International Journal of Computational Vision and Robotics http://www.inderscience.com/browse/index.php?journalID=232&year=2011&vol=2&issue=4 Inderscience Publishers Ltd en-uk International Journal of Computational Vision and Robotics 1752-9131 1752-914X © 2011 Inderscience Publishers Ltd editor@inderscience.com https://www.inderscience.com/images/files/coverImgs/ijcvr_scoverijcvr.jpg http://www.inderscience.com/browse/index.php?journalID=232&year=2011&vol=2&issue=4 http://www.inderscience.com/link.php?id=45263 This paper deals with the path-planning of a robot during the exploration and 3D map building in the unknown environment. The robot uses a stereocamera for significant features detection, then matches them in both images and computes their 3D coordinates. This way the robot incrementally creates the 3D map of its surroundings and tries to explore as much area as possible. This paper describes the way of marking the traversable path in the map created so far and the path planning to the next explored goal point. As the map uses points and triangles to represent shape of the surface, the traversable area marking and the path planning is also done in the map which is represented in the same way. Path planning and traversable area marking for stereo vision-based 3D map building
Jaroslav Rozman; František V. Zbořil
International Journal of Computational Vision and Robotics, Vol. 2, No. 4 (2011) pp. 277 - 289
This paper deals with the path-planning of a robot during the exploration and 3D map building in the unknown environment. The robot uses a stereocamera for significant features detection, then matches them in both images and computes their 3D coordinates. This way the robot incrementally creates the 3D map of its surroundings and tries to explore as much area as possible. This paper describes the way of marking the traversable path in the map created so far and the path planning to the next explored goal point. As the map uses points and triangles to represent shape of the surface, the traversable area marking and the path planning is also done in the map which is represented in the same way.

]]> 10.1504/IJCVR.2011.045263 International Journal of Computational Vision and Robotics, Vol. 2, No. 4 (2011) pp. 277 - 289 Jaroslav Rozman; František V. Zbořil Faculty of Information Technology, Brno University of Technology, Božetĕchova 1/2, 612 66 Brno, Czech Republic. ' Faculty of Information Technology, Brno University of Technology, Božetĕchova 1/2, 612 66 Brno, Czech Republic robot path planning stereo vision visual SLAM traversable area marking feature detection robot vision 3D map building robot navigation. 2012-02-03T23:20:50-05:00 2 4 277 289 2012-02-03T23:20:50-05:00 http://www.inderscience.com/link.php?id=45264 In multilingual countries like India, majority of the documents may contain text information in more than one script/language forms. For automatic processing of such documents through optical character recognition (OCR), it is necessary to design multilingual OCR. With reference to Karnataka state, this paper proposed handwritten Kannada and English character recognition system. The proposed zone based pixel density features are employed for classification of Kannada and English characters. A total of 6,000 handwritten Kannada and English sample images are used for classification. The character images are normalised into 32 × 32 dimensions. Then the normalised images are divided into 64 zones and their pixel densities are calculated and generated a total of 64 features. Further, these features are fed to KNN and SVM classifiers for recognition of the said characters. To measure the performance of the classifiers two-fold cross validation is employed. The proposed algorithm classifies Kannada numerals, vowels and English numerals, uppercase alphabets independently and in combination of these. The average recognition accuracy of 89.21% with KNN and 93.22% with SVM classifiers are achieved. The novelty of the proposed algorithm is free from characters thinning and slants of the characters. A recognition system for handwritten Kannada and English characters
B.V. Dhandra; Gururaj Mukarambi; Mallikarjun Hangarge
International Journal of Computational Vision and Robotics, Vol. 2, No. 4 (2011) pp. 290 - 301
In multilingual countries like India, majority of the documents may contain text information in more than one script/language forms. For automatic processing of such documents through optical character recognition (OCR), it is necessary to design multilingual OCR. With reference to Karnataka state, this paper proposed handwritten Kannada and English character recognition system. The proposed zone based pixel density features are employed for classification of Kannada and English characters. A total of 6,000 handwritten Kannada and English sample images are used for classification. The character images are normalised into 32 × 32 dimensions. Then the normalised images are divided into 64 zones and their pixel densities are calculated and generated a total of 64 features. Further, these features are fed to KNN and SVM classifiers for recognition of the said characters. To measure the performance of the classifiers two-fold cross validation is employed. The proposed algorithm classifies Kannada numerals, vowels and English numerals, uppercase alphabets independently and in combination of these. The average recognition accuracy of 89.21% with KNN and 93.22% with SVM classifiers are achieved. The novelty of the proposed algorithm is free from characters thinning and slants of the characters.

