样式: 排序: IF: - GO 导出 标记为已读
-
3D human pose estimation model using location-maps for distorted and disconnected images by a wearable omnidirectional camera IPSJ T. Comput. Vis. Appl. Pub Date : 2020-08-31 Teppei Miura, Shinji Sako
We address a 3D human pose estimation for equirectangular images taken by a wearable omnidirectional camera. The equirectangular image is distorted because the omnidirectional camera is attached closely in front of a person’s neck. Furthermore, some parts of the body are disconnected on the image; for instance, when a hand goes out to an edge of the image, the hand comes in from another edge. The distortion
-
Application of evolutionary and swarm optimization in computer vision: a literature survey IPSJ T. Comput. Vis. Appl. Pub Date : 2020-08-31 Takumi Nakane, Naranchimeg Bold, Haitian Sun, Xuequan Lu, Takuya Akashi, Chao Zhang
Evolutionary algorithms (EAs) and swarm algorithms (SAs) have shown their usefulness in solving combinatorial and NP-hard optimization problems in various research fields. However, in the field of computer vision, related surveys have not been updated during the last decade. In this study, inspired by the recent development of deep neural networks in computer vision, which embed large-scale optimization
-
Pseudo-labelling-aided semantic segmentation on sparsely annotated 3D point clouds IPSJ T. Comput. Vis. Appl. Pub Date : 2020-07-02 Yasuhiro Yao, Katie Xu, Kazuhiko Murasaki, Shingo Ando, Atsushi Sagata
Manually labelling point cloud scenes for use as training data in machine learning applications is a time- and labour-intensive task. In this paper, we aim to reduce the effort associated with learning semantic segmentation tasks by introducing a semi-supervised method that operates on scenes with only a small number of labelled points. For this task, we advocate the use of pseudo-labelling in combination
-
Phase disambiguation using spatio-temporally modulated illumination in depth sensing IPSJ T. Comput. Vis. Appl. Pub Date : 2020-04-07 Takahiro Kushida, Kenichiro Tanaka, Takahito Aoto, Takuya Funatomi, Yasuhiro Mukaigawa
Phase ambiguity is a major problem in the depth measurement in either time-of-flight or phase shifting. Resolving the ambiguity using a low frequency pattern sacrifices the depth resolution, and using multiple frequencies requires a number of observations. In this paper, we propose a phase disambiguation method that combines temporal and spatial modulation so that the high depth resolution is preserved
-
Pedestrian segmentation based on a spatio-temporally consistent graph-cut with optimal transport IPSJ T. Comput. Vis. Appl. Pub Date : 2019-11-29 Yang Yu, Yasushi Makihara, Yasushi Yagi
We address a method of pedestrian segmentation in a video in a spatio-temporally consistent way. For this purpose, given a bounding box sequence of each pedestrian obtained by a conventional pedestrian detector and tracker, we construct a spatio-temporal graph on a video and segment each pedestrian on the basis of a well-established graph-cut segmentation framework. More specifically, we consider three
-
Spatio-temporal silhouette sequence reconstruction for gait recognition against occlusion IPSJ T. Comput. Vis. Appl. Pub Date : 2019-11-20 Md. Zasim Uddin, Daigo Muramatsu, Noriko Takemura, Md. Atiqur Rahman Ahad, Yasushi Yagi
Gait-based features provide the potential for a subject to be recognized even from a low-resolution image sequence, and they can be captured at a distance without the subject’s cooperation. Person recognition using gait-based features (gait recognition) is a promising real-life application. However, several body parts of the subjects are often occluded because of beams, pillars, cars and trees, or
-
Thermal non-line-of-sight imaging from specular and diffuse reflections IPSJ T. Comput. Vis. Appl. Pub Date : 2019-11-04 Masaki Kaga, Takahiro Kushida, Tsuyoshi Takatani, Kenichiro Tanaka, Takuya Funatomi, Yasuhiro Mukaigawa
This paper presents a non-line-of-sight technique to estimate the position and temperature of an occluded object from a camera via reflection on a wall. Because objects with heat emit far infrared light with respect to their temperature, positions and temperatures are estimated from reflections on a wall. A key idea is that light paths from a hidden object to the camera depend on the position of the
-
Deep learning-based strategies for the detection and tracking of drones using several cameras IPSJ T. Comput. Vis. Appl. Pub Date : 2019-07-24 Eren Unlu, Emmanuel Zenou, Nicolas Riviere, Paul-Edouard Dupouy
