The use of multi-view images acquired by a 360-degree camera can reconstruct a 3D space with a wide area. There are 3D reconstruction methods from equirectangular images based on NeRF and 3DGS, as well as Novel View Synthesis (NVS) methods. On the other hand, it is necessary to overcome the large distortion caused by the projection model of a 360-degree camera when equirectangular images are used. In 3DGS-based methods, the large distortion of the 360-degree camera model generates extremely large 3D Gaussians, resulting in poor rendering accuracy. We propose ErpGS, which is Omnidirectional GS based on 3DGS to realize NVS addressing the problems. ErpGS introduce some rendering accuracy improvement techniques: geometric regularization, scale regularization, and distortion-aware weights and a mask to suppress the effects of obstacles in equirectangular images. Through experiments on public datasets, we demonstrate that ErpGS can render novel view images more accurately than conventional methods.

Semantic segmentation is a fundamental task in medical image analysis and autonomous driving and has a problem with the high cost of annotating the labels required in training. To address this problem, semantic segmentation methods based on semi-supervised learning with a small number of labeled data have been proposed. For example, one approach is to train a semantic segmentation model using images with annotated labels and pseudo labels. In this approach, the accuracy of the semantic segmentation model depends on the quality of the pseudo labels, and the quality of the pseudo labels depends on the performance of the model to be trained and the amount of data with annotated labels. In this paper, we generate pseudo labels using zero-shot annotation with the Segment Anything Model (SAM) and Contrastive Language-Image Pretraining (CLIP), improve the accuracy of the pseudo labels using the Unified Dual-Stream Perturbations Approach (UniMatch), and use them as enhanced labels to train a semantic segmentation model. The effectiveness of the proposed method is demonstrated through the experiments using the public datasets: PASCAL and MS COCO.

Gaussian Splatting (GS) has gained attention as a fast and effective method for novel view synthesis. It has also been applied to 3D reconstruction using multi-view images and can achieve fast and accurate 3D reconstruction. However, GS assumes that the input contains a large number of multi-view images, and therefore, the reconstruction accuracy significantly decreases when only a limited number of input images are available. One of the main reasons is the insufficient number of 3D points in the sparse point cloud obtained through Structure from Motion (SfM), which results in a poor initialization for optimizing the Gaussian primitives. We propose a new 3D reconstruction method, called Sparse2DGS, to enhance 2DGS in reconstructing objects using only three images. Sparse2DGS employs DUSt3R, a fundamental model for stereo images, along with COLMAP MVS to generate highly accurate and dense 3D point clouds, which are then used to initialize 2D Gaussians. Through experiments on the DTU dataset, we show that Sparse2DGS can accurately reconstruct the 3D shapes of objects using just three images.

Demographic bias is one of the major challenges for face recognition systems. The majority of existing studies on demographic biases are heavily dependent on specific demographic groups or demographic classifier, making it difficult to address performance for unrecognised groups. This paper introduces "LabellessFace", a novel framework that improves demographic bias in face recognition without requiring demographic group labeling typically required for fairness considerations. We propose a novel fairness enhancement metric called the class favoritism level, which assesses the extent of favoritism towards specific classes across the dataset. Leveraging this metric, we introduce the fair class margin penalty, an extension of existing margin-based metric learning. This method dynamically adjusts learning parameters based on class favoritism levels, promoting fairness across all attributes. By treating each class as an individual in facial recognition systems, we facilitate learning that minimizes biases in authentication accuracy among individuals. Comprehensive experiments have demonstrated that our proposed method is effective for enhancing fairness while maintaining authentication accuracy.

In this paper, we propose a method to refine depth maps estimated by Multi-View Stereo (MVS) with Neural Radiance Field (NeRF) optimization to estimate depth maps from multi-view images with high accuracy. MVS estimates the depths on object surfaces with high accuracy, and NeRF estimates the depths at object boundaries with high accuracy. The key ideas of the proposed method are (i) to combine MVS and NeRF to utilize the advantages of both in depth map estimation, (ii) not to require any training process, therefore no training dataset and ground truth are required, and (iii) to use NeRF for depth map refinement. Through a set of experiments using the Redwood-3dscan dataset, we demonstrate the effectiveness of the proposed method compared to conventional depth map estimation methods.

