Inkyu Moon

Daegu Gyeongbuk Institute of Science and Technology | DGIST · Department of Robotics Engineering

Image‐based stain‐free elliptical cancer cell classification is very challenging due to interclass morphological similarity. Herein, the classification of three types of cancer cell lines (lung, breast, and skin) by feature‐based machine learning and image‐based deep learning with a convolutional neural network (CNN) is addressed. Digital holograph...

Cloud storage has become eminent, with an increasing amount of data being produced daily; this has led to substantial concerns related to privacy and unauthorized access. To secure privacy, users can protect their private data by uploading encrypted data to the cloud. Data encryption allows computations to be performed on encrypted data without the...

Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) are a class of Recurrent Neural Networks (RNN) suitable for sequential data processing. Bidirectional LSTM (BLSTM) enables a better understanding of context by learning the future time steps in a bidirectional manner. Moreover, GRU deploys reset and update gates in the hidden layer, whic...

A depth slice image that is computationally reconstructed from an integral imaging system consists of focused and out of focus areas. The unfocused areas affect three-dimensional (3D) image analyses and visualization including 3D object detection, extraction, and tracking. In this work, we present a deep learning integral imaging system that can re...

Digital holography can provide quantitative phase images related to the morphology and content of biological samples. After the numerical image reconstruction, the phase values are limited between -π and π; thus, discontinuity may occur due to the modulo 2π operation. We propose a new deep learning model that can automatically reconstruct unwrapped...

With the emergence of cloud computing, large amounts of private data are stored and processed in the cloud. On the other hand, data owners (users) may not want to reveal data information to cloud providers to protect their privacy. Therefore, users may upload encrypted data to the cloud or third-party platforms, such as Google Cloud, Amazon Web Ser...

Digital cryptosystems can provide perfect forward secrecy (PFS) for key exchange protocols based on the Diffie–Hellman (DH) scheme. However, key exchange algorithms are optimally designed only to encode small datasets, such as text and voice sets, which makes rapidly processing large-scale datasets difficult. In this paper, we propose new schemes t...

This paper proposes a new non-invasive, low-cost, and fully automated platform to quantitatively analyze dynamics of human-induced pluripotent stem cell-derived cardiomyocytes (hiPS-CMs) at the single-cell level by holographic image-based tracking for cardiotoxicity screening. A dense Farneback optical flow method and holographic imaging informatic...

Information security has become an intrinsic part of data communication. Cryptanalysis using deep learning–based methods to identify weaknesses in ciphers has not been thoroughly studied. Recently, long short-term memory (LSTM) networks have shown promising performance in sequential data processing by modeling the dependencies and data dynamics. Gi...

In this Plenary address paper, we overview recently published work for automated cell identification using 3D optical imaging in compact and field portable biophotonic sensors. Digital holographic microscopy systems and lensless pseudorandom phase encoding systems capture 3D information of biological cells and make highly accurate automated cell id...

This paper shows that deep learning can eliminate the superimposed twin-image noise in phase images of Gabor holographic setup. This is achieved by the conditional generative adversarial model (C-GAN), trained by input-output pairs of noisy phase images obtained from synthetic Gabor holography and the corresponding quantitative noise-free contrast-...

Human-induced pluripotent stem cell-derived cardiomyocytes (hiPS-CMs) beating can be efficiently characterized by time-lapse quantitative phase imaging (QPIs) obtained by digital holographic microscopy. Particularly, the CM's nucleus section can precisely reflect the associated rhythmic beating pattern of the CM suitable for subsequent beating patt...

We use quantitative phase digital holographic microscopy (QP-DHM) to image and quantify the beating movement of cardiomyocytes, derived from induced pluripotent stem cells (iPSCs), in control and drug-treated conditions. The development of an analysis algorithm has allowed extracting from the recorded quantitative phase signal (QPS) a set of severa...

Encrypted images obtained through double random phase-encoding (DRPE) occupy considerable storage space. We propose efficient compression schemes to reduce the size of the encrypted data. In the proposed schemes, two state-of-art compression methods of JPEG and JP2K are applied to the quantized encrypted phase images obtained by combining the DRPE...

We propose novel random phase key exchange schemes for image cryptography, which are complex sinusoidal waveform versions of the Diffie-Hellman (DH) key exchange algorithm. We demonstrate that the proposed schemes can be particularly helpful to establish a shared secret key in Fourier optics-based image cryptosystems since the problem of symmetric...