Commercial Unmanned aerial vehicle (UAV) industry, which is publicly known as drone, has seen a tremendous increase in last few years, making these devices highly accessible to public. This phenomenon has immediately raised security concerns due to fact that these devices can intentionally or unintentionally cause serious hazards. In order to protect critical locations, the academia and industry have
-
Learning-based active 3D measurement technique using light field created by video projectors IPSJ T. Comput. Vis. Appl. Pub Date : 2019-07-17 Yuki Shiba, Satoshi Ono, Ryo Furukawa, Shinsaku Hiura, Hiroshi Kawasaki
The combination of a pattern projector and a camera is widely used for 3D measurement. To recover shape from a captured image, various kinds of depth cues are extracted from projected patterns in the image, such as disparities from active stereo or blurriness for depth from defocus. Recently, several techniques have been proposed to improve 3D quality using multiple depth cues by installing coded apertures
-
Learning 3D joint constraints from vision-based motion capture datasets IPSJ T. Comput. Vis. Appl. Pub Date : 2019-06-25 Pramod Murthy, Hammad T. Butt, Sandesh Hiremath, Alireza Khoshhal, Didier Stricker
Realistic estimation and synthesis of articulated human motion must satisfy anatomical constraints on joint angles. A data-driven approach is used to learn human joint limits from 3D motion capture datasets. We represent joint constraints with a new formulation (s1,s2,τ) using swing-twist representation in exponential maps form. Our parameterization is applied on Human3.6M dataset to create the lookup-map
-
Gait-based age estimation using multi-stage convolutional neural network IPSJ T. Comput. Vis. Appl. Pub Date : 2019-06-10 Atsuya Sakata, Noriko Takemura, Yasushi Yagi
Gait-based age estimation has been extensively studied for various applications because of its high practicality. In this paper, we propose a gait-based age estimation method using convolutional neural networks (CNNs). Because gait features vary depending on a subject’s attributes, i.e., gender and generation, we propose the following three CNN stages: (1) a CNN for gender estimation, (2) a CNN for
-
Unsupervised anomaly detection with compact deep features for wind turbine blade images taken by a drone IPSJ T. Comput. Vis. Appl. Pub Date : 2019-06-04 Yinan Wang, Ryota Yoshihashi, Rei Kawakami, Shaodi You, Tohru Harano, Masahiko Ito, Katsura Komagome, Makoto Iida, Takeshi Naemura
Detecting anomalies in wind turbine blades from aerial images taken by drones can reduce the costs of periodic inspections. Deep learning is useful for image recognition, but it requires large amounts of data to be collected on rare abnormalities. In this paper, we propose a method to distinguish normal and abnormal parts of a blade by combining one-class support vector machine, an unsupervised learning
-
Symbol spotting for architectural drawings: state-of-the-art and new industry-driven developments IPSJ T. Comput. Vis. Appl. Pub Date : 2019-05-10 Alireza Rezvanifar, Melissa Cote, Alexandra Branzan Albu
This review paper offers a contemporary literature survey on symbol spotting in architectural drawing images. Research on isolated symbol recognition is quite mature; the same cannot be said for recognizing a symbol in context. One important challenge is the segmentation/recognition paradox: a system should segment symbols before recognizing them, but some kind of recognition may be necessary to obtain
-
Attacking convolutional neural network using differential evolution IPSJ T. Comput. Vis. Appl. Pub Date : 2019-02-22 Jiawei Su, Danilo Vasconcellos Vargas, Kouichi Sakurai
The output of convolutional neural networks (CNNs) has been shown to be discontinuous which can make the CNN image classifier vulnerable to small well-tuned artificial perturbation. That is, images modified by conducting such alteration (i.e., adversarial perturbation) that make little difference to the human eyes can completely change the CNN classification results. In this paper, we propose a practical
-
Estimating 3D human shape under clothing from a single RGB image IPSJ T. Comput. Vis. Appl. Pub Date : 2018-12-27 Yui Shigeki, Fumio Okura, Ikuhisa Mitsugami, Yasushi Yagi
