Robust recognition of partially occluded 3-D objects from computationally reconstructed hologram by using a spatial filtering scheme

Park, Seok‐Chan; Lee, Keong-Jin; Sang-Hyun, Lee; Kim, Seung-Cheol; Kim, Eun-Soo

doi:10.1117/12.808388

Cited by 3 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Matching [42,43] In [42], Park et al have studied the sensitivity of employing correlation in matching the reconstructed images of a pair of holograms if the target object T is partially blocked by an occluding object O c . Their evaluation reveals that the amplitude of the correlation peak will be attenuated in the presence of O c , to the extent that the similarity between the reference and the target objects cannot be determined correctly.…”

Section: F Overcoming the Occlusion Problem In Hologrammentioning

confidence: 99%

“…A vigorous study on the use of wavelet transform in the recognition of SEOL holograms has also been reported in [40,41]. Park et al [42] have studied the sensitivity of employing correlation in matching the reconstructed images of a pair of holograms when one of them is partially occluded. Apart from addressing the occlusion issue, they have also utilized the look-up-table method [43] (which is referred to as the N-LUT method in the article) to increase the computation efficiency of the recognition process.…”

Section: Introductionmentioning

confidence: 97%

“…The organization of this work is as follows. In Section 2, we shall describe the works conducted by VanderLugt [18], Poon and Kim [26,27], Javidi et al [28][29][30][31][32][33], Seifi et al [36], Nelleri et al [37,38], and Park et al [42]. In Section 3, we describe our investigation on H3DOR, which is based on the recently proposed virtual diffraction plane (VDP) framework [46].…”

Section: Introductionmentioning

confidence: 98%

See 2 more Smart Citations

Review of holographic-based three-dimensional object recognition techniques [Invited]

et al. 2014

View full text Add to dashboard Cite

With the advancement of computing and optical technologies, it is now possible to capture digital holograms of real-life object scenes. Theoretically, through the analysis of a hologram, the three-dimensional (3D) objects coded on the hologram can be identified. However, being different from an optical image, a hologram is composed of complicated fringes that cannot be analyzed easily with traditional computer vision methods. Over the years, numerous important research investigations have been attempted to provide viable solutions to this problem. The aim of this work is three-fold. First, we provide a quick walkthrough on the overall development of holographic-based 3D object recognition (H3DOR) in the past five decades, from film-based approaches to digital-based innovation. Second, we describe in more detail a number of selected H3DOR methods that are introduced at different timelines, starting from the late sixties and then from the seventies, where viable digital holographic-based 3D recognition methods began to emerge. Finally, we present our work on digital holographic, pose-invariant 3D object recognition that is based on a recently introduced virtual diffraction plane framework. As our method has not been reported elsewhere, we have included some experimental results to demonstrate the feasibility of the approach.

show abstract

Section: F Overcoming the Occlusion Problem In Hologrammentioning

confidence: 99%

Section: Introductionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

Review of holographic-based three-dimensional object recognition techniques [Invited]

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Most of these approaches are sensitive to positional shifts and deformations. The methods and the problems are described in detail by VanderLugt works in [1] and the articles in [2][3][4][5]. The hologram classifier employed in this paper is EDL-IOHC [6], in which a modern deep learning approach is employed.…”

Section: Introductionmentioning

confidence: 99%

Off-Axis Holographic Interferometer with Ensemble Deep Learning for Biological Tissues Identification

2022

View full text Add to dashboard Cite

This paper proposes a method with an off-axis interferometer and an ensemble deep learning (I-EDL) hologram-classifier to interpret noisy digital holograms captured from the tissues of flawed biological specimens. The holograms are captured by an interferometer, which serves as a digital holographic scanner to scan the tissue with 3D information. The method achieves a high success rate of 99.60% in identifying the specimens through the tissue holograms. It is found that the ensemble deep learning hologram-classifier can effectively adapt to optical aberration coming from dust on mirrors and optical lens aberrations such as the Airy-plaque-like rings out-turn from the lenses in the interferometer. The deep learning network effectively adapts to these irregularities during the training stage and performs well in the later recognition stage without prior optical background compensations. The method does not require an intact sample with a full outline shape of the specimens or the organs to understand the objects’ identities. It demonstrates a new paradigm in object identification by ensemble deep learning through a direct wavefront recognition technique.

show abstract

“…Most of these approaches are sensitive to positional shifts and deformations. The methods and the problems are described in detail by VanderLugt works in [1] and the articles in [2][3][4][5]. The hologram-classi er employed in this paper is EDL-IOHC in [6] which employs a modern deep learning approach.…”

Section: Introductionmentioning

confidence: 99%

Off-axis Holographic Interferometer with Ensemble Deep Learning for Biological Tissues Identification

Lam

Zhu

Buranasiri

2022

Preprint

View full text Add to dashboard Cite

This paper proposes a method with an off-axis interferometer and an ensemble deep learning (I-EDL) hologram-classifier to interpret noisy digital holograms captured from the tissues of flawed biological specimens. The holograms are captured by an interferometer which serves as a digital holographic scanner to scan the tissue with 3D information. A red laser beam penetrates the tissue of the specimen. It scans across the x-y directions to capture thousands of off-axis hologram samples for the training, testing, and recognizing the microstructure of the tissue and, hence, identifying the specimens' identity. The method achieves a high success rate of 99.60% in identifying the specimens through the tissue holograms. It is found that the ensemble deep learning hologram-classifier can effectively adapt to optical aberration coming from dust on mirrors and optical lenses aberration such as the Airy-plaque-like rings out-turn from the lenses in the interferometer. The deep learning network effectively adapts to these irregularities during the training stage and performs well in the later recognition stage without prior optical background compensations. The method does not require an intact sample with a full outline shape of the specimens or the organs to understand the objects' identities. It demonstrates a new paradigm in object identification by ensemble deep learning through a direct wavefront recognition technique.

show abstract

Robust recognition of partially occluded 3-D objects from computationally reconstructed hologram by using a spatial filtering scheme

Cited by 3 publications

References 12 publications

Review of holographic-based three-dimensional object recognition techniques [Invited]

Review of holographic-based three-dimensional object recognition techniques [Invited]

Off-Axis Holographic Interferometer with Ensemble Deep Learning for Biological Tissues Identification

Off-axis Holographic Interferometer with Ensemble Deep Learning for Biological Tissues Identification

Contact Info

Product

Resources

About