In this paper, we propose a method to improve the accuracy of depth map estimation from multi-view images using Neural Radiance Fields (NeRF). A depth map can be estimated from multi-view images using Multi-View Stereo (MVS), which can estimates the depths inside objects with high accuracy, while NeRF can estimate the depths at object boundaries with high accuracy. We consider using both advantages to improve the accuracy of depth map estimation from multi-view images and making NeRF as a refinement module. Through a set of experiments using a public MVS dataset, we demonstrate the effectiveness of the proposed method compared to conventional depth map estimation methods.

Abstract PatchMatch Stereo is a method for generating a depth map from stereo images by repeating spatial propagation and view propagation. The concept of PatchMatch Stereo can be easily extended to Multi-View Stereo (MVS). In this paper, we present PatchMatch Multi-View Stereo (PM-MVS), which is a highly accurate 3D reconstruction method that can be used in various environments. Three techniques are introduced to PM-MVS: (i) matching score evaluation, (ii) viewpoint selection, and (iii) outlier filtering. The combination of normalized cross-correlation with bilateral weights and geometric consistency between viewpoints is used to improve the estimation accuracy of depth and normal maps at object boundaries and poor-texture regions. For each pixel, viewpoints used for stereo matching are carefully selected in order to improve robustness against disturbances such as occlusion, noise, blur, and distortion. Outliers are removed from reconstructed 3D point clouds by a weighted median filter and consistency-based filters assuming multi-view geometry. Through a set of experiments using public multi-view image datasets, we demonstrate that the proposed method exhibits efficient performance compared with conventional methods.

In this paper, we improve the performance of CNN-based fingerprint recognition without increasing the size of CNN, while training CNN on a limited number of data in public databases to guarantee reproducibility. We propose a Texture-Minutiae Network (TMNet) for extracting texture and minutia features based on ResNet-34. We introduce multiple attention mechanisms to TMNet in order to improve performance on fingerprint recognition without increasing the size of the network. Through experiments of performance evaluation using FVC2004 DB1, DB2, and DB3, we demonstrate that the proposed method is more effective than the conventional methods for fingerprint recognition.

In this paper, we propose a robust and accurate image correspondence method by combining SuperPoint + SuperGlue (SP+SG) and Local feature matching with TRansformers (LoFTR). The proposed method finds corresponding points on regions with rich texture by SP+SG and those with poor texture by LoFTR since SP+SG exhibits high localization accuracy of image correspondence and LoFTR exhibits high robustness against poor texture regions. The proposed method can be used for image correspondence in SfM to not only improve the estimation accuracy of camera parameters in SfM, but also to improve the reconstruction accuracy and expand the reconstruction area in MVS. Through experiments on the ETH3D dataset, we demonstrate that the proposed method achieves more accurate 3D reconstruction than conventional methods, and also show the impact of image correspondence accuracy in SfM on multi-view 3D reconstruction.

Remote sensing using Synthetic Aperture Radar (SAR) is an indispensable technology for effective disaster management, owing to its large observation area, cloud penetrating ability and its independence from sunlight, which allow for quick observation of large disaster affected areas disregarding weather or time of the day. In particular, 3D measurement from SAR images could contribute a better understanding of the affected area and speed up decision making. Most methods require prior knowledge of the scene such as ground control points to achieve a reasonable level of 3D measurement accuracy, resulting in losing the advantage of quick observation. In this paper, we propose an accurate 3D measurement method from SAR images based on the principle of stereo vision without any prior knowledge of the scene. We demonstrate the effectiveness of our method compared with the conventional method through a set of experiments using an airborne SAR image dataset.

Although most fingerprint matching methods utilize minutia points and/or texture of fingerprint images as fingerprint features, the frequency spectrum is also a useful feature since a fingerprint is composed of ridge patterns with its inherent frequency band. We propose a novel CNN-based method for extracting fingerprint features from texture, minutiae, and frequency spectrum. In order to extract effective texture features from local regions around the minutiae, the minutia attention module is introduced to the proposed method. We also propose new data augmentation methods, which takes into account the characteristics of fingerprint images to increase the number of images during training since we use only a public dataset in training, which includes a few fingerprint classes. Through a set of experiments using FVC2004 DB1 and DB2, we demonstrated that the proposed method exhibits the efficient performance on fingerprint verification compared with a commercial fingerprint matching software and the conventional method.