Estimation of naked human shape is essential in several applications such as virtual try-on. We propose an approach that estimates naked human 3D pose and shape, including non-skeletal shape information such as musculature and fat distribution, from a single RGB image. The proposed approach optimizes a parametric 3D human model using person silhouettes with clothing category, and statistical displacement
-
Optical tomography based on shortest-path model for diffuse surface object IPSJ T. Comput. Vis. Appl. Pub Date : 2018-11-23 Takafumi Iwaguchi, Takuya Funatomi, Takahito Aoto, Hiroyuki Kubo, Yasuhiro Mukaigawa
We tackle an optical measurement of the internal structure of a diffuse surface object—we define as an object that has a diffuse surface and its interior is transparent, like grapes or hollow plastic bottles. Our approach is based on optical tomography that reconstructs the interior from observations of absorption of light rays from various views, under the projection of the light. The difficulty lies
-
Camera calibration with coplanar conics: a unified explanation and ambiguity analysis IPSJ T. Comput. Vis. Appl. Pub Date : 2018-11-08 Shen Cai, Zhanhao Wu
In this paper, we propose a two-step method to give a unified explanation of camera calibration with two coplanar conics. Various kinds of conics-based patterns in which often two parameters are unknown have been studied in previous literatures. The key in such algorithms is to adopt different strategies to compute the world-to-image projective transformation (also called 2D homography). In the first
-
Decomposition of reflection and scattering by multiple-weighted measurements IPSJ T. Comput. Vis. Appl. Pub Date : 2018-10-23 Tsuyoshi Takatani, Yasuhiro Mukaigawa, Yasuyuki Matsushita, Yasushi Yagi
An observed image is composed of multiple components based on optical phenomena, such as light reflection and scattering. Decomposing the observed image into individual components is an important process for various computer vision tasks. No general approach to combine them exists although many decomposition methods exist. This paper proposes a general approach to combine different decomposition methods
-
Pedestrian detection with motion features via two-stream ConvNets IPSJ T. Comput. Vis. Appl. Pub Date : 2018-09-27 Ryota Yoshihashi, Tu Tuan Trinh, Rei Kawakami, Shaodi You, Makoto Iida, Takeshi Naemura
Motion information can be important for detecting objects, but it has been used less for pedestrian detection, particularly with deep-learning-based methods. We propose a method that uses deep motion features as well as deep still-image features, following the success of two-stream convolutional networks, each of which are trained separately for spatial and temporal streams. To extract motion clues
-
An multi-scale learning network with depthwise separable convolutions IPSJ T. Comput. Vis. Appl. Pub Date : 2018-07-31 Gaihua Wang, Guoliang Yuan, Tao Li, Meng Lv
We present a simple multi-scale learning network for image classification that is inspired by the MobileNet. The proposed method has two advantages: (1) It uses the multi-scale block with depthwise separable convolutions, which forms multiple sub-networks by increasing the width of the network while keeping the computational resources constant. (2) It combines the multi-scale block with residual connections
-
Directional characteristics evaluation of silhouette-based gait recognition IPSJ T. Comput. Vis. Appl. Pub Date : 2018-07-31 Yui Shigeki, Fumio Okura, Ikuhisa Mitsugami, Kenichi Hayashi, Yasushi Yagi
Gait is an important biometric trait for identifying individuals. The use of inputs from multiple or moving cameras offers a promising extension of gait recognition methods. Personal authentication systems at building entrances, for example, can utilize multiple cameras installed at appropriate positions to increase their authentication accuracy. In such cases, it is important to identify effective
-
Supervoxel-based segmentation of 3D imagery with optical flow integration for spatiotemporal processing IPSJ T. Comput. Vis. Appl. Pub Date : 2018-06-19 Xiaohui Huang, Chengliang Yang, Sanjay Ranka, Anand Rangarajan
The past 20 years has seen a progressive evolution of computer vision algorithms for unsupervised 2D image segmentation. While earlier efforts relied on Markov random fields and efficient optimization (graph cuts, etc.), the next wave of methods beginning in the early part of this century were, in the main, stovepiped. Of these 2D segmentation efforts, one of the most popular and, indeed, one that
-
Numerical shape-from-shading revisited IPSJ T. Comput. Vis. Appl. Pub Date : 2018-06-14 Hiroaki Santo, Masaki Samejima, Yasuyuki Matsushita
