发布求助
文献互助 智能选刊 最新文献

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)最新文献

筛选
英文 中文
Robust object recognition in wearable eye tracking system 可穿戴眼动追踪系统的鲁棒目标识别
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486583
Mustafa Shdaifat, S. S. Bukhari, Takumi Toyama, A. Dengel
{"title":"Robust object recognition in wearable eye tracking system","authors":"Mustafa Shdaifat, S. S. Bukhari, Takumi Toyama, A. Dengel","doi":"10.1109/ACPR.2015.7486583","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486583","url":null,"abstract":"Object recognition is a versatile capability. Automatic guided tours and augmented reality are just two examples. Humans seem to do it subconsciously - unaware of the extensive processing required for it - while it is a complex task for machines. Methods based on SIFT features have proven to be robust for recognition. However, a prior detection step is required to limit confusion, caused by, e.g., scene clutter. We present an attention-guided method that offloads this to humans through eye tracking. Gaze data is used to extract candidate patches to recognize afterwards. It improves upon previous work by automatically selecting the dynamic size of said patch, instead of fixed large local region. Therefore increasing robustness and independence compared to fixed window size technique.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"32 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131776399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Distributed forests for MapReduce-based machine learning 基于mapreduce的机器学习的分布式森林
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486509
Ryoji Wakayama, R. Murata, Akisato Kimura, Takayoshi Yamashita, Yuji Yamauchi, H. Fujiyoshi
{"title":"Distributed forests for MapReduce-based machine learning","authors":"Ryoji Wakayama, R. Murata, Akisato Kimura, Takayoshi Yamashita, Yuji Yamauchi, H. Fujiyoshi","doi":"10.1109/ACPR.2015.7486509","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486509","url":null,"abstract":"This paper proposes a novel method for training random forests with big data on MapReduce clusters. Random forests are well suited for parallel distributed systems, since they are composed of multiple decision trees and every decision tree can be independently trained by ensemble learning methods. However, naive implementation of random forests on distributed systems easily overfits the training data, yielding poor classification performances. This is because each cluster node can have access to only a small fraction of the training data. The proposed method tackles this problem by introducing the following three steps. (1) \"Shared forests\" are built in advance on the master node and shared with all the cluster nodes. (2) With the help of transfer learning, the shared forests are adapted to the training data placed on each cluster node. (3) The adapted forests on every cluster node are returned to the master node, and irrelevant trees yielding poor classification performances are removed to form the final forests. Experimental results show that our proposed method for MapReduce clusters can quickly learn random forests without any sacrifice of classification performance.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131322027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 8
An extension of PatchMatch Stereo for 3D reconstruction from multi-view images PatchMatch Stereo的扩展，用于从多视图图像进行3D重建
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486466
Mutsuki Hiradate, Koichi Ito, T. Aoki, Takafumi Watanabe, Hiroki Unten
{"title":"An extension of PatchMatch Stereo for 3D reconstruction from multi-view images","authors":"Mutsuki Hiradate, Koichi Ito, T. Aoki, Takafumi Watanabe, Hiroki Unten","doi":"10.1109/ACPR.2015.7486466","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486466","url":null,"abstract":"PatchMatch Stereo is a method generating a depth map from stereo images by repeatedly applying spatial propagation and view propagation to the depth map. The extension of PatchMatch Stereo for multi-view 3D reconstruction has been recently proposed. This extension is very ad hoc and does not fully utilize the potential of multi-view images, since the method generates a 3D point cloud by combining a set of depth maps obtained from each binocular stereo image pair. This paper proposes a multi-view 3D reconstruction method using PatchMatch Stereo. To fully utilize the impact of multi-view images, the proposed method have two key ideas: (i) integrate matching scores from multiple stereo image pairs and (ii) perform view propagation among multi-view images. The use of multi-view images makes it possible to generate a reliable depth map by reducing occlusions. Through a set of experiments, we demonstrate that the proposed method generates more reliable depth map from multi-view images than the conventional method.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131670522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Multilayer feature combination for visual tracking 多层特征组合视觉跟踪
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486571
Heng Fan, Jinhai Xiang, Fuchuan Ni
{"title":"Multilayer feature combination for visual tracking","authors":"Heng Fan, Jinhai Xiang, Fuchuan Ni","doi":"10.1109/ACPR.2015.7486571","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486571","url":null,"abstract":"This paper proposes a new tracking method based on multilayer feature combination. In each layer, the target is segmented into local patches, and patch sizes of different layers are different. Through this way, each layer contains different local information of the object, which are mutually complementary for each other. For each layer, the local patches are represented with sparse codes. We combine these sparse codes into a histogram of sparse codes (HSC) for each layer. To handle appearance variations, we improve the HSC and obtain a modified histogram of sparse codes (MHSC), which is used to represent each layer. We combine the MHSCs of multilayer to form the feature vector of the object. To improve the robustness of the feature vector, different weights are assigned to various layers because each layer has different discriminative power under different cases. Within Bayesian framework, we achieve visual tracking by finding the candidate which has the highest similarity with the reference. Experiments demonstrate that the proposed method outperforms several state-of-the-art trackers.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133309672","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Stacked partial least squares regression for image classification 叠置偏最小二乘回归图像分类
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486606
Ryoma Hasegawa, K. Hotta
{"title":"Stacked partial least squares regression for image classification","authors":"Ryoma Hasegawa, K. Hotta","doi":"10.1109/ACPR.2015.7486606","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486606","url":null,"abstract":"In recent years, the researches based on Convolutional Neural Network (CNN) have been doing in computer vision after the success in ILSVRC 2012. Hierarchical feature extraction is one of the reasons why CNN gives the state-of-the-art performance. On the other hand, Partial Least Squares (PLS) Regression which has been widely used in chemo-metrics is also used in computer vision in recent years. If class labels are used as objective variables for PLS, PLS can extract features suitable for classification. In this paper, we combine the idea of hierarchical feature extraction of CNN with feature extraction suitable for classification by PLS and propose a new method called Stacked PLS. It extracts features hierarchically in reference to CNN using PLS. The proposed method is evaluated on the MNIST