Synthetic Aperture Radar (SAR) has been used to acquire images for analyzing geometrical properties of the ground surface. In this paper, we propose a method of detecting seismic ground deformation from the airborne SAR images with parameter optimization. The optimal parameters in ground deformation detection are estimated so as to minimize the reprojection error in the radar projection model based on the idea of bundle adjustment. We demonstrate the effectiveness of our method in detecting seismic ground deformation through the experiment using the airborne SAR images taken before and after the Kumamoto Earthquake in 2016.

BACKGROUND: The combination of systematic evolution of ligands by exponential enrichment (SELEX) and deep sequencing is termed high-throughput (HT)-SELEX, which enables searching aptamer candidates from a massive amount of oligonucleotide sequences. A clustering method is an important procedure to identify sequence groups including aptamer candidates for evaluation with experimental analysis. In general, aptamer includes a specific target binding region, which is necessary for binding to the target molecules. The length of the target binding region varies depending on the target molecules and/or binding styles. Currently available clustering methods for HT-SELEX only estimate clusters based on the similarity of full-length sequences or limited length of motifs as target binding regions. Hence, a clustering method considering the target binding region with different lengths is required. Moreover, to handle such huge data and to save sequencing cost, a clustering method with fast calculation from a single round of HT-SELEX data, not multiple rounds, is also preferred. RESULTS: We developed fast string-based clustering (FSBC) for HT-SELEX data. FSBC was designed to estimate clusters by searching various lengths of over-represented strings as target binding regions. FSBC was also designed for fast calculation with search space reduction from a single round, typically the final round, of HT-SELEX data considering imbalanced nucleobases of the aptamer selection process. The calculation time and clustering accuracy of FSBC were compared with those of four conventional clustering methods, FASTAptamer, AptaCluster, APTANI, and AptaTRACE, using HT-SELEX data (>15 million oligonucleotide sequences). FSBC, AptaCluster, and AptaTRACE could complete the clustering for all sequence data, and FSBC and AptaTRACE performed higher clustering accuracy. FSBC showed the highest clustering accuracy and had the second fastest calculation speed among all methods compared. CONCLUSION: FSBC is applicable to a large HT-SELEX dataset, which can facilitate the accurate identification of groups including aptamer candidates. AVAILABILITY OF DATA AND MATERIALS: FSBC is available at http://www.aoki.ecei.tohoku.ac.jp/fsbc/.

A clustering method for high-throughput sequencing with SELEX pools (HT-SELEX) is crucial for selecting different types of aptamer candidates. The fast and accurate clustering method is indispensable for an enormous sequence data produced by HT-SELSEX. We have already developed a fast motif-based clustering (FMBC) method for HT-SELEX data implemented by R language. FMBC exhibited high accuracy of sequence clustering compared with conventional methods, while the processing time of FMBC is longer than AptaCluster. This paper proposes the parallel implementation of FMBC using Python with multi-threading to improve the performance of FMBC. Experimental evaluation using the NCBI SRA data of SRR3279661 from BioProject PRJNA315881 demonstrated that parallel FMBC exhibited higher accuracy of clustering and shorter processing time than conventional methods.

We introduce a learning based method for extracting distinctive features on video objects. Based on the extracted features, we are able to derive dense correspondences between the object in the current video frame and the reference template, and then use the correspondences to identify the grasping points on the object. We train a deep-learning model to predict dense feature maps using the training data collected via solving simultaneous localization and mapping (SLAM). Further, a new feature-aggregation technique based on the optical flow of consecutive frames is applied to the integration of multiple feature maps for alleviating uncertainties. We also use the optical flow information to assess the reliability of feature matching. The experimental results show that our approach effectively reduces unreliable correspondences and thus improves the matching accuracy.

Observation of seismic ground deformation is one of the fundamental topics in remote sensing. A Synthetic Aperture Radar (SAR) has been used to obtain images representing geometrical properties of the ground surface. SAR images can be taken in nearly all weather conditions and in nearly all time. This paper proposes a ground deformation observation method using image correspondence matching, which employs phase-only correlation to estimate displacement between two SAR intensity images with sub-pixel accuracy. Through experiments using airborne SAR intensity images of the Kumamoto Earthquake, we demonstrate that the proposed method exhibits the efficient performance in observing seismic ground deformation.