This paper revisits the numerical shape-from-shading method proposed in early 1980s. The original problem is non-convex due to the unit norm constraint for surface normal, and the existing approaches including the original Ikeuchi and Horn’s work uses approximate solution strategies for the original problem. This paper instead studies relaxation strategies for the original non-convex constraint and
-
Controlling translucency by UV printing on a translucent object IPSJ T. Comput. Vis. Appl. Pub Date : 2018-06-08 Tsuyoshi Takatani, Koki Fujita, Kenichiro Tanaka, Takuya Funatomi, Yasuhiro Mukaigawa
UV printer, a digital fabrication tool, can print 2D patterns on 3D objects consisting of various materials by using UV inks which immediately dry through being exposed to ultraviolet light. In general use, the translucency of the materials is removed by printing a matte white layer. On the other hand, we propose a method to control the translucency of a printed object by rather utilizing both of the
-
Structure from motion using dense CNN features with keypoint relocalization IPSJ T. Comput. Vis. Appl. Pub Date : 2018-05-31 Aji Resindra Widya, Akihiko Torii, Masatoshi Okutomi
Structure from motion (SfM) using imagery that involves extreme appearance changes is yet a challenging task due to a loss of feature repeatability. Using feature correspondences obtained by matching densely extracted convolutional neural network (CNN) features significantly improves the SfM reconstruction capability. However, the reconstruction accuracy is limited by the spatial resolution of the
-
The OU-ISIR Large Population Gait Database with real-life carried object and its performance evaluation IPSJ T. Comput. Vis. Appl. Pub Date : 2018-05-30 Md. Zasim Uddin, Thanh Trung Ngo, Yasushi Makihara, Noriko Takemura, Xiang Li, Daigo Muramatsu, Yasushi Yagi
In this paper, we describe the world’s largest gait database with real-life carried objects (COs), which has been made publicly available for research purposes, and its application to the performance evaluation of vision-based gait recognition. Whereas existing databases for gait recognition include at most 4007 subjects, we constructed an extremely large-scale gait database that includes 62,528 subjects
-
Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition IPSJ T. Comput. Vis. Appl. Pub Date : 2018-02-20 Noriko Takemura, Yasushi Makihara, Daigo Muramatsu, Tomio Echigo, Yasushi Yagi
This paper describes the world’s largest gait database with wide view variation, the “OU-ISIR gait database, multi-view large population dataset (OU-MVLP)”, and its application to a statistically reliable performance evaluation of vision-based cross-view gait recognition. Specifically, we construct a gait dataset that includes 10,307 subjects (5114 males and 5193 females) from 14 view angles ranging
-
A histogram specification technique for dark image enhancement using a local transformation method IPSJ T. Comput. Vis. Appl. Pub Date : 2018-02-12 Khalid Hussain, Shanto Rahman, Md. Mostafijur Rahman, Shah Mostafa Khaled, M. Abdullah-Al Wadud, Muhammad Asif Hossain Khan, Mohammad Shoyaib
Traditional image enhancement techniques produce different types of noise such as unnatural effects, over-enhancement, and artifacts, and these drawbacks become more prominent in enhancing dark images. To overcome these drawbacks, we propose a dark image enhancement technique where local transformation of the pixels have been performed. Here, we apply a transformation method of different parts of the
-
Constrained multi-target tracking for team sports activities IPSJ T. Comput. Vis. Appl. Pub Date : 2018-01-16 Rikke Gade, Thomas B. Moeslund
In sports analysis, player tracking is essential to the extraction of statistics such as speed, distance and direction of motion. Simultaneous tracking of multiple people is still a very challenging computer vision problem to which there is no satisfactory solution. This is especially true for sports activities, for which people often wear similar uniforms, move quickly and erratically, and have close
-
Visual saliency detection for RGB-D images under a Bayesian framework IPSJ T. Comput. Vis. Appl. Pub Date : 2018-01-10 Songtao Wang, Zhen Zhou, Wei Jin, Hanbing Qu