This paper introduces an efficient image-based verification approach that integrates double random phase encoding (DRPE) and chaotic dynamic mapping. The main objective is to propose a new DRPE-based image verification scheme by replacing random phase masks (RPM) with efficient chaotic phase masks (CPM) which are dependent on an input image. For ve...

Recent developments in 3D computational optical imaging such as digital holographic microscopy has ushered in a new era for biological research. Therefore, efficient and secure storage and retrieval of digital holograms is a challenging task for future cloud computing services. In this study, we propose a novel scheme to securely store and retrieve...

Digital propagation of an off-axis hologram can provide the quantitative phase-contrast image if the exact distance between the sensor plane (such as CCD) and the reconstruction plane is correctly provided. In this paper, we present a deep-learning convolutional neural network with a regression layer as the top layer to estimate the best reconstruc...

In this paper, a new integrated approach is proposed for authenticating digital color image. Here, a new technique, Poisson-Multinomial Distribution (PMD) is introduced for the first time in image processing. It is used for Photon Counting Imaging (PCI) which is integrated with Double Random Phase Encoding (DRPE) scheme in this system. The main goa...

This paper investigates the rhythm strip and parameters of synchronization of human induced pluripotent stem cell (iPS) derived cardiomyocytes. The synchronization is evaluated from quantitative phase images of beating cardiomyocytes which are obtained using the time-lapse digital holographic imaging method. By quantitatively monitoring the dry mas...

We present a new image-authentication algorithm based on binary-quantified double random phase encoding (DRPE) and a discrete cosine transformation (DCT)-domain watermarking scheme. The image is encrypted using a DRPE scheme, in which only the phase part of the encoded image is preserved. Then this phase image is quantified to become a binary image...

We propose methods to quantitatively calculate the fluctuation rate of red blood cells with nanometric axial and millisecond temporal sensitivity at the single-cell level by using time-lapse holographic cell imaging. For this quantitative analysis, cell membrane fluctuations (CMFs) were measured for RBCs stored at different storage times. Measureme...

We propose a new scheme to encrypt multiple images simultaneously using two-dimensional binary phase masks. Each of the original greyscale images is first decomposed into two pure phase-only images, which corresponds to the reverse process of an optical interference. Two phase-only images have random distributions of phases in the range from 0 to 2...

Disclosed is a method of measuring red blood cell membrane fluctuations based on dynamic cell parameters using a digital holographic microscope; the method including a step of modeling the three-dimensional images of red blood cells to be measured, and a step of measuring red blood cell membrane fluctuations based on the three-dimensional images. A...

Quantitative phase information obtained by digital holographic microscopy (DHM) can provide new insight into the functions and morphology of single red blood cells (RBCs). Since the functionality of a RBC is related to its three-dimensional (3-D) shape, quantitative 3-D geometric changes induced by storage time can help hematologists realize its op...

The encoding step in full-search fractal image compression is time intensive because a sequential search through a massive domain pool has to be executed to find the best-matched domain for every range block. To afford a fair encoding time, immaterial domain–range block comparisons should be prevented. In this paper, a new local binary feature rese...

In this paper, we present two models for automatically extracting red blood cells (RBCs) from RBCs holographic images based on a deep learning fully convolutional neural network (FCN) algorithm. The first model, called FCN-1, only uses the FCN algorithm to carry out RBCs prediction, whereas the second model, called FCN-2, combines the FCN approach...

We present unsupervised clustering methods for automatic grouping of human red blood cells (RBCs) extracted from RBC quantitative phase images obtained by digital holographic microscopy into three RBC clusters with regular shapes, including biconcave, stomatocyte, and sphero-echinocyte. We select some good features related to the RBC profile and mo...

In this paper, we proposed an image authentication method based on least significant bit (LSB) hiding and double random phase encoding (DRPE) technique. An image that needs to be authenticated is first encrypted using DRPE algorithm. All amplitude information in this encrypted image is discarded and the phase mask is reserved. Then, the phase image...

In recent years, many studies have focused on authentication of two-dimensional (2D) images using double random phase encryption techniques. However, there has been little research on three-dimensional (3D) imaging systems, such as integral imaging, for 3D image authentication. We propose a 3D image authentication scheme based on a double random ph...