This paper proposes an outlier and artifact removal method for multiview stereo. The proposed method introduces the three filters, which check (i) consistency among depth maps and their visibility, (ii) left-right consistency and (iii) consistency between the depth map and color intensity, respectively. The proposed method removes outliers and artifacts from depth maps generated by PatchMatch Multi-View Stereo. We demonstrate that the proposed method exhibits the efficient performance on 3D reconstruction compared with conventional methods through a set of experiments using public datasets and under practical situations.

Elevation measurement using Synthetic Aperture Radar (SAR) is one of fundamental techniques in remote sensing. Interferometric SAR (InSAR), which is the most popular technique of elevation measurement using SAR, uses the phase differences between the signals received by SAR antennas. InSAR requires Ground Control Points (GCPs) to measure absolute elevation values, although GCPs cannot be obtained in emergency situations. In addition, rapid observation, i.e., on-board processing, is expected in emergency situations. Addressing the above problem, this paper proposes an elevation measurement method using interferometry and radargrametry from single-pass airborne SAR images. Through the experiments, we demonstrate that the proposed method exhibits efficient performance in elevation measurement.

Elevation measurement using Synthetic Aperture Radar (SAR) is one of fundamental techniques in remote sensing. The cross-track Interferometric SAR (InSAR), which is the most popular technique of elevation measurement using SAR, uses the phase differences between the signals received by SAR antennas. Single-pass InSAR can be achieved by a single platform with two antennas. InSAR requires Ground Control Points (GCPs) to measure absolute elevation values, although it is a time-consuming and cost-intensive task to acquire GCPs. Addressing the above problem, this paper proposes an elevation measurement method using two SAR intensity images taken by a single-pass airborne SAR system. A projection model is derived to apply the principle of stereo vision to elevation measurement from SAR images. Phase-Only Correlation is employed to obtain accurate correspondence between two SAR images having below 1-pixel disparities. Through the experiment using SAR images, we demonstrate that the proposed method exhibits efficient performance in elevation measurement.

A lot of feature-based correspondence matching methods have been proposed in the field of computer vision, image processing and pattern recognition. These methods are also effective for biometric recognition. In general, in the case of feature-based matching methods, the matching score is calculated as a ratio between the number of feature points and corresponding points. These methods need to normalize image deformation by fitting an image transformation model to images according to the correspondence between images. Then, the matching score is calculated from the normalized images so as to take into consideration image deformation. On the other hand, this paper proposes a score calculation method which calculates a matching score from positional information of corresponding point pairs. The proposed method does not need any deformation model defined for each biometric trait to handle image deformation. The combination of the matching scores defined by the number of corresponding points and the positional information improves the performance of biometric recognition algorithms, since these scores play a complementary role in decision. Through a set of experiments using a palmprint image database, we demonstrate that the proposed method exhibits efficient performance for biometric recognition.

Elevation measurement using Synthetic Aperture Radar (SAR) is one of crucial applications in remote sensing, since the use of SAR in elevation measurement makes it possible to measure a wide range of planar area and not to set any monitoring device on the ground. Most of conventional methods need Ground Control Points (GCPs) to achieve accurate 3D measurement, where GCP acquisition is a time-consuming and cost-intensive task. Addressing the above problem, this paper proposes a novel stereo radargrammetry method using airborne SAR images without GCP. We define a new sensor model with only parameters provided in SAR image acquisition which derives from the principle of stereo vision. We employ bundle adjustment so as to minimize reprojection errors in 3D measurement, since the proposed sensor model is based on stereo vision. We also employ Phase-Only Correlation (POC), which is a sub-pixel image matching method using phase information obtained by Discrete Fourier Transform (DFT) of given images, to obtain dense and accurate correspondence between two SAR images. Through an experiment using SAR images, we demonstrate that the proposed method exhibits efficient performance of radargrammetry compared with Interferommetric SAR (InSAR).

This paper proposes a sequential online 3D reconstruction system using dense stereo matching for a non-expert user, which can sequentially reconstruct accurate and dense 3D point clouds when the new image is captured. The proposed system is based on a novel processing pipeline of sequential online 3D reconstruction with two key techniques: (i) camera parameter estimation of Structure from Motion (SfM) and (ii) dense stereo correspondence matching using Phase-Only Correlation (POC). The user can confirm the reconstruction result and add supplementary images to the system in order to reconstruct a complete 3D model as needed. Through a set of experiments, the proposed system exhibits efficient performance in terms of reconstruction accuracy and computation time compared with the conventional system.