In this paper, we propose a saliency detection model for RGB-D images based on the deep features of RGB images and depth images within a Bayesian framework. By analysing 3D saliency in the case of RGB images and depth images, the class-conditional mutual information is computed for measuring the dependence of deep features extracted using a convolutional neural network; then, the posterior probability
-
Sample-based integrated background subtraction and shadow detection IPSJ T. Comput. Vis. Appl. Pub Date : 2017-12-22 Arun Varghese, Sreelekha G
This paper presents an integrated background subtraction and shadow detection algorithm to identify background, shadow, and foreground regions in a video sequence, a fundamental task in video analytics. The background is modeled at pixel level with a collection of previously observed background pixel values. An input pixel is classified as background if it finds the required number of matches with
-
The OU-ISIR Gait Database comprising the Large Population Dataset with Age and performance evaluation of age estimation IPSJ T. Comput. Vis. Appl. Pub Date : 2017-12-21 Chi Xu, Yasushi Makihara, Gakuto Ogi, Xiang Li, Yasushi Yagi, Jianfeng Lu
In this paper, we describe the world’s largest gait database, the “OU-ISIR Gait Database, Large Population Dataset with Age (OULP-Age)” and its application to a statistically reliable performance evaluation of gait-based age estimation. Whereas existing gait databases include only 4016 subjects at most, we constructed an extremely large-scale gait database that includes 63,846 subjects (31,093 males
-
Efficient video collection association using geometry-aware Bag-of-Iconics representations IPSJ T. Comput. Vis. Appl. Pub Date : 2017-12-15 Ke Wang, Enrique Dunn, Mikel Rodriguez, Jan-Michael Frahm
Recent years have witnessed the dramatic evolution in visual data volume and processing capabilities. For example, technical advances have enabled 3D modeling from large-scale crowdsourced photo collections. Compared to static image datasets, exploration and exploitation of Internet video collections are still largely unsolved. To address this challenge, we first propose to represent video contents
-
Generic and attribute-specific deep representations for maritime vessels IPSJ T. Comput. Vis. Appl. Pub Date : 2017-12-11 Berkan Solmaz, Erhan Gundogdu, Veysel Yucesoy, Aykut Koc
Fine-grained visual categorization has recently received great attention as the volumes of labeled datasets for classification of specific objects, such as cars, bird species, and air-crafts, have been increasing. The availability of large datasets led to significant performance improvements in several vision-based classification tasks. Visual classification of maritime vessels is another important
-
Accurate laser scanner to camera calibration with application to range sensor evaluation IPSJ T. Comput. Vis. Appl. Pub Date : 2017-11-10 Peter Fuersattel, Claus Plank, Andreas Maier, Christian Riess
Multi-modal sensory data plays an important role in many computer vision and robotics tasks. One popular multi-modal pair is cameras and laser scanners. To overlay and jointly use the data from both modalities, it is necessary to calibrate the sensors, i.e., to obtain the spatial relation between the sensors. Computing such a calibration is challenging as both sensors provide quite different data:
-
Effective hyperparameter optimization using Nelder-Mead method in deep learning IPSJ T. Comput. Vis. Appl. Pub Date : 2017-11-10 Yoshihiko Ozaki, Masaki Yano, Masaki Onishi
In deep learning, deep neural network (DNN) hyperparameters can severely affect network performance. Currently, such hyperparameters are frequently optimized by several methods, such as Bayesian optimization and the covariance matrix adaptation evolution strategy. However, it is difficult for non-experts to employ these methods. In this paper, we adapted the simpler coordinate-search and Nelder-Mead
-
Computer vision methods for cranial sex estimation IPSJ T. Comput. Vis. Appl. Pub Date : 2017-09-29 Olasimbo Ayodeji Arigbabu, Iman Yi Liao, Nurliza Abdullah, Mohamad Helmee Mohamad Noor
The objective of this study is to demonstrate through empirical evaluation the potential of a number of computer vision (CV) methods for sex determination from human skull. To achieve this, six local feature representations, two feature learnings, and three classification algorithms are rigorously combined and evaluated on skull regions derived from skull partitions. Furthermore, we introduce for the
-
MultiQ: single sensor-based multi-quality multi-modal large-scale biometric score database and its performance evaluation IPSJ T. Comput. Vis. Appl. Pub Date : 2017-07-26 Md. Zasim Uddin, Daigo Muramatsu, Takuhiro Kimura, Yasushi Makihara, Yasushi Yagi
