Journal of Applied Information Science

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

2D to 3D Conversion of Images Using Defocus Method Along with Laplacian Matting for Improved Medical Diagnosis


Affiliations
1 Rashtreeya Vidyalaya College of Engineering, Bengaluru, Karnataka, India
     

   Subscribe/Renew Journal


In today’s medicine field, there is an increasing need to be more efficient and to be able to develop new techniques to diagnose and cure different diseases and ailments. From the wide range of medical images, there has been an initiative to concentrate or restrict the implementation to X-rays, since X-ray images are the only valid analogies that can be compared to vision from a camera with a perspective. Due to the older diagnosis methods implemented, there is an excess of 2D data when compared to 3D data. Therefore, conversion of 2D data to 3D plays an important factor in arriving at the required result with higher efficiency since it is more cost effective to convert 2D images to 3D rather than create a 3D image from scratch. In this work, the first concept used is of defocus method to perform the depth estimation of the given X-ray image, with the help of edge detection and the second concept used is, gradient magnitude calculation along with image matting using Laplacian process to produce a 3D structure of the 2D image.

Keywords

ARE and RMSE, Defocus Method, Image Quality Metrics, Laplacian Matting.
Subscription Login to verify subscription
User
Notifications
Font Size


  • J. L. Herrera, J. Konrad, C. R. del-Blanco, and N. García, “Learning-based depth estimation from 2D images using gist and saliency,” 2015 IEEE International Conference on Image Processing (ICIP), IEEE, pp. 4753-4757, Quebec City, QC, Canada, 27-30 September 2015.

  • J. L. Herrera, C. R. del-Blanco, and N. García, “Fast 2D to 3D conversion using a clustering-based hierarchical search in a machine learning framework,” 2014 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON), IEEE, pp. 384-387, Budapest, Hungary, 2-4 July 2014.

  • P. R. Kapse, and S. S. Hippargi, “Automatic 2D-to-3D image conversion using KNN search,” 2016 IEEE International Conference on Advances in Electronics, Communication and Computer Technology (ICAECCT), IEEE, pp. 210-215, Pune, India, 2-3 December 2016.

  • H. Tian, B. Zhuang, Y. Hua, and A. Cai, “Depth extraction from a single image by sampling based on distance metric learning,” 2014 IEEE International Conference on Image Processing (ICIP), IEEE, pp. 2017-2021, Paris, France, 27-30 October 2014.

  • J. L. Herrera, C. R. del-Blanco, and N. García, “Learning 3D structure from 2D images using LBP features,” 2014 IEEE International Conference on Image Processing (ICIP), IEEE, pp. 2022-2025, Paris, France, 27-30 October 2014.

  • A. J. Afifi, and O. Hellwich, “Object depth estimation from a single image using fully convolutional neural network,” 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), IEEE, pp. 582-588, Gold Coast, QLD, Australia, 30 November - 2 December 2016.

  • I. Laina, C. Rupprecht, V. Belagiannis, F. Tombari, and N. Navab, “Deeper depth prediction with fully convolutional residual networks,” 2016 Fourth International Conference on 3D Vision, IEEE, pp. 239-248, 2016.

  • M. Liu, M. Salzmann, and X. He, “Discrete-continuous depth estimation from a single image,” 2014 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp. 716-723, Columbus, OH, USA, 23-28 June 2014.

  • S. Manonmani, V. P. Lalitha, and S. Rangaswamy, “Survey on image denoising techniques,” International Journal of Science, Engineering and Technology Research (IJSETR), vol. 5, no. 9, pp. 2824-2827, September 2016.

  • A. L. Wicks, A. T. Asbeck, and S. C. Southward, “Using texture features to perform depth estimation,” Bhavi Bharat Kotha, Blacksburg, Virginia, 15 December 2017.

  • Y. Ren, and J. Liu, “Single outdoor image depth map generation based on scene classification and object detection,” 2014 7th International Conference on Ubi-Media Computing and Workshops, IEEE, pp. 91-94, Ulaanbaatar, Mongolia, 12-14 July 2014.

  • S. Zhuo, and T. Sim, “Defocus map estimation from a single image,” Pattern Recognition, vol. 44, pp. 1852-1858, Elsevier, 2011.