]]> 10.1504/IJCVR.2011.045264 International Journal of Computational Vision and Robotics, Vol. 2, No. 4 (2011) pp. 290 - 301 B.V. Dhandra; Gururaj Mukarambi; Mallikarjun Hangarge Department of P.G. Studies and Research in Computer Science, Gulbarga University, Gulbarga – 585106, Karnataka, India. ' Department of P.G. Studies and Research in Computer Science, Gulbarga University, Gulbarga – 585106, Karnataka, India. ' Department of Computer Science, Karnatak Arts, Science and Commerce College, Bidar – 585401, Karnataka, India document image analysis zone features KNN classifier k nearest neighbour SVM support vector machines Kannada characters handwritten characters English characters India optical character recognition multilingual OCR classification. 2012-02-03T23:20:50-05:00 2 4 290 301 2012-02-03T23:20:50-05:00 http://www.inderscience.com/link.php?id=45267 Chi-square histogram distance is one of the distance measures that can be used to find dissimilarity between two histograms. Motivated by the fact that texture discrimination by human vision system is based on second-order statistics, we make use of histogram of grey level co-occurrence matrix (GLCM) that is based on second-order statistics and propose a new machine vision algorithm for automatic defect detection on patterned textures. Input defective images are split into several periodic blocks and GLCMs are computed after quantising the grey levels from 0-255 to 0-63 to keep the size of GLCM compact and to reduce computation time. Dissimilarity matrix derived from chi-square distances of the GLCMs is subjected to hierarchical clustering to automatically identify defective and defect-free blocks. Effectiveness of the proposed method is demonstrated through experiments on defective real-fabric images of two major wallpaper groups (pmm and p4m groups). GLCM-based chi-square histogram distance for automatic detection of defects on patterned textures
V. Asha; N.U. Bhajantri; P. Nagabhushan
International Journal of Computational Vision and Robotics, Vol. 2, No. 4 (2011) pp. 302 - 313
Chi-square histogram distance is one of the distance measures that can be used to find dissimilarity between two histograms. Motivated by the fact that texture discrimination by human vision system is based on second-order statistics, we make use of histogram of grey level co-occurrence matrix (GLCM) that is based on second-order statistics and propose a new machine vision algorithm for automatic defect detection on patterned textures. Input defective images are split into several periodic blocks and GLCMs are computed after quantising the grey levels from 0-255 to 0-63 to keep the size of GLCM compact and to reduce computation time. Dissimilarity matrix derived from chi-square distances of the GLCMs is subjected to hierarchical clustering to automatically identify defective and defect-free blocks. Effectiveness of the proposed method is demonstrated through experiments on defective real-fabric images of two major wallpaper groups (pmm and p4m groups).

]]> 10.1504/IJCVR.2011.045267 International Journal of Computational Vision and Robotics, Vol. 2, No. 4 (2011) pp. 302 - 313 V. Asha; N.U. Bhajantri; P. Nagabhushan Department of Computer Applications, New Horizon College of Engineering, Outer Ring Road, Marathahalli, Panathur Post, Bangalore – 560 103, Karnataka, India; JSS Research Foundation, SJCE Campus, University of Mysore, Mysore – 570 006, Karnataka, India. ' Department of Computer Science Engineering, Government Engineering College, Chamarajanagar – 571 313, Mysore District, Karnataka, India. ' Department of Studies in Computer Science, University of Mysore, Manasagangotri, Mysore – 570 006, Karnataka, India Chi-square histogram cluster grey level co-occurrence matrix defect detection periodicity patterned textures machine vision fabric images wallpaper defects dissimilarity. 2012-02-03T23:20:50-05:00 2 4 302 313 2012-02-03T23:20:50-05:00 http://www.inderscience.com/link.php?id=45268 This paper proposes a novel computational intelligent vision-based image processing and analysis techniques that can be used in Floatex density separator (FDS), a hindered settling classifier for recovery of quality products from minerals (iron, coal) in order to develop an optimum process control strategy suitable for manipulating complex variables characterised by relatively slow process dynamics. Image processing and analysis software, MATLAB 7.0 was used to process the high speed CCD camera image. The steps include calibration, contrast enhancement and segmentation. Image features are demonstrated and correlated with voidage, particle size distribution, bed height change and density mapping under specific feed rate, pulp density and teeter flow rate of the process. All these information are used for estimation of bed pressure, underflow density cut which will help in the development of accurate control system for reliable operation of FDS from a remote control station. Study of process dynamics in Floatex density separator based on computational intelligent vision
S.K. Mandal
International Journal of Computational Vision and Robotics, Vol. 2, No. 4 (2011) pp. 314 - 322
This paper proposes a novel computational intelligent vision-based image processing and analysis techniques that can be used in Floatex density separator (FDS), a hindered settling classifier for recovery of quality products from minerals (iron, coal) in order to develop an optimum process control strategy suitable for manipulating complex variables characterised by relatively slow process dynamics. Image processing and analysis software, MATLAB 7.0 was used to process the high speed CCD camera image. The steps include calibration, contrast enhancement and segmentation. Image features are demonstrated and correlated with voidage, particle size distribution, bed height change and density mapping under specific feed rate, pulp density and teeter flow rate of the process. All these information are used for estimation of bed pressure, underflow density cut which will help in the development of accurate control system for reliable operation of FDS from a remote control station.