Single sensor-based multi-modal biometrics is a promising approach that offers simple system construction, low cost, and wide applicability to real situations such as CCTV footage-based criminal investigations. In multi-modal biometrics, fusion at the score-level is a popular and promising approach, and data qualities that affect the matching score of each modality are often incorporated as a quality-dependent
-
A survey of diminished reality: Techniques for visually concealing, eliminating, and seeing through real objects IPSJ T. Comput. Vis. Appl. Pub Date : 2017-06-28 Shohei Mori, Sei Ikeda, Hideo Saito
In this paper, we review diminished reality (DR) studies that visually remove, hide, and see through real objects from the real world. We systematically analyze and classify publications and present a technology map as a reference for future research. We also discuss future directions, including multimodal diminished reality. We believe that this paper will be useful mainly for students who are interested
-
Visual SLAM algorithms: a survey from 2010 to 2016 IPSJ T. Comput. Vis. Appl. Pub Date : 2017-06-02 Takafumi Taketomi, Hideaki Uchiyama, Sei Ikeda
SLAM is an abbreviation for simultaneous localization and mapping, which is a technique for estimating sensor motion and reconstructing structure in an unknown environment. Especially, Simultaneous Localization and Mapping (SLAM) using cameras is referred to as visual SLAM (vSLAM) because it is based on visual information only. vSLAM can be used as a fundamental technology for various types of applications
-
Recovering temporal PSF using ToF camera with delayed light emission IPSJ T. Comput. Vis. Appl. Pub Date : 2017-06-02 Kazuya Kitano, Takanori Okamoto, Kenichiro Tanaka, Takahito Aoto, Hiroyuki Kubo, Takuya Funatomi, Yasuhiro Mukaigawa
Recovering temporal point spread functions (PSFs) is important for various applications, especially analyzing light transport. Some methods that use amplitude-modulated continuous wave time-of-flight (ToF) cameras are proposed to recover temporal PSFs, where the resolution is several nanoseconds. Contrarily, we show in this paper that sub-nanosecond resolution can be achieved using pulsed ToF cameras
-
Global ray-casting range image registration IPSJ T. Comput. Vis. Appl. Pub Date : 2017-05-08 Linh Tao, Tam Bui, Hiroshi Hasegawa
This paper presents a novel method for pair-wise range image registration, a backbone task in world modeling, parts inspection and manufacture, object recognition, pose estimation, robotic navigation, and reverse engineering. The method finds the most suitable homogeneous transformation matrix between two constructed range images to create a more complete 3D view of a scene. The proposed solution integrates
-
4-D light field reconstruction by irradiance decomposition IPSJ T. Comput. Vis. Appl. Pub Date : 2017-04-08 Takahito Aoto, Tomokazu Sato, Yasuhiro Mukaigawa, Naokazu Yokoya
Common light sources such as an ordinary flashlight with lenses and/or reflectors make complex 4-D light field that cannot be represented by conventional isotropic distribution model nor point light source model. This paper describes a new approach to estimate 4-D light field using an illuminated diffuser. Unlike conventional works that capture a 4-D light field directly, our method decomposes observed
-
Selecting image pairs for SfM by introducing Jaccard Similarity IPSJ T. Comput. Vis. Appl. Pub Date : 2017-04-04 Takaharu Kato, Ikuko Shimizu, Tomas Pajdla
We present a new approach for selecting image pairs that are more likely to match in Structure from Motion (SfM). We propose to use Jaccard Similarity (JacS) which shows how many different visual words is shared by an image pair. In our method, the similarity between images is evaluated using JacS of bag-of-visual-words in addition to tf-idf (term frequency-inverse document frequency), which is popular
-
Fast search based on generalized similarity measure IPSJ T. Comput. Vis. Appl. Pub Date : 2017-03-27 Yuzuko Utsumi, Tomoya Mizuno, Masakazu Iwamura, Koichi Kise
This paper proposes a fast recognition method based on generalized similarity measure (GSM). The GSM achieves good recognition accuracy for face recognition, but has a scalability problem. Because the GSM method requires the similarity measures between a query and all samples to be calculated, the computational cost for recognition is in proportion to the number of samples. A reasonable approach to
