ≤≤ i (3)
Where,
iHf is a feature value of ith
horizontal zone and it is computed as shown in (4).
iVf is a feature value of ith
vertical zone and it is computed as shown in (5).
∑∑=
2
1
30
1
),( yxgHf ii
  (4)
∑ ∑=
30
1
2
1
),( yxgVf ii
  (5)
Where, gi is ith
zone that encompasses the chosen region of the character image. The
dataset of such feature vectors obtained from training samples is further used for construction
of knowledge base.
3.3 Construction of Knowledge Base for Training Neural Network
For the purpose of knowledge base construction, the images were captured from
display boards of Karnataka Government offices, names of streets, institute names, names of
shops, building names, company names, road signs, traffic direction and warning signs
captured from 2 Mega Pixels cameras on mobile phones. The images are captured at various
sizes 240x320, 600x800, 900x1200 at a distance of 1 to 6 meters. All these images are used
for evaluating the performance of the proposed model. The images captured with a size of
240x320 at a distance of 1 to 3 meters are found to be clear when the viewing angle is parallel
to the text plane, perspective distortions and other degradations occur beyond 3 meters with
other viewing angles. But the images captured at a distance of 1 to 6 meters with other stated
resolutions are clear, perspective distortions still occur when the viewing angle is not parallel.
The images in the database are characterized by variable font size and style, uneven thickness,
minimal information context, small skew, noise, perspective distortion and other degradations.
The image database consists of 490 Kannada basic character images of varying resolutions.
Then from the database, 50% of samples are used for training. During training, the features are
extracted from all training samples and knowledge base is organized as a dataset of feature
vectors as depicted in (6). The stored information in the knowledge base sufficiently
characterizes all variations in the input. Testing is carried out for all samples containing 50%
trained and 50% untrained samples. Some sample images captured using 2 Mega Pixels
cameras on mobile phones from display boards are shown in Fig 2.
][ jXKB = Nj ≤≤1 (6)
Where, KB is knowledge base comprising feature vectors of training samples., Xj is a feature
vector of jth
image in the KB and N is the number of training sample images.

14
Fig. 2. Sample Images Captured from 2 Mega Pixels Cameras on Mobile Phones
3.4 Training and Recognition with Feed Forward Neural Network
After the data set is obtained and organized into knowledge base of basic Kannada
character images, training and recognition tasks are carried out using feed forward neural
networks. The details of training and recognition are described in the following;
Before network design, the data from in the knowledge base is prepared to cover the
range of inputs for which the network will be used. The feed forward neural network does not
have the ability to accurately extrapolate beyond the range of inputs, so the training data is
chosen to span the full range of the input space. Later, the normalization step is applied to
both the input vectors and the target vectors in the data set. In this way, the network output
always falls into a normalized range. Once the data is ready, the feed forward neural network
object is created with 30 neurons in the input layer, 15 neurons in the hidden layer, and
configured with default weights and biases for the prepared data set in the knowledgebase.
The network is configured with tan sigmoid functions in the input and hidden neurons, linear
transfer functions for output neurons and Levenberg-Marquardt and Gradient Descent with
Momentum learning algorithms. The default performance function for feed forward network
used is mean square error. The parameters learning rate and minimum performance are
initialized with value 0.01. The magnitude of the gradient and the number of validation
checks are used to terminate the training. The number of validation checks parameter is
configured with value 10 and represents the number of successive iterations that the
validation performance fails to decrease.
After the network weights and biases are initialized and configured with other training
parameters, the network is ready for training. The multilayer feed forward network is trained
for function approximation (nonlinear regression) or pattern recognition with network inputs
and target outputs. The training process tunes the values of the weights and biases of the
network to optimize network performance, as defined by the network performance function.
After the network is trained, its performance is verified using several trained and test
character images. The neural network classifier gives an average recognition accuracy of
92%.

