Minutiae pattern extraction plays a crucial role in fingerprint registration and identification for electronic applications. However, the extraction accuracy is seriously compromised by the presence of contaminated ridge lines and complex background scenarios. General image processing-based methods, which rely on many prior hypotheses, fail to effectively handle minutiae extraction in complex scenarios. Previous works have shown that CNN-based methods can perform well in object detection tasks. However, the deep neural networks (DNNs)-based methods are restricted by the limitation of public labeled datasets due to legitimate privacy concerns. To address these challenges comprehensively, this paper presents a fully automated minutiae extraction method leveraging DNNs. Firstly, we create a fingerprint minutiae dataset using a semi-automated minutiae annotation algorithm. Subsequently, we propose a minutiae extraction model based on Residual Networks (Resnet) that enables end-to-end prediction of minutiae. Moreover, we introduce a novel non-maximal suppression (NMS) procedure, guided by the Generalized Intersection over Union (GIoU) metric, during the inference phase to effectively handle outliers. Experimental evaluations conducted on the NIST SD4 and FVC 2004 databases demonstrate the superiority of the proposed method over existing state-of-the-art minutiae extraction approaches.

This paper presents a deep network based on unrolling the diffusion process with the morphological Laplacian. The diffusion process is an iterative algorithm that can solve the diffusion equation and represents time evolution with Laplacian. The diffusion process is applied to smoothing of images and has been extended with non-linear operators for various image processing tasks. In this study, we introduce the morphological Laplacian to the basic diffusion process and unwrap to deep networks. The morphological filters are non-linear operators with parameters that are referred to as structuring elements. The discrete Laplacian can be approximated with the morphological filters without multiplications. Owing to the non-linearity of the morphological filter with trainable structuring elements, the training uses error back propagation and the network of the morphology can be adapted to specific image processing applications. We introduce two extensions of the morphological Laplacian for deep networks. Since the morphological filters are realized with addition, max, and min, the error caused by the limited bit-length is not amplified. Consequently, the morphological parts of the network are implemented in unsigned 8-bit integer with single instruction multiple data set (SIMD) to achieve fast computation on small devices. We applied the proposed network to image completion and Gaussian denoising. The results and computational time are compared with other denoising algorithm and deep networks.

This paper presents a deep network based on morphological filters for Gaussian denoising. The morphological filters can be applied with only addition, max, and min functions and require few computational resources. Therefore, the proposed network is suitable for implementation using a small microprocessor. Each layer of the proposed network consists of a top-hat transform, which extracts small peaks and valleys of noise components from the input image. Noise components are iteratively reduced in each layer by subtracting the noise components from the input image. In this paper, the extensions of opening and closing are introduced as linear combinations of the morphological filters for the top-hat transform of this deep network. Multiplications are only required for the linear combination of the morphological filters in the proposed network. Because almost all parameters of the network are structuring elements of the morphological filters, the feature maps and parameters can be represented in short bit-length integer form, which is suitable for implementation with single instructions, multiple data (SIMD) instructions. Denoising examples show that the proposed network obtains denoising results comparable to those of BM3D [1] without linear convolutions and with approximately one tenth the number of parameters of a full-scale deep convolutional neural network [2]. Moreover, the computational time of the proposed method using SIMD instructions of a microprocessor is also presented.

Blob detection is an important part of computer vision and a special case of region detection with important applications in the image analysis. In this paper, the dilation operator in standard mathematical morphology is firstly extended to the order dilation operator of soft morphology, three soft morphological filters are designed by using the operator, and a novel blob detection algorithm called SMBD is proposed on that basis. SMBD had been proven to have better performance of anti-noise and blob shape detection than similar blob filters based on mathematical morphology like Quoit and N-Quoit in terms of theoretical and experimental aspects. Additionally, SMBD was also compared to LoG and DoH in different classes, which are the most commonly used blob detector, and SMBD also achieved significantly great results.

For image restoration, an image prior that is obtained from the morphological gradient has been proposed. In the field of mathematical morphology, the optimization of the structuring element (SE) used for this morphological gradient using a genetic algorithm (GA) has also been proposed. In this paper, we introduce a new image prior that is the sum of the morphological gradients and total variation for an image restoration problem to improve the restoration accuracy. The proposed image prior makes it possible to almost match the fitness to a quantitative evaluation such as the mean square error. It also solves the problem of the artifact due to the unsuitability of the SE for the image. An experiment shows the effectiveness of the proposed image restoration method.