  • S. Paris, P. Kornprobst, J. Tumblin, and F. Durand, “Bilateral filtering: Theory and applications,” Foundations and Trends® in Computer Graphics and Vision, vol. 4, no. 1, pp. 1-73, 2009.

  • S. H. Teoh, and H. Ibrahim, “Median filtering frameworks for reducing impulse noise from grayscale digital images: A literature survey,” International Journal of Future Computer and Communication, vol. 1, no. 4, pp. 323-326, December 2012.

  • J. Konrad, M. Wang, and P. Ishwar, “2D-to-3D image conversion by learning depth from examples,” 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE, pp. 16-22, Providence, RI, USA 16-21 June 2012.

  • S. Rangarajan, “Algorithms for edge detection,”. Available at http://www.uta.edu/faculty/krrao/dip/EE Courses/5356/Edge%20detection%20project.doc [Accessed on January 25th 2018]

  • A. Kulkarni, S. Rangaswamy, and Manonmani S., “Comparative study of major image enhancement algorithms,” European Journal of Engineering Research and Science, vol. 2, no. 7, July 2017.

  • J. Canny, “A computational approach to edge detection,” Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679-698, November 1986.

  • Y. L. Wei, B. Li, J. D. Li, and Y. Y. Fan, “Impulse noise filtering algorithm based on dual threshold criterion,” Applied Mechanics and Materials, vol. 437, pp. 849-852, 2013.

  • T. Sun, M. Gabbouj, and Y. Neuvo, “Center weighted median filters: Some properties and their applications in image processing,” Signal Processing, Elsevier, vol. 35, no. 3, pp. 213-229, 1994.

  • R. Chandel, and G. Gupta, “Image filtering algorithms and techniques: A review,” International Journal of Advanced Research in Computer Science and Software Engineering, vol. 3, no. 10, pp. 198-202, 2013.

  • M. Basu, “Gaussian-based edge-detection methods - A survey,” IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications and Reviews, vol. 32, no. 3, pp. 252-260, 2002.

  • C. Cadena, Y. Latif, and I. D. Reid, “Measuring the performance of single image depth estimation methods,” 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 9-14 October 2016.

  • C. Chen, J. Twycross, and J. M. Garibaldi, “A new accuracy measure based on bounded relative error for time series forecasting,” Published, 24 March 2017.


Abstract Views: 320

PDF Views: 0




  • 2D to 3D Conversion of Images Using Defocus Method Along with Laplacian Matting for Improved Medical Diagnosis

Abstract Views: 320  |  PDF Views: 0

Authors

S. Manonmani
Rashtreeya Vidyalaya College of Engineering, Bengaluru, Karnataka, India
Shanta Rangaswamy
Rashtreeya Vidyalaya College of Engineering, Bengaluru, Karnataka, India
K. Dhanush Kumar
Rashtreeya Vidyalaya College of Engineering, Bengaluru, Karnataka, India
Ishan Srivastava
Rashtreeya Vidyalaya College of Engineering, Bengaluru, Karnataka, India
Jonnalagadda Akhilesh
Rashtreeya Vidyalaya College of Engineering, Bengaluru, Karnataka, India
Joshua Issac
Rashtreeya Vidyalaya College of Engineering, Bengaluru, Karnataka, India

Abstract


In today’s medicine field, there is an increasing need to be more efficient and to be able to develop new techniques to diagnose and cure different diseases and ailments. From the wide range of medical images, there has been an initiative to concentrate or restrict the implementation to X-rays, since X-ray images are the only valid analogies that can be compared to vision from a camera with a perspective. Due to the older diagnosis methods implemented, there is an excess of 2D data when compared to 3D data. Therefore, conversion of 2D data to 3D plays an important factor in arriving at the required result with higher efficiency since it is more cost effective to convert 2D images to 3D rather than create a 3D image from scratch. In this work, the first concept used is of defocus method to perform the depth estimation of the given X-ray image, with the help of edge detection and the second concept used is, gradient magnitude calculation along with image matting using Laplacian process to produce a 3D structure of the 2D image.

Keywords


ARE and RMSE, Defocus Method, Image Quality Metrics, Laplacian Matting.

References