15
4. EXPERIMENTAL RESULTS AND ANALYSIS
The proposed methodology has been evaluated for 490 low resolution basic Kannada character
images of varying font size and style, uneven thickness and other degradations. The experimental
results of processing a sample character image is described in section 4.1. And the results of processing
several other character images dealing with various issues, the overall performance of the system and
comparison results with other methods are reported in section 4.2.
4.1. An Experimental Analysis for a Sample Kannada Character Image
The Character image with uneven thickness, uneven lighting conditions, and other
degradations given in Fig. 3a is initially preprocessed for binarization, resized to a constant size of
30x30 pixels and thinned as shown in Fig. 3b.
Fig. 3. a) A Sample Character Test Image b) Preprocessed Image
Further, the image is divided into 15 vertical zones and 15 horizontal zones. Then, the zone
wise statistical features are computed from all zones and are organized into a feature vector T as in (1)
to (5). The experimental values of all zones are shown in Table 1.
TABLE 1. Zone Wise Vertical and Horizontal Features of Sample Input Image in Fig. 3b
Feature Vector
T
[ VFeatures (4 3 13 5 6 6 6 8 6 7 6 9 13 13 4)
HFeatures (2 2 3 6 3 4 9 5 5 6 4 4 5 9 15)
]
T= [ 4 3 13 5 6 8 6 6 8 6 7 6 9 13 13 4 2 2 3 6 3 4 9 5 5 6 4 4 5 9 15]
The experimental values in Table 1 clearly depict the distribution of pixels in various
segments/primitives of the character image. And these distributions are different from character to
character because of varying positions and shapes of segments/primitives of basic Kannada characters.
This is demonstrated considering two sample images in Table 2.
TABLE 2. Vertical and Horizontal Features of Two Sample Images Demonstrating Pixel
Distribution Patterns
Character Image Zone Wise Statistical Features
9 5 6 2 3 2 4 3 11 7 8 11 21 10 2 13 1 5 11
4 4 4 13 9 4 8 5 2 3 5 4
12 8 6 6 6 6 14 18 8 6 6 6 9 14 10 3
2 2 6 8 22 2 2 17 17 9 7 12 10 16
The values in Table 2 clearly show that, the feature values in most of the corresponding zones
of the characters are distinct. For example, the feature values 9, 5, 6, 2 of vertical zones 1, 2, 3 and 4 of
character in first row of Table 2 are distinct from feature values 12, 8, 6, 6 in the corresponding zones
of character in the second row. The similar characteristic exists with the feature values in other zones.
The arrangement of these features into a feature vector creates a pixel distribution pattern that makes

16
samples distinguishable. It is also observed that, the proposed zone wise features also take care of
uncertainty in the appearance of primitives of character image. After extracting features from test input
image in Fig. 2a, the neural network classifier is used to recognize the character.
4.2. An Experimental Analysis dealing with various issues
The proposed methodology has produced good results for low resolution images containing
Kannada characters of different size, font, and alignment with varying background. The advantage lies
in less computation involved in feature extraction and recognition phases of the method. During
experiments it is noticed that, the zone wise features made samples separable in the feature space.
Hence, the proposed work is robust and achieves an average recognition accuracy of 92%. The overall
performance of the system after conducting the experimentation on the dataset is reported in Table 3.
The comparison of the proposed method with other scene text recognition methods is described in
Table 4.
TABLE 3. Overall system performance
Character
Image
Number
of
Samples
Tested
Number of
Samples
Correctly
Recognized
Number
of
Samples
Miss
Classified
% of
Recognitio
n Accuracy
Character
Image
Number
of
Samples
Tested
Number of
Samples
Correctly
Recognized
Number of
Samples
Miss
Classified
% of
Recognition
Accuracy
10 9 1 90 10 10 0 100
10 9 1 90 10 9 1 90
10 9 1 90 10 9 1 90
10 9 1 90 10 10 0 100
10 10 0 100 10 9 1 90
10 9 1 90 10 10 0 100
10 9 1 90 10 9 1 90
10 10 0 100 10 9 1 90
10 10 0 100 10 8 2 80
10 9 1 90 10 10 0 100
10 10 0 100 10 9 1 90
10 9 1 90 10 9 1 90
10 9 1 90 10 9 1 90
10 9 1 90 10 9 1 90
10 8 2 80 10 10 0 100
10 10 0 100 10 8 2 80
10 10 0 100 10 10 0 100
10 10 0 100 10 9 1 90
10 9 1 90 10 8 2 80
10 8 2 80 10 10 0 100
10 10 0 100 10 9 1 90
10 9 1 90 10 9 1 90
10 9 1 90 10 8 2 80
10 10 0 100 10 9 1 90
10 9 1 90