Background: Red blood cells collected in citrate-phosphate-dextrose can be stored for up to 42 days at 4 °C in saline-adenine-glucose-mannitol additive solution. During this controlled, but nevertheless artificial, ex vivo ageing, red blood cells accumulate lesions that can be reversible or irreversible upon transfusion. The aim of the present stu...

Digital holographic microscopy can provide quantitative phase images (QPIs) of 3D profile of red blood cell (RBC) with nanometer accuracy. In this paper we propose applying k-means clustering method to cluster RBCs into two groups of young and old RBCs by using a four-dimensional feature vector. The features are RBC thickness average, surface area-...

Digital holographic microscopy is an ideal tool for 3-D cell imaging and characterization. It provides a host of cell parameters based on cell morphology and its temporal dynamics or time variation. These parameters can be used to study and quantify cell growth and cell physiology. When coupled with classification algorithms, this technique can als...

The classification of erythrocytes plays an important role in the field of hematological diagnosis, specifically blood disorders. Since the biconcave shape of red blood cell (RBC) is altered during the different stages of hematological disorders, we believe that the three-dimensional (3-D) morphological features of erythrocyte provide better classi...

In this paper, we evaluate lossless and lossy compression techniques to compress quantitative phase images of red blood cells (RBCs) obtained by an off-axis digital holographic microscopy (DHM). The RBC phase images are numerically reconstructed from their digital holograms and are stored in 16-bit unsigned integer format. In the case of lossless c...

A method of extending signal reception region is proposed and experimentally demonstrated for an infrastructure-to-car communications based on a visible light communication (VLC) link. To confirm the necessity of elevation angle control for a received fixed at a car, we calculate the change of received optical signal power according to the position...

We present a new scheme for optical encryption of a binary image. In our method, the original binary data page is first divided into two identical pages. In each data page, the "on" and "off' pixels are represented by two discrete phases that are 90 apart. The first page corresponds to the phase conjugation of the second page, and vice versa. In ad...

Recently, double random phase encoding (DRPE) has been integrated with the photon counting (PC) imaging technique for the purpose of secure image authentication. In this scheme, the same key should be securely distributed and shared between the sender and receiver, but this is one of the most vexing problems of symmetric cryptosystems. In this stud...

We present methods that automatically select a linear or nonlinear classifier for red blood cell (RBC) classification by analyzing the equality of the covariance matrices in Gabor-filtered holographic images. First, the phase images of the RBCs are numerically reconstructed from their holograms, which are recorded using off-axis digital holographic...

In this paper, we present an overview of the avalanche and bit independence characteristics of double random phase encoding (DRPE) scheme in the virtual optical domains. DRPE apparently demonstrates outstanding bit independence property in both the Fourier and Fresnel domains. Experimental results validate that the DRPE performance in Fresnel domai...

We report the effect of interferences on visible light car-to-car communication system. The interferences from floor reflections and fluorescent lamps are taken into account for indoor car-to-car visible light communication (VLC) systems. The system is composed of a white LED lamp as a VLC transmitter and a photo-receiver with an appropriate optica...

We propose an automated calibration method with a closed-form solution for three-dimensional (3-D) integral imaging with randomly distributed sensors of unknown positions in 3-D space. In the method presented, a robust feature-detection algorithm is applied to the elemental image set, and the matching features are used to derive the relations betwe...

Red blood cell (RBC) phase images that are numerically reconstructed by digital holographic microscopy (DHM) can describe the cell structure and dynamics information beneficial for a quantitative analysis of RBCs. However, RBCs investigated with time-lapse DHM undergo temporal displacements when their membranes are loosely attached to the substrate...

In this Invited Paper, we present an overview of our reported work on 3D sensing and imaging applied to automated cell identification. The sensing and imaging methods include digital holographic imaging, interferometric systems, and integral imaging.

Quantitative phase information obtained by digital holographic microscopy (DHM) can provide new insight into the functions and morphology of single red blood cells (RBCs). Since the functionality of a RBC is related to its three-dimensional (3-D) shape, quantitative 3-D geometric changes induced by storage time can help hematologists realize its op...

In this paper we overview a method to automatically count morphologically normal red blood cells (RBCs) by using off-axis digital holographic microscopy and statistical methods. Three kinds of RBC are used as training and testing data. All of the RBC phase images are obtained with digital holographic microscopy (DHM) that is robust to transparent o...