We propose a method that detects vehicles from in-vehicle monocular camera images captured during nighttime driving. Detecting vehicles from their shape is difficult at night; however, many vehicle detection methods focusing on light have been proposed. We detect bright spots by appropriate binarization based on the characteristics of vehicle lights such as brightness and color. Also, as the detected bright spots include lights other than vehicles, we need to distinguish the vehicle lights from other bright spots. Therefore, the bright spots were distinguished using Random Forest, a multiclass classification machine-learning algorithm. The features of bright spots not associated with vehicles were effectively utilized in the vehicle detection in our proposed method. More precisely vehicle detection is performed by giving weights to the results of the Random Forest based on the features of vehicle bright spots and the features of bright spots not related to the vehicle. Our proposed method was applied to nighttime images and confirmed effectiveness.

This paper presents convex filter networks that are obtained from extensions of morphological filters. The proposed filter network consists of a convex and concave filter that are extensions of the dilation and erosion of mathematical morphology with the maxout activation function. Maxout can approximate arbitrary convex functions as piecewise linear functions, including the max function. The class of the convex function hence includes the morphological dilation and can be trained for specific image processing tasks. In this paper, the closing filter is extended to a convex-concave filter network with maxout. The convex-concave filter is trained by the stochastic gradient method for noise and mask removal. The examples of noise and mask removal show that the convex-concave filter can obtain a recovered image, whose quality is comparable to inpainting by using the total variation minimization with reduced computational cost without mask information of the corrupted pixels.

In this paper, an image prior based on soft-morphological filters and its application to image recovery are presented. In morphological image processing, a gray-scale image is represented as a subset in a three-dimensional space, which is spanned by spatial and intensity axes. Morphological opening and closing, which are basic operations in morphological image processing, respectively approximate the image subset and its complementary images as the unions of structuring elements that are translated in the three-dimensional space. In this study, the opening and closing filters are applied to an image prior to resolve the regularization problem of image recovery. When the proposed image prior is applied, the image is recovered as an image that has no noise component, which is eliminated by the opening and closing. However, the closing and opening filters are less able to eliminate Gaussian noise. In order to improve the robustness against Gaussian noise, the closing and opening filters are respectively approximated as soft-closing and soft-opening with relaxed max and min functions. In image recovery experiments, image denoising and deblurring using the proposed prior are demonstrated. Comparisons of the proposed prior with the existing priors that impose a penalty on the gradient of the intensity are also shown.

This paper proposes an adaptation method for structuring elements of morphological filters. A structuring element of a morphological filter specifies a shape of local structures that is eliminated or preserved in the output. The adaptation of the structuring element is hence a crucial problem for image denoising using morphological filters. Existing adaptation methods for structuring elements require preliminary training using example images. We propose an adaptation method for structuring elements of morphological opening filters that does not require such training. In our approach, the opening filter is interpreted as an approximation method with the union of the structuring elements. In order to eliminate noise components, a penalty defined from an assumption of image smoothness is imposed on the structuring element. Image denoising is achieved through decreasing the objective function, which is the sum of an approximation error term and the penalty function. In experiments, we use the proposed method to demonstrate positive impulsive noise reduction from images.

In this paper, we propose a novel texture analysis method capable of estimating multiple primitives, which are elements repetitively arranged to compose a texture, in multi-structured textures. The approach is based on a texture description model that uses mathematical morphology, called the “Primitive, Grain, and Point Configuration (PGPC)” texture model. The estimation of primitives based on the PGPC texture model involves searching the optimal structuring element for primitives according to a size distribution function and a magnification. The proposed method achieves the following two improvements: (1) the simultaneous estimation of a multiple number of primitives in multi-structured textures with a ranking of primitives on the basis of their significance. and (2) the introduction of flexibility in the process of magnification to obtain a higher degree of fitness of large grains. With a computational combination of different primitives, the method provides an ordered priority to denote the significance of elements. The promising performance of the proposed method is experimentally shown by a comparison with conventional methods.