17
A closer examination of results revealed that misclassifications arise due to noise,
more similarity between character structures/primitives and other degradations. It is also
noticed that, zonal features takes care of variations in the appearance of character primitives. It
is also found that, if the knowledge base is trained for all variations and degradations, better
performance can be obtained.
TABLE 4. Comparison of Proposed Method with Other Scene Text Recognition
Methods
Author Approach Features Recognition
Accuracy
Jerod J. Weinman. et. al.
(2008)
A Discriminative
Semi-Markov Model
for Robust Scene
Text Recognition
Wavelet features 82.08%
Onur Tekdas. et. al
(2009)
Recognizing
Characters in Natural
Scenes: A Feature
Study
Raw intensities,
Shape Contexts, and
wavelet features
85.328
Masakazu Iwamura. et.
al (2011)
Recognition of
Multiple Characters
in a Scene Image
Using Arrangement
of Local Features
Scale invariant
feature transform and
voting method
76.5%
Anand Mishra., etal.,
(2012)
Top down and
bottom up cues for
scene text recogntion
Bottom up cues,
language statistics
and condtional
random field model.
73%
Proposed Method Character
Recognition of
Kannada Text in
Scene Images Using
Neural Network
Zone wise vertical
and horizontal profile
based features
92%
5. CONCLUSION
In this work, a novel method for recognition of basic Kannada characters from camera
based images is proposed. The proposed method uses zone wise horizontal and vertical
profile based features and neural network classifier for basic Kannada character recognition.
The system works in two phases, training phase and testing phase. Exhaustive
experimentation was done to analyze zone wise horizontal and vertical profile based features
using neural networks classifier. The results obtained by considering zone wise horizontal
and vertical profile features and neural network classifier are encouraging and it has been
observed that the system is robust and insensitive for several challenges like, unusual fonts,
variable lighting condition, noise, blur etc. The method is tested on 490 samples and gives an
average recognition accuracy of 92%. The proposed method can be extended for character
recognition considering new set of features and classification algorithm.

18
REFERENCES
[1] Abowd Gregory D. Christopher G. Atkeson, Jason Hong, Sue Long, Rob Kooper,
and Mike Pinkerton, 1997, “CyberGuide: A mobile context-aware tour guide”,
Wireless Networks, 3(5): pp.421-433.
[2] Natalia Marmasse and Chris Schamandt, 2000, “Location aware information
delivery with comMotion”, In Proceedings of Conference on Human Factors in
Computing Systems, pp.157-171.
[3] Tollmar K. Yeh T. and Darrell T., 2004, “IDeixis - Image-Based Deixis for Finding
Location-Based Information”, In Proceedings of Conference on Human Factors in
Computing Systems (CHI’04), pp.781-782.
[4] Gillian Leetch, Dr. Eleni Mangina, 2005, “A Multi-Agent System to Stream
Multimedia to Handheld Devices”, Proceedings of the Sixth International
Conference on Computational Intelligence and Multimedia Applications
(ICCIMA’05).
[5] Wichian Premchaiswadi, 2009, “A mobile Image search for Tourist Information
System”, Proceedings of 9th international conference on SIGNAL PROCESSING,
COMPUTATIONAL GEOMETRY and ARTIFICIAL VISION, pp.62-67.
[6] Ma Chang-jie, Fang Jin-yun, 2008, “Location Based Mobile Tour Guide Services
Towards Digital Dunhaung”, International archives of phtotgrammtery, Remote
Sensing and Spatial Information Sciences, Vol. XXXVII, Part B4, Beijing.
[7] Shih-Hung Wu, Min-Xiang Li, Ping-che Yanga, Tsun Kub, 2010, “Ubiquitous
Wikipedia on Handheld Device for Mobile Learning”, 6th IEEE International
Conference on Wireless, Mobile, and Ubiquitous Technologies in Education, pp.
228-230.
[8] Tom yeh, Kristen Grauman, and K. Tollmar., 2005, “A picture is worth a thousand
keywords: image-based object search on a mobile platform”, In Proceedings of
Conference on Human Factors in Computing Systems, pp.2025-2028.
[9] Fan X. Xie X. Li Z. Li M. and Ma. 2005, “Photo-to-search: using multimodal
queries to search web from mobile phones”, In proceedings of 7th ACM SIGMM
international workshop on multimedia information retrieval.
[10] Lim Joo Hwee, Jean Pierre Chevallet and Sihem Nouarah Merah, 2005,
“SnapToTell: Ubiquitous information access from camera”, Mobile human
computer interaction with mobile devices and services, Glasgow, Scotland.
[11] Jing Zhang, Xilin Chen, Andreas Hanneman, Jie Yang, and Alex Waibel.,2002, “A
Robust Approach for Recognition of Text Embedded in Natural Scenes”, proc.
16th International conf. Pattern recognition, volume 3, pp. 204-207 (2002).
[12] Xilin Chen, Jie Yang, Jing Zhang, and Alex Waibel, January 2004, “Automatic
Detection and Recognition of Signs From Natural Scenes”, IEEE Transactions On
Image Processing, Vol. 13, No. 1, pp. 87-99 (January 2004).
[13] Anand Mishra, Karteek Alahari, C. V. Jawahar, 2012, “Top-Down and Bottom-Up
Cues for Scene Text Recognition” , Proceedings of the IEEE Conference on
Computer Vision and Pattern Recognition (CVPR), 2012.
[14] Zohra Saidane and Christophe Garcia, 2007, “Automatic Scene Text Recognition
using a Convolutional Neural Network”, CBDAR, p6, pp. 100-106 (2007)