]]> 10.1504/IJCVR.2011.045268 International Journal of Computational Vision and Robotics, Vol. 2, No. 4 (2011) pp. 314 - 322 S.K. Mandal Materials Science and Technology Division, National Metallurgical Laboratory, Jamshedpur, Jharkhand 831 007, India computational intelligence intelligent vision computer vision image processing image analysis contrast enhancement calibration Floatex density separator FDS product recovery minerals iron coal process control process dynamics calibration contrast enhancement image segmentation bed pressure underflow density cut remote control. 2012-02-03T23:20:50-05:00 2 4 314 322 2012-02-03T23:20:50-05:00 http://www.inderscience.com/link.php?id=45269 With the rapid development of information and communication technology (ICT), the communication sector has improved continuously. Artificial intelligence (AI) is a field which has a broad, highly technical and specialised research area focusing on different types of sub areas and has generated a lot of interest with many novel applications in the IT world. Along with recent developments in image processing, AI has also been used to automatically recognise sign language gestures, in what is known as automatic sign language recognition (ASLR). This paper reviews methods of facilitating the communication between deaf and non-deaf persons. Review on sign language recognition methods for supporting communication between deaf and non-deaf persons
Dilushinie De Silva; Rukmal Fernando
International Journal of Computational Vision and Robotics, Vol. 2, No. 4 (2011) pp. 323 - 329
With the rapid development of information and communication technology (ICT), the communication sector has improved continuously. Artificial intelligence (AI) is a field which has a broad, highly technical and specialised research area focusing on different types of sub areas and has generated a lot of interest with many novel applications in the IT world. Along with recent developments in image processing, AI has also been used to automatically recognise sign language gestures, in what is known as automatic sign language recognition (ASLR). This paper reviews methods of facilitating the communication between deaf and non-deaf persons.

]]> 10.1504/IJCVR.2011.045269 International Journal of Computational Vision and Robotics, Vol. 2, No. 4 (2011) pp. 323 - 329 Dilushinie De Silva; Rukmal Fernando Informatics Institute of Technology, University of Westminster, 57, Ramakrishna Road, Colombo, Sri Lanka. ' Informatics Institute of Technology, University of Westminster, 57, Ramakrishna Road, Colombo, Sri Lanka automatic sign language recognition: ASLR computer vision feature extraction support vector machines SVM MATLAB information technology communications technology ICT sign language gestures deaf people non-deaf people. 2012-02-03T23:20:50-05:00 2 4 323 329 2012-02-03T23:20:50-05:00 http://www.inderscience.com/link.php?id=45270 A fourth-order partial differential equation-based approach with a set of local constraints is proposed in this paper, to denoise the images without losing much of the semantically important features like edges and textures. The results provided both in terms of qualitative and quantitative measures substantially endorse the capability of the method. Fourth-order variational model with local-constraints for denoising images with textures
P. Jidesh; Santhosh George
International Journal of Computational Vision and Robotics, Vol. 2, No. 4 (2011) pp. 330 - 340
A fourth-order partial differential equation-based approach with a set of local constraints is proposed in this paper, to denoise the images without losing much of the semantically important features like edges and textures. The results provided both in terms of qualitative and quantitative measures substantially endorse the capability of the method.

]]> 10.1504/IJCVR.2011.045270 International Journal of Computational Vision and Robotics, Vol. 2, No. 4 (2011) pp. 330 - 340 P. Jidesh; Santhosh George Department of Mathematical and Computational Sciences, National Institute of Technology, Karnataka, Mangalore – 575 025, India. ' Department of Mathematical and Computational Sciences, National Institute of Technology, Karnataka, Mangalore – 575 025, India image denoising variational methods fourth-order PDE local constraints partial differential equations edges textures image processing. 2012-02-03T23:20:50-05:00 2 4 330 340 2012-02-03T23:20:50-05:00