This paper presents a multi-finger knuckle recognition system and proposes a finger knuckle region extraction algorithm from a video sequence. The use of video sequences makes it possible to achieve stable and robust finger knuckle region extraction, since the optimal image frame can be selected from a set of image frames to extract a region to be matched for each finger. Through a set of experiments, we demonstrate that the extraction rates of the proposed algorithm are 96.4%, 99.4%, 97.6% and 96.4% for index, middle, ring and little fingers, respectively, which are acceptable in practice. The result indicates that four fingers can be used for person authentication in most cases. We also demonstrate that the use of multiple finger knuckle regions exhibits efficient performance for person authentication.

This paper proposes a 3D reconstruction algorithm for urban environments from video sequences taken by an in-vehicle fisheye camera. The proposed algorithm employs (i) fisheye camera calibration to apply the general Structure from Motion to video sequences taken by the fisheye camera and (ii) accurate, dense and robust feature point tracking using phase-based correspondence matching. Experimental evaluation using the video sequence taken by the in-vehicle fisheye camera demonstrates that the proposed algorithm exhibits efficient performance of 3D reconstruction compared with the laser measurement system.

Reconstructing occluded regions of the object is to automatically detect the occluded regions and background in the image and reconstruct these regions using image interpolation. This paper proposes a novel occluded region reconstruction method using Fast Weighted Principal Component Analysis (FW-PCA). The computation time of the weighted PCA can be reduced by using only the effective regions when calculating the principal component scores. The occluded regions are accurately detected by recursively updating the weight for each pixel in the image using FW-PCA. Then, the occluded regions can be reconstructed using the final weight. Thorough a set of experiments, we demonstrate that the proposed method exhibits higher performance than the conventional method.

This paper proposes an accurate, dense and robust wide-baseline stereo correspondence matching method combining ASIFT (Affine-SIFT) and POC (Phase-Only Correlation). ASIFT-based matching is robust against perspective deformation of the stereo images, while the corresponding points are sparse. POC-based matching can find dense correspondence, while the corresponding points are not reliable in the case of the wide-baseline stereo. The complementary use of ASIFT and POC makes it possible to find accurate and dense stereo correspondence regardless of the length of camera baseline. Through a set of experiments, we demonstrate that the proposed method exhibits efficient performance compared with the conventional methods. We also apply the proposed method to 3D reconstruction from multi-view images.

This paper proposes a Graphics Processing Unit (GPU) implementation of the stereo correspondence matching using Phase-Only Correlation (POC). The use of high-accuracy stereo correspondence matching based on POC makes it possible to measure accurate 3D shape of the object using stereo vision, while the drawback of POC-based approach is its high computational cost. Addressing this problem, we propose a GPU implementation of POC-based correspondence matching. Through a set of experiments using a variety of GPUs, we demonstrate that the proposed implementation is high-speed and high-efficiency compared with the CPU implementation. We also apply the proposed approach to a real-time 3D measurement system.

This paper proposes a 2D face recognition algorithm using phase-based correspondence matching. The phase information obtained from 2D DFT (Discrete Fourier Transform) of images contains important information of image representation. The phase-based image matching is successfully applied to sub-pixel image registration tasks for computer vision applications and image recognition tasks for biometric authentication applications. Hierarchical block matching using phase information, i.e, phase-based correspondence matching, can find the corresponding points on the input image from the reference points on the registered image with sub-pixel accuracy. For face recognition, the phase-based correspondence matching is useful for minute change of texture, such as facial expression change, illumination change, etc. Experimental evaluation using the CSU Face Identification Evaluation System with the FERET database demonstrates efficient recognition performance of the proposed algorithm compared with the conventional face recognition algorithms.

Image inpainting is a technique for estimating missing pixel values in an image by using the pixel value information obtained from neighbor pixels of a missing pixel or the prior knowledge derived from learning the object class. In this paper, we propose a fast and accurate image inpainting method using similarity of the subspace. The proposed method generates the subspace from many images related to the object class in the learning step and estimates the missing pixel values of the input image belonging to the same object class so as to maximize the similarity between the input image and the subspace in the inpainting step. Through a set of experiments, we demonstrate that the proposed method exhibits excellent performance in terms of both inpainting accuracy and computation time compared with conventional algorithms.