We describe a multi-step approach for automatic segmentation of the femoral head and the acetabulum in the hip joint from three dimensional (3D) CT images. Our segmentation method consists of the following steps: 1) construction of the valley-emphasized image by subtracting valleys from the original images; 2) initial segmentation of the bone regions by using conventional techniques including the initial threshold and binary morphological operations from the valley-emphasized image; 3) further segmentation of the bone regions by using the iterative adaptive classification with the initial segmentation result; 4) detection of the rough bone boundaries based on the segmented bone regions; 5) 3D reconstruction of the bone surface using the rough bone boundaries obtained in step 4) by a network of triangles; 6) correction of all vertices of the 3D bone surface based on the normal direction of vertices; 7) adjustment of the bone surface based on the corrected vertices. We evaluated our approach on 35 CT patient data sets. Our experimental results show that our segmentation algorithm is more accurate and robust against noise than other conventional approaches for automatic segmentation of the femoral head and the acetabulum. Average root-mean-square (RMS) distance from manual reference segmentations created by experienced users was approximately 0.68 mm (in-plane resolution of the CT data).

A method of estimating dual primitives in a textural image is proposed. This method is based on the Primitive, Grain, and Point Configuration (PGPC) texture model, which regards a texture as an arrangement of grains derived from one or a few primitives. Appropriate primitives can be represented by morphological structuring elements estimated from a texture. Conventional primitive estimation methods estimate only one primitive from each textural image. However, they do not work well on textural images that contain more than one basic structure, since two or more types of grain cannot be generated from only one primitive. The proposed method simultaneously estimates two optimal structuring elements of a texture. The experimental results show that the proposed method provides more representative estimations than the conventional method.

In this paper, we propose an image enlargement method by using morphological operators. Our enlargement method is based on the nonlinear frequency extrapolation method (Greenspan et al., 2000) by using a Laplacian pyramid image representation. In this method, the sampling process of input images is modeled as the Laplacian pyramid. A high resolution image is obtained with the finer scale Laplacian that is extrapolated by a nonlinear operation from a low resolution Laplacian. In this paper, we propose a novel nonlinear operation for extrapolation of the finer scale Laplacian. Our nonlinear operation is realized by morphological operators and is capable of generating the finer scale Laplacian, the amplitude of which is proportional to contrasts of edges that appear in the low resolution image. In experiments, the enlargement results given by the proposed method are demonstrated. Compared with the Greenspan's method, the proposed method can recover sharp intensity transients of image edges with small artifacts.

The purpose of our study is to develop an algorithm that would enable the automated detection of lacunar infarct on T1- and T2-weighted magnetic resonance (MR) images. Automated identification of the lacunar infarct regions is not only useful in assisting radiologists to detect lacunar infarcts as a computer-aided detection (CAD) system but is also beneficial in preventing the occurrence of cerebral apoplexy in high-risk patients. The lacunar infarct regions are classified into the following two types for detection: "isolated lacunar infarct regions" and "lacunar infarct regions adjacent to hyperintensive structures." The detection of isolated lacunar infarct regions was based on the multiple-phase binarization (MPB) method. Moreover, to detect lacunar infarct regions adjacent to hyperintensive structures, we used a morphological opening processing and a subtraction technique between images produced using two types of circular structuring elements. Thereafter, candidate regions were selected based on three features -- area, circularity, and gravity center. Two methods were applied to the detected candidates for eliminating false positives (FPs). The first method involved eliminating FPs that occurred along the periphery of the brain using the region-growing technique. The second method, the multi-circular regions difference method (MCRDM), was based on the comparison between the mean pixel values in a series of double circles on a T1-weighted image. A training dataset comprising 20 lacunar infarct cases was used to adjust the parameters. In addition, 673 MR images from 80 cases were used for testing the performance of our method; the sensitivity and specificity were 90.1% and 30.0% with 1.7 FPs per image, respectively. The results indicated that our CAD system for the automatic detection of lacunar infarct on MR images was effective.

Fingerprints are useful for biometric purposes because of their well known properties of distinctiveness and persistence over time. However, owing to skin conditions or incorrect finger pressure, original fingerprint images always contain noise. Especially, some of them contain useless components, which are often mistaken for the terminations that are an essential minutia of a fingerprint. Mathematical Morphology (MM) is a powerful tool in image processing. In this paper, we propose a linear time algorithm to eliminate impulsive noise and useless components, which employs generalized and ordinary morphological operators based on Euclidean distance transform. There are two contributions. The first is the simple and efficient MM method to eliminate impulsive noise, which can be restricted to a minimum number of pixels. We know the performance of MM is heavily dependent on structuring elements (SEs), but finding an optimal SE is a difficult and nontrivial task. So the second contribution is providing an automatic approach without any experiential parameter for choosing appropriate SEs to eliminate useless components. We have developed a novel algorithm for the binarization of fingerprint images [1]. The information of distance transform values can be obtained directly from the binarization phase. The results show that using this method on fingerprint images with impulsive noise and useless components is faster than existing denoising methods and achieves better quality than earlier methods.

