Research on feature point extraction and matching machine learning method based on light field imaging

  • Wu Yue 
Machine Learning - Applications & Techniques in Cyber Intelligence


At present, there are many methods to realize the matching of specified images with features, and the basic components include image feature point detection, feature description, and image matching. Based on this background, this article has done different research and exploration around these three aspects. The image feature point detection method is firstly studied, which commonly include image edge information-based feature detection method, corner information-based detection method, and various interest operators. However, all of the traditional detection methods are involved in problems of large computation burden and time consumption. In order to solve this problem, a feature detection method based on image grayscale information-FAST operator is used in this paper, which is combined with decision tree theory to effectively improve the speed of extracting image feature points. Then, the feature point description method BRIEF operator is studied, which is a local expression of detected image feature points based on descriptors. Since the descriptor does not have rotation invariance, the detection operator is endowed by a direction that is proposed in this paper, and then the local feature description is conducted on the feature descriptor to generate a binary string array containing direction information. Finally, the feature matching machine learning method is analyzed, and the nearest search method is used to find the nearest feature point pair in Euclidean distance, of which the calculation burden is small. The simulation results show that the proposed nearest neighbor search and matching machine learning algorithm has higher matching accuracy and faster calculation speed compared with the classical feature matching algorithm, which has great advantages in processing a large number of array images captured by the light field camera.


Image matching Machine learning Nearest neighbor search Light field imaging 


Compliance with ethical standards

Conflict of interest

The authors declare that they have no competing interest.


