ACCURATE RECOVERY OF 3-DIMENSIONAL SHAPE FROM IMAGE FOCUS

被引:210
|
作者
SUBBARAO, M [1 ]
CHOI, T [1 ]
机构
[1] HYUNDAI ELECTR AMER,ENGLEWOOD CLIFFS,NJ 07632
基金
美国国家科学基金会;
关键词
SHAPE-FROM-FOCUS; FOCUSED IMAGE SURFACE; PARAXIAL-GEOMETRIC OPTICS; FOCUS MEASURE; CAMERA PARAMETERS; SHAPE RECOVERY; FOCUSED IMAGE RECONSTRUCTION;
D O I
10.1109/34.368191
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A new Shape-from-focus method is described which is based on a new concept named Focused Image Surface (FIS). PIS of an object is defined as the surface formed by the set of points at which the object points are focused by a camera lens. According to paraxial-geometric optics, there is a one-to-one correspondence between the shape of an object and the shape of its FIS. Therefore, the problem of shape recovery can be posed as the problem of determining the shape of the PIS. From the shape of FIS the shape of the object is easily obtained. In this paper the shape of the FIS is determined by searching for a shape which maximizes a focus measure. In contrast to previous literature where the focus measure is computed over the planar image detector of the camera, here the focus measure is computed over the PIS. This results in more accurate shape recovery than the traditional methods. Also, using FIS, a more accurate focused image can be reconstructed from a sequence of images than is possible with traditional methods. The new method has been implemented on an actual camera system, and the results of shape recovery and focused image reconstruction are presented.
引用
收藏
页码:266 / 274
页数:9
相关论文
共 50 条
  • [41] SHAPE FROM FOCUS BY TOTAL VARIATION
    Mahmood, Muhammad Tariq
    2013 IEEE 11TH IVMSP WORKSHOP: 3D IMAGE/VIDEO TECHNOLOGIES AND APPLICATIONS (IVMSP 2013), 2013,
  • [42] MRT letter: A total variation based method for 3D shape recovery of microscopic objects through image focus
    Mahmood, Muhammad Tariq
    MICROSCOPY RESEARCH AND TECHNIQUE, 2013, 76 (09) : 877 - 881
  • [43] Block Based Focus Volume Pyramid for Shape from Focus
    Ashfaq, Khurram
    Mahmood, Muhammad Tariq
    2024 IEEE TENTH INTERNATIONAL CONFERENCE ON COMMUNICATIONS AND ELECTRONICS, ICCE 2024, 2024, : 522 - 526
  • [44] Guided image filtering in shape-from-focus: A comparative analysis
    Ali, Usman
    Lee, Ik Hyun
    Mahmood, Muhammad Tariq
    PATTERN RECOGNITION, 2021, 111
  • [45] Shape from focus using gradient of focus measure curve
    Fu, Boya
    He, Renzhi
    Yuan, Yilin
    Jia, Wenchao
    Yang, Shichao
    Liu, Fei
    OPTICS AND LASERS IN ENGINEERING, 2023, 160
  • [46] Analysis of focus measure operators for shape-from-focus
    Pertuz, Said
    Puig, Domenec
    Angel Garcia, Miguel
    PATTERN RECOGNITION, 2013, 46 (05) : 1415 - 1432
  • [47] A phase correlation based peak detection method for accurate shape from focus measurements
    Gladines, J.
    Sels, S.
    De Boi, I.
    Vanlanduit, S.
    MEASUREMENT, 2023, 213
  • [48] A simplified approach using deep neural network for fast and accurate shape from focus
    Mutahira, Husna
    Muhammad, Mannan Saeed
    Li, Mikhail
    Shin, Dong-Ryeol
    MICROSCOPY RESEARCH AND TECHNIQUE, 2021, 84 (04) : 656 - 667
  • [49] 3D shape reconstruction from focus and enhanced focus volume
    Wang, Yuezong
    Zhang, Lu
    Chen, Jiqiang
    Zhang, Jialun
    MEASUREMENT, 2025, 245
  • [50] 3D SHAPE RECONSTRUCTION ENDOSCOPE USING SHAPE FROM FOCUS
    Takeshita, T.
    Nakajima, Y.
    Kim, M. K.
    Onogi, S.
    Mitsuishi, M.
    Matsumoto, Y.
    VISAPP 2009: PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOL 1, 2009, : 411 - +