This paper proposes a high-accuracy image correction method using SIFT (Scale-Invariant Feature Transform) and POC (Phase-Only Correlation) for multi-projector display. The accurate correspondence between the projector and camera images is required to achieve seamless imagery in a multiprojector display. The conventional methods need to project and take special light patterns on a screen many times to obtain the correspondence. On the other hand, the proposed method needs to take only one snapshot of ordinary images so as to realize real-time geometric correction of projector images. Through a set of experiments, we demonstrate that the proposed method is effective for practical use of multi-projector display compared with the conventional methods.

This paper proposes a multi-stage scale estimation algorithm using phase-based correspondence matching for electron microscope images. Consider a sequence of microscope images of the same target object, where the image magnification is gradually increased so that the final image has a very large scale factor S (e.g., S=1,000) with respect to the initial image. The problem considered in this paper is to estimate the overall scale factor S of the given image sequence. The proposed scale estimation technique provides a new methodology for high-accuracy magnification calibration of electron microscopes. Experimental evaluation using Mandelbrot images as precisely scale-controlled image sequence shows that the proposed method can estimate the scale factor S=1,000 with approximately 0.1%-scale error. This paper also describes an application of the proposed algorithm to the magnification calibration of an actual STEM (Scanning Transmission Electron Microscope).

When a cellular phone is lost or stolen, it may be used improperly or the personal information may be stolen from it by a malicious user. Biometric authentication such as palm-print recognition is the strongest of the personal authentication technologies designed to prevent such misuse. Ito et al. proposed several palmprint recognition schemes using correspondence matching based on the phase-only correlation among various schemes. However, these schemes require a palmprint image to be captured with the hand touching the dedicated device, while palmprint images must be captured without such physical contact when using cellular phones. Thus these schemes cannot be applied to cellular phones since there are large positioning gaps and large differences in brightness and distortion between the images. Furthermore, they are not implemented in the cellular phone and their performances are not evaluated either.

Palmprint images taken from a camera are distorted due to movement of a hand and fingers. To achieve reliable palmprint recognition, it is necessary to employ a recognition algorithm dealing with nonlinear distortion, while the conventional algorithms only consider the rigid body transformation between palmprint images. This paper proposes a palmprint recognition algorithm using phase-based correspondence matching. In order to handle nonlinear distortion, the proposed algorithm (i) finds corresponding points between two images using phase-based correspondence matching and (ii) evaluates a similarity between local image blocks around the corresponding points. Experimental evaluation using a palmprint image database demonstrates efficient recognition performance of the proposed algorithm compared with conventional algorithms.

High-accuracy image registration is an important fundamental task in many fields, such as image sensing, image/video processing, computer vision, etc. In order to evaluate accuracy of image registration algorithms, the reference images transformed with known parameters have to be used. Reference images taken by a camera may include human errors, while reference images generated by a computer may require pixel interpolation in the process. To address these problems, this paper proposes a performance evaluation method using the Mandelbrot set which is one of the famous fractals. Experimental evaluation shows effectiveness of the proposed method.

This paper proposes a practical palmprint recognition algorithm using two-dimensional (2D) phase information. The proposed algorithm (i) reduces the registered data size by registering quantized phase information and (ii) deals with nonlinear distortion between palmprint images by local block matching. Experimental evaluation using palmprint image databases clearly demonstrates efficient recognition performance of the proposed algorithm compared with the conventional palmprint recognition algorithms.

This paper proposes an efficient dental radiograph registration algorithm using Phase-Only Correlation (POC). The use of phase components in 2D (two-dimensional) discrete Fourier transforms of dental radiograph images makes it possible to achieve highly robust image registration and recognition. The proposed algorithm finds correspondence points between two images using the sub-pixel correspondence search using POC and corrects nonlinear distortion based on the Thin-Plate Spline (TPS) model. Experimental evaluation using a dental radiograph database indicates that the proposed algorithm exhibits efficient recognition performance even for distorted radiographs.