  1. 1.
    Kim SS, Sohn KH, Savaljev V et al (2001) A full parallax three-dimensional imaging system based on a point light source array. Jpn J Appl Phys 40(8):4913–4915CrossRefGoogle Scholar
  2. 2.
    Choi H, Wadduwage DN, Tu TY et al (2015) Three-dimensional image cytometer based on widefield structured light microscopy and high-speed remote depth scanning. Cytometry Part A 87(1):49–60CrossRefGoogle Scholar
  3. 3.
    Fang SY, Fang JJ (2011) Automatic head and facial feature extraction based on geometry variations. Comput Aided Des 43(12):1729–1739CrossRefGoogle Scholar
  4. 4.
    Kim HS, Jeong KM, Hong SI et al (2012) Analysis of image distortion based on light ray field by multi-view and horizontal parallax only integral imaging display. Opt Express 20(21):23755CrossRefGoogle Scholar
  5. 5.
    Yin HX, Zhu CR, Shen Y et al (2014) Enhanced light extraction in n-GaN-based light-emitting diodes with three-dimensional semi-spherical structure. Appl Phys Lett 104(6):1274Google Scholar
  6. 6.
    Zhang M, Geng Z, Pei R et al (2017) Three-dimensional light field microscope based on a lenslet array. Opt Commun 403:133–142CrossRefGoogle Scholar
  7. 7.
    Young EF, Rannou P, Mckay CP et al (2007) A three-dimensional map of titan’s tropospheric haze distribution based on [ITAL] Hubble Space Telescope [/ITAL] imaging. Astron J 123(6):3473CrossRefGoogle Scholar
  8. 8.
    Kumar RP, Albregtsen F, Reimers M et al (2015) Three-dimensional blood vessel segmentation and centerline extraction based on two-dimensional cross-section analysis. Ann Biomed Eng 43(5):1223–1234CrossRefGoogle Scholar
  9. 9.
    Arimura H, Li Q, Korogi Y et al (2006) Computerized detection of intracranial aneurysms for three-dimensional MR angiography: feature extraction of small protrusions based on a shape-based difference image technique. Med Phys 33(2):394–401CrossRefGoogle Scholar
  10. 10.
    Xie C, Guan W, Wu X, et al. (2018) The LED-ID detection and recognition method based on visible light positioning using proximity method. IEEE Photonics J 99:1.Google Scholar
  11. 11.
    Asakura T, Sakata K, Date Y et al (2018) Regional feature extraction of various fishes based on chemical and microbial variable selection using machine learning. Anal Methods. CrossRefGoogle Scholar
  12. 12.
    Shi J, Wang Y, Chen T et al (2018) Automatic evaluation of traumatic brain injury based on terahertz imaging with machine learning. Opt Express 26(5):6371–6381CrossRefGoogle Scholar
  13. 13.
    Ertuğrul ÖF, Tağluk ME (2017) A novel machine learning method based on generalized behavioral learning theory. Neural Comput Appl 28(12):3921–3939CrossRefGoogle Scholar
  14. 14.
    Sun Q, Zhang Y, Wang J, et al. (2017) An improved FAST feature extraction based on RANSAC method of vision/SINS integrated navigation system in GNSS-denied environments. Adv Space Res 60(12)Google Scholar
  15. 15.
    Nagayama T, Mancini RC, Florido R et al (2012) Investigation of a polychromatic tomography method for the extraction of the three-dimensional spatial structure of implosion core plasmas. Phys Plasmas 19(8):139CrossRefGoogle Scholar
  16. 16.
    Rosalesortega FF, Arribas S, Colina L (2012) Integrated spectra extraction based on signal-to-noise optimization using integral field spectroscopy. Astron Astrophys 539(1):307–316Google Scholar
  17. 17.
    Ukwatta E, Awad J, Ward AD et al (2011) Three-dimensional ultrasound of carotid atherosclerosis: semiautomated segmentation using a level set-based method. Med Phys 38(5):2479–2493CrossRefGoogle Scholar
  18. 18.
    Wischgoll T, Choy JS, Ritman EL et al (2008) Validation of image-based method for extraction of coronary morphometry. Ann Biomed Eng 36(3):356–368CrossRefGoogle Scholar
  19. 19.
    Du Q, Liu R, Pan Y (2017) Depth extraction for a structured light system based on mismatched image pair rectification using a virtual camera. IET Image Proc 11(11):1086–1093CrossRefGoogle Scholar
  20. 20.
    Iglesias JE, Liu CY, Thompson PM et al (2011) Robust brain extraction across datasets and comparison with publicly available methods. IEEE Trans Med Imaging 30(9):1617–1634CrossRefGoogle Scholar
  21. 21.
    Tariq F, Yufit V, Kishimoto M et al (2014) Three-dimensional high resolution X-ray imaging and quantification of lithium ion battery mesocarbon microbead anodes. J Power Sources 248(4):1014–1020CrossRefGoogle Scholar
  22. 22.
    Fadeyev V, Haber C, Maul C et al (2004) Reconstruction of mechanically recorded sound from an edison cylinder using three dimensional non-contact optical surface metrology. J Audio Eng Soc 53(6):485–508Google Scholar
  23. 23.
    Kühmstedt P, Schreiber P, Notni G (2014) Array projection of aperiodic sinusoidal fringes for high-speed three-dimensional shape measurement. Opt Eng 53(11):112208CrossRefGoogle Scholar
  24. 24.
    Geilhufe J, Tieg C, Pfau B et al (2014) Extracting depth information of 3-dimensional structures from a single-view X-ray Fourier-transform hologram. Opt Express 22(21):24959–24969CrossRefGoogle Scholar
  25. 25.
    Yelnik J, Bardinet E, Dormont D et al (2007) A three-dimensional, histological and deformable atlas of the human basal ganglia. I. Atlas construction based on immunohistochemical and MRI data. Neuroimage 34(2):618–638CrossRefGoogle Scholar
  26. 26.
    Liu B, Cheng HD, Huang J et al (2010) Fully automatic and segmentation-robust classification of breast tumors based on local texture analysis of ultrasound images. Pattern Recogn 43(1):280–298CrossRefGoogle Scholar
  27. 27.
    Borgnia MJ, Subramaniam S, Milne JLS (2008) Three-dimensional imaging of the highly bent architecture of bdellovibrio bacteriovorus by using cryo-electron tomography. J Bacteriol 190(7):2588CrossRefGoogle Scholar
  28. 28.
    Chandar R, Leitherer C, Tremonti C et al (2003) The stellar content of henize 2-10 from space telescope imaging spectrograph ultraviolet spectroscopy. Astrophys J 586(2):939CrossRefGoogle Scholar
  29. 29.
    Stal C, Tack F, Maeyer PD et al (2013) Airborne photogrammetry and lidar for DSM extraction and 3D change detection over an urban area—a comparative study. Int J Remote Sens 34(4):1087–1110CrossRefGoogle Scholar
  30. 30.
    Yu Z, Holst MJ, Hayashi T et al (2008) Three-dimensional geometric modeling of membrane-bound organelles in ventricular myocytes: bridging the gap between microscopic imaging and mathematical simulation. J Struct Biol 164(3):304–313CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.Administrative Committee of Changsha High-Tech Industrial Development ZoneChangshaChina
  2. 2.College of Information System and ManagementNational University of Defense TechnologyChangshaChina

Personalised recommendations