This paper presents an overview of research work and some novel strategies and results on using data fusion in 3-D imaging when using multiple information sources. We examine a variety of approaches and applications such as 3-D imaging integrated with polarimetric and multispectral imaging, low levels of photon flux for photon-counting 3-D imaging,...

In this paper, we present an overview of a color image authentication scheme via multispectral photon-counting (MPCI) double random phase encoding (DRPE). The MPCI makes image sparse distributed and DRPE lets image be stationary white noise which make intruder attacks difficult. In this method, the original RGB image is down-sampled into Bayer imag...

Conventionally, the 3D object reconstructed from computational integral imaging technique consists of focused and off-focused areas. The reconstructed object with off-focused points will affect the high-level image analysis such as object classification, recognition, and tracking. Therefore, it is necessary to develop a method to remove the off-foc...

Compounds tested during drug development may have adverse effects on the heart; therefore all new chemical entities have to undergo extensive preclinical assessment for cardiac liability. Conventional intensity-based imaging techniques are not robust enough to provide detailed information for cell structure and the captured images result in low-con...

Counting morphologically normal cells in human red blood cells (RBCs) is extremely beneficial in the health care field. We propose a three-dimensional (3-D) classification method of automatically determining the morphologically normal RBCs in the phase image of multiple human RBCs that are obtained by off-axis digital holographic microscopy (DHM)....

Clustering methods are very useful in many fields such as data mining, classification, and object recognition. Both the supervised and unsupervised grouping approaches can classify a series of sample data with a predefined or automatically assigned cluster number. However, there is no constraint on the number of elements for each cluster. Numbers o...

In this paper, we present a graphics processing unit (GPU)-based matching technique for the purpose of fast feature matching between different images. The scale invariant feature transform algorithm developed by Lowe for various feature matching applications, such as stereo vision and object recognition, is computationally intensive. To address thi...

We propose a three-dimensional (3D) object recognition approach via computational integral imaging and scale invariant feature transform (SIFT) that can be invariance to object changes in illumination, scale, rotation and affine. Usually, the matching between features extracted in reference object and that in computationally reconstructed image sho...

This paper provides an overview of a colorful photon-counting integral imaging system using Bayer elemental images for 3D visualization of photon limited scenes. The color image sensor with a format of Bayer color filter array, i.e., a red, a green, or a blue filter in a repeating pattern, captures elemental image set of a photon limited three-dime...

In this paper, we propose a new method for the occluded object visualization using multiple Kinect sensors. The quality of occluded object reconstructed from conventional reconstruction method with elemental images captured by common camera arrays in integral imaging is usually degraded due to the existence of occlusion object in the 3D space which...

A novel error correction method is proposed for volume holographic memory systems. In this method the information of two adjacent binary bits is recorded in the space between the two bits, which is used to correct the errors in the data bits. The new method is compared with (15, 5) Reed—Solomon code using the same redundancy of 200% as ours. It is...

In this paper, we propose a new method for color image-based authentication that combines multispectral photon-counting imaging (MPCI) and double random phase encoding (DRPE) schemes. The sparsely distributed information from MPCI and the stationary white noise signal from DRPE make intruder attacks difficult. In this authentication method, the...

In this work, we evaluate the avalanche effect and bit independence properties of the double random phase encoding (DRPE) algorithm in the Fourier and Fresnel domains. Experimental results show that DRPE has excellent bit independence characteristics in both the Fourier and Fresnel domains. However, DRPE achieves better avalanche effect results in...

The reconstruction of multiple depth images with a ray back-propagation algorithm in three-dimensional (3D) computational integral imaging is computationally burdensome. Further, a reconstructed depth image consists of a focus and an off-focus area. Focus areas are 3D points on the surface of an object that are located at the reconstructed depth, w...

We propose a fast double random phase encoding (DRPE) algorithm using a graphics processing unit (GPU)-based stream-processing model. A performance analysis of the accelerated DRPE implementation that employs the Compute Unified Device Architecture programming environment is presented. We show that the proposed methodology executed on a GPU can dra...

This paper provides an overview of a method for a compression of elemental images in the photon counting three-dimensional (3D) integral imaging.

Quantitative phase (QP) images of red blood cells (RBCs), which are obtained by off-axis digital holographic microscopy, can provide quantitative information about three-dimensional (3D) morphology of human RBCs and the characteristic properties such as mean corpuscular hemoglobin (MCH) and MCH surface density (MCHSD). In this paper, we investigate...