19
[15] Céline Mancas-Thillou, June 2007, “Natural Scene Text Understanding”,
Segmentation and Pattern Recognition, I-Tech, Vienna, Austria, pp.123-142 (June
2007)
[16] Jerod J. Weinman, Erik Learned-Miller, and Allen Hanson, September 2007, “Fast
Lexicon-Based Scene Text Recognition with Sparse Belief Propagation”, Proc. Intl.
Conf. on Document Analysis and Recognition, Curitiba, Brazil (September 2007)
[17] Jerod J. Weinman, Erik Learned-Miller and Allen Hanson, December 2008, “A
Discriminative Semi-Markov Model for Robust Scene Text Recognition”, IEEE,
Proc. Intl. Conf. on Pattern Recognition (ICPR), Tampa, FL, USA, pp. 1-5
(December 2008)
[18] Te´ofilo E. de Campos and Bodla Rakesh Bab, 2009, “Character Recognition In
Natural Images”, Computer Vision Theory and Applications, Proc. International
Conf. volume , pp. 273-280 (2009)
[19] Onur Tekdas and Nikhil Karnad, 2009, “Recognizing Characters in Natural Scenes:
A Feature Study”, CSCI 5521 Pattern Recognition, pp. 1-14 (2009)
[20] Sangame S.K., Ramteke R.J., and Rajkumar Benne, 2009, “Recognition of isolated
handwritten Kannada vowels”, Advances in Computational Research, ISSN: 0975–
3273, Volume 1, Issue 2, pp 52-55 (2009)
[21] B.V.Dhandra, Mallikarjun Hangarge, and Gururaj Mukarambi, 2010, ”Spatial
Features for Handwritten Kannada and English Character Recognition”, IJCA
Special Issue on Recent Trends in Image Processing and Pattern Recognition
(RTIPPR), pp 146-151 (2010)
[22] Mallikarjun Hangarge, Shashikala Patil, and B.V.Dhandra, 2010, “Multi-font/size
Kannada Vowels and Numerals Recognition Based on Modified Invariant
Moments”, IJCA Special Issue on Recent Trends in Image Processing and Pattern
Recognition (RTIPPR), pp 126-130 (2010)
[23] Masakazu Iwamura, Tomohiko Tsuji, and Koichi Kise, 2010, “Memory-Based
Recognition of Camera-Captured Characters”, 9th
IAPR international workshop on
document analysis systems, pp. 89-96 (2010)
[24] Masakazu Iwamura, Takuya Kobayashi, and Koichi Kise, 2011, “Recognition of
Multiple Characters in a Scene Image Using Arrangement of Local Features”,
IEEE, International Conference on Document Analysis and Recognition, pp. 1409-
1413(2011)
[25] Primekumar K.P and Sumam Mary Idicula, “Performance of on-Line Malayalam
Handwritten character Recognition using Hmm And Sfam”, International Journal of
Computer Engineering & Technology (IJCET), Volume 3, Issue 1, 2012,
pp. 115 - 125, ISSN Print: 0976 – 6367, ISSN Online: 0976 – 6375.
[26] Mr.Lokesh S. Khedekar and Dr.A.S.Alvi, “Advanced Smart Credential Cum
Unique Identification and Recognition System. (Ascuirs)”, International Journal of
Computer Engineering & Technology (IJCET), Volume 4, Issue 1, 2013,
pp. 97 - 104, ISSN Print: 0976 – 6367, ISSN Online: 0976 – 6375.

Character recognition of kannada text in scene images using neural

More Related Content

What's hot (20)

Viewers also liked (6)

Similar to Character recognition of kannada text in scene images using neural (20)

More from IAEME Publication (20)

Recently uploaded (20)

Character recognition of kannada text in scene images using neural