An integrated and effective metal artifact reduction method named Metal Erasing (ME) especially suited to dental applications is proposed. Layout of metals is identified as metal-only tomogram, using its characteristics of X-ray opacity and simple image processing technique of binarization together with backward projection. Metal-only sinogram is calculated by forward projection of the metal-only tomogram, and identifies corrupted areas on the original sinogram. The areas are then replaced by interpolation, and filtered back projection (FBP) produces a tomogram without figures of metals. The metals can be reproduced by overlaying already obtained metal-only tomogram utilizing linear characteristics of FBP. It is expected that the ME method can be incorporated into commercial CT scanners easily with reasonable computational overhead.

This paper presents an efficient algorithm for iris recognition using phase-based image matching--an image matching technique using phase components in 2D Discrete Fourier Transforms (DFTs) of given images. Experimental evaluation using CASIA iris image databases (versions 1.0 and 2.0) and Iris Challenge Evaluation (ICE) 2005 database clearly demonstrates that the use of phase components of iris images makes possible to achieve highly accurate iris recognition with a simple matching algorithm. This paper also discusses major implementation issues of our algorithm. In order to reduce the size of iris data and to prevent the visibility of iris images, we introduce the idea of 2D Fourier Phase Code (FPC) for representing iris information. The 2D FPC is particularly useful for implementing compact iris recognition devices using state-of-the-art Digital Signal Processing (DSP) technology.

Dental radiographs have been used for the accurate assessment and treatment of dental diseases. For an accurate diagnosis, the complete geometric registration between radiographs is required. The perspective projection between two radiographs may be observed, even if they are taken from the same oral regions of the subject. This paper presents an efficient dental radiograph registration algorithm using Phase-Only Correlation (POC) function. The use of phase components in 2D (two-dimensional) discrete Fourier transforms of dental radiograph images makes possible to achieve highly robust image registration and recognition. Experimental evaluation using a dental radiograph database indicates that the proposed algorithm exhibits efficient recognition performance even for distorted radiographs.

A major approach for palmprint recognition today is to extract feature vectors corresponding to individual palmprint images and to perform palmprint matching based on some distance metrics. One of the difficult problems in feature-based recognition is that the matching performance is significantly influenced by many parameters in feature extraction process, which may vary depending on environmental factors of image acquisition. This paper presents a palmprint recognition algorithm using phase-based image matching. The use of phase components in 2D (two-dimensional) discrete Fourier transforms of palmprint images makes possible to achieve highly robust palmprint recognition. Experimental evaluation using a palmprint image database clearly demonstrates an efficient matching performance of the proposed algorithm.

This paper presents an implementation of iris recognition algorithm using phase-based image matching-an image matching technique using phase components in 2D discrete Fourier transforms (DFTs) of given images. Our experimental observation clearly shows that the use of phase components of iris images makes possible to achieve highly accurate iris recognition even for low-quality iris images. In this paper, we consider the problem of designing a compact phase-based iris recognition algorithm especially suitable for hardware implementation. We also present prototype implementation of an iris recognition system based on the proposed algorithm. The prototype system fully utilizes state-of-the-art DSP (digital signal processor) technology to achieve real-time iris recognition capability within a compact hardware module.

A major approach for fingerprint recognition today is to extract minutiae from fingerprint images and to perform fingerprint matching based on the number of corresponding minutiae pairings. One of the most difficult problems in fingerprint recognition has been that the recognition performance is significantly influenced by fingertip surface condition, which may vary depending on environmental or personal causes. Addressing this problem, this paper presents a fingerprint recognition algorithm using phase-based image matching. The use of phase components in 2D (two-dimensional) discrete Fourier transforms of fingerprint images makes possible to achieve highly robust fingerprint recognition for low-quality fingerprints. Experimental evaluation using a set of fingerprint images captured from fingertips with difficult conditions (e.g., dry fingertips, rough fingertips, allergic-skin fingertips) demonstrates an efficient recognition performance of the proposed algorithm compared with a typical minutiae-based algorithm.

A major approach for iris recognition today is to generate feature vectors corresponding to individual iris images and to perform iris matching based on some distance metrics. One of the difficult problems in feature-based iris recognition is that the matching performance is significantly influenced by many parameters in feature extraction process, which may vary depending on environmental factors of image acquisition. This paper presents an efficient algorithm for iris recognition using phase-based image matching. The use of phase components in 2D (two-dimensional) discrete Fourier transforms of iris images makes possible to achieve highly robust iris recognition in a unified fashion with a simple matching algorithm. Experimental evaluation using an iris image database clearly demonstrates an efficient matching performance of the proposed algorithm.