This article introduces a novel approach to model phonology and morphosyntax in morpheme unit-based speech recognizers. The proposed methods are evaluated on a Hungarian newspaper dictation task that requires modeling over 1 million different word forms. The architecture of the recognition system is based on the weighted finite-state transducer (WFST) paradigm. The vocabulary units used in the system are morpheme-based in order to provide sufficient coverage of the large number of word-forms resulting from affixation and compounding. Besides the basic pronunciation model and the morpheme N-gram language model we evaluate a novel phonology model and the novel stochastic morphosyntactic language model (SMLM). Thanks to the flexible transducer-based architecture of the system, these new components are integrated seamlessly with the basic modules with no need to modify the decoder itself. We compare the phoneme, morpheme, and word error-rates as well as the sizes of the recognition networks in two configurations. In one configuration we use only the N-gram model while in the other we use the combined model. The proposed stochastic morphosyntactic language model decreases the morpheme error rate by between 1.7 and 7.2% relatively when compared to the baseline trigram system. The proposed phonology model reduced the error rate by 8.32%. The morpheme error-rate of the best configuration is 18% and the best word error-rate is 22.3%.

The deposition conditions of Y0.9Ba1.9La0.2Cu3Oy (La-YBCO) and (LaAlO3)0.3-(SrAl0.5Ta0.5O3)0.7 (LSAT) thin films were studied with the aim of fabricating ramp-edge Josephson junctions on a superconducting ground plane. These films were deposited by a magnetron sputtering method and utilized as a base electrode and an insulating layer under the electrode, respectively. YBa2Cu3Oy thick films grown by liquid phase epitaxy (LPE-YBCO) were used for a ground plane. Insertion of a SrTiO3 buffer layer between LSAT and LPE-YBCO significantly improved the flatness of the film surface. La-YBCO films with a flat surface and Tc (zero) of 87K were reproducibly obtained by DC sputtering. We have fabricated ramp-edge Josephson junctions using these films. Resistively and capacitively shunted junction (RCSJ)-like characteristics were observed in them. An Ic spread of 10.2% (at 4.2K, average Ic = 0.5 mA) was obtained for a 1000-junction series-array.

Polyurethane elastomer (PUE) films similar to polymer gel materials have been found to exhibit the electrostriction effect. We proposed the application their to a moving device such as an actuator without ionic solvent using the electrostriction effect of PUE. The actuators are of monomorph type fabricated by PUE film and metal electrodes evaporated at different thicknesses on the film surface. Because these actuators work at high voltage more than 1 KV, we controlled the molecular structure of the films by doping C60 derivatives (fullerenol) into PUE so that the actuators could operate under a low voltage. In order to clear the bending mechanism of actuators, we measured the space charge of PUE films using the pulsed electroacoustic method.

Edge detection has been an essential step in image processing, and there has been much work undertaken to date. This paper inspects a fuzzy mathematical morphology in order to reach a higher-level of edge-image processing. The proposed scheme uses a fuzzy morphological gradient to detect object boundaries, when the boundaries are roughly defined as a curve or a surface separating homogeneous regions. The automatic edge detection algorithm consists of two major steps. First, a new version of anisotropic diffusion is proposed for edge detection and image restoration. All improvements of the new version use fuzzy mathematical morphology to preserve the edge accuracy and to restore the images to homogeneity. Second, the fuzzy morphological gradient operation detects the step edges between the homogeneous regions as object boundaries. This operation uses geometrical characteristics contained in the structuring element in order to extract the edge features in the set of edgeness, a set consisting of the quality values of the edge pixels. This set is prepared with fuzzy logic for decision and selection of authentic edge pixels. For experimental results, the proposed method has been tested successfully with both synthetic and real pictures.

A novel method for the primitive description of the multiprimitive texture is proposed. This method segments a texture by the watershed algorithm into fragments each of which contains one grain. The similar fragments are grouped by the cluster analysis in the feature space whose basis is the morphological size density. Each primitive is extracted as the grain of the central fragment in each cluster.