-
A practical person authentication system using second minor finger knuckles for door security IPSJ T. Comput. Vis. Appl. Pub Date : 2017-03-24 Daichi Kusanagi, Shoichiro Aoyama, Koichi Ito, Takafumi Aoki
This paper proposes a person authentication system using second minor finger knuckles, i.e., metacarpophalangeal (MCP) joints, for door security. This system acquires finger knuckle patterns on MCP joints when a user takes hold of a door handle and recognizes a person using MCP joint patterns. The proposed system can be constructed by attaching a camera onto a door handle to capture MCP joints. Region
-
Convolutional bag of words for diabetic retinopathy detection from eye fundus images IPSJ T. Comput. Vis. Appl. Pub Date : 2017-03-24 Pedro Costa, Aurélio Campilho
This paper describes a methodology for diabetic retinopathy detection from eye fundus images using a generalization of the bag-of-visual-words (BoVW) method. We formulate the BoVW as two neural networks that can be trained jointly. Unlike the BoVW, our model is able to learn how to perform feature extraction, feature encoding, and classification guided by the classification error. The model achieves
-
Mobile hologram verification with deep learning IPSJ T. Comput. Vis. Appl. Pub Date : 2017-03-24 Daniel Soukup, Reinhold Huber-Mörk
Holograms are security features applied to security documents like banknotes, passports, and ID cards in order to protect them from counterfeiting. Checking the authenticity of holograms is an important but difficult task, as holograms comprise different appearances for varying observation and/or illumination directions. Multi-view and photometric image acquisition and analysis procedures have been
-
In-line recognition of agglomerated pharmaceutical pellets with density-based clustering and convolutional neural network IPSJ T. Comput. Vis. Appl. Pub Date : 2017-03-16 Andraž Mehle, Boštjan Likar, Dejan Tomaževič
We present a method for recognition of agglomerates in images acquired during the coating process of pharmaceutical pellets. The pellets in the images are not perfectly dispersed, and it is often hard to differentiate between a random group of primary particles and a real agglomerate. The method utilizes a clustering-based image segmentation for candidate region detection and a convolutional neural
-
Deep residual coalesced convolutional network for efficient semantic road segmentation IPSJ T. Comput. Vis. Appl. Pub Date : 2017-03-15 Igi Ardiyanto, Teguh Bharata Adji
This paper proposes a deep learning-based efficient and compact solution for road scene segmentation problem, named deep residual coalesced convolutional network (RCC-Net). Initially, the RCC-Net performs dimensionality reduction to compress and extract relevant features, from which it is subsequently delivered to the encoder. The encoder adopts the residual network style for efficient model size.
-
Incremental structural modeling on sparse visual SLAM IPSJ T. Comput. Vis. Appl. Pub Date : 2017-03-15 Rafael A. Roberto, Hideaki Uchiyama, João Paulo S. M. Lima, Hajime Nagahara, Rin-ichiro Taniguchi, Veronica Teichrieb
This paper presents an incremental structural modeling approach that improves the precision and the stability of existing batch-based ones for sparse and noisy point clouds from visual simultaneous localization and mapping (SLAM). The main idea is to use the generating process of point clouds on SLAM effectively. First, a batch-based method is applied to point clouds that are incrementally generated
-
Co-occurrence context of the data-driven quantized local ternary patterns for visual recognition IPSJ T. Comput. Vis. Appl. Pub Date : 2017-03-14 Xian-Hua Han, Yen-Wei Chen, Gang Xu
In this paper, we describe a novel local descriptor of image texture representation for visual recognition. The image features based on micro-descriptors such as local binary patterns (LBP) and local ternary patterns (LTP) have been very successful in a number of applications including face recognition, object detection, and texture analysis. Instead of binary quantization in LBP, LTP thresholds the
-
Abnormality tracking during video capsule endoscopy using an affine triangular constraint based on surrounding features IPSJ T. Comput. Vis. Appl. Pub Date : 2017-03-01 Yukiko Yanagawa, Tomio Echigo, Hai Vu, Hirotoshi Okazaki, Yasuhiro Fujiwara, Tetsuo Arakawa, Yasushi Yagi
The precise tracking of an abnormality in the gastrointestinal tract is useful for medical training purposes. However, the gastrointestinal wall deforms continuously in an unpredictable manner, while abnormalities lack distinctive features, making them difficult to track over continuous frames. To address this problem, we propose a tracking method for capsule endoscopy using the surrounding features
-
A learned sparseness and IGMRF-based regularization framework for dense disparity estimation using unsupervised feature learning IPSJ T. Comput. Vis. Appl. Pub Date : 2017-02-09 Sonam Nahar,Manjunath V. Joshi
In this work, we propose a new approach for dense disparity estimation in a global energy minimization framework. We propose to use a feature matching cost which is defined using the learned hierarchical features of given left and right stereo images and we combine it with the pixel-based intensity matching cost in our energy function. Hierarchical features are learned using the deep deconvolutional
-
Real-time rendering of aerial perspective effect based on turbidity estimation IPSJ T. Comput. Vis. Appl. Pub Date : 2017-01-13 Carlos Morales,Takeshi Oishi,Katsushi Ikeuchi
In real outdoor scenes, objects distant from the observer suffer from a natural effect called aerial perspective that fades the colors of the objects and blends them to the environmental light color. The aerial perspective can be modeled using a physics-based approach; however, handling with the changing and unpredictable environmental illumination as well as the weather conditions of real scenes is
-
Temporally coherent disparity maps using CRFs with fast 4D filtering IPSJ T. Comput. Vis. Appl. Pub Date : 2016-12-09 Siavash Arjomand Bigdeli,Gregor Budweiser,Matthias Zwicker
State-of-the-art methods for disparity estimation achieve good results for single stereo frames, but temporal coherence in stereo videos is often neglected. In this paper, we present a method to compute temporally coherent disparity maps. We define an energy over whole stereo sequences and optimize their conditional random field (CRF) distributions using the mean-field approximation. In addition, we
-
A novel framework for cross-spectral iris matching IPSJ T. Comput. Vis. Appl. Pub Date : 2016-11-05 Mohammed A. M. Abdullah,Satnam S. Dlay,Wai L. Woo,Jonathon A. Chambers
Previous work on iris recognition focused on either visible light (VL), near-infrared (NIR) imaging, or their fusion. However, limited numbers of works have investigated cross-spectral matching or compared the iris biometric performance under both VL and NIR spectrum using unregistered iris images taken from the same subject. To the best of our knowledge, this is the first work that proposes a framework
-
Nuclear detection in 4D microscope images of a developing embryo using an enhanced probability map of top-ranked intensity-ordered descriptors IPSJ T. Comput. Vis. Appl. Pub Date : 2016-11-03 Xian-Hua Han,Yukako Tohsato,Koji Kyoda,Shuichi Onami,Ikuko Nishikawa,Yen-Wei Chen
Nuclear detection in embryos is an indispensable process for quantitative analysis of the development of multicellular organisms. Due to the overlap in the distribution of pixel intensity of nuclear and cytoplasmic regions and the large variation of pixel intensity even within the same type of cellular components in different embryos, it is difficult to separate nuclear regions from the surrounding
-
Vertical error correction of eye trackers in nonrestrictive reading condition IPSJ T. Comput. Vis. Appl. Pub Date : 2016-09-14 Charles Lima Sanches,Olivier Augereau,Koichi Kise
The eye tracking technology is used for four decades for studying reading behavior. The applications are various: estimating the reader comprehension, identifying the reader, summarizing a read document, creating a reading-life log, etc. The gaze data used in such applications has to be accurate enough to perform the analysis. In order to improve the accuracy, most of the experiments are set up with
-
Effective elliptic arc selection from connected edge points IPSJ T. Comput. Vis. Appl. Pub Date : 2016-09-06 Tomonari Masuzaki,Yasuyuki Sugaya
Extracting edge points from an image and fitting ellipses to them is a fundamental technique for computer vision applications. However, since the extracted edge points sometimes contain non-elliptic arcs such as line segments, it is a very difficult to extract only elliptic arcs from them. In this paper, we propose a new method for extracting elliptic arcs from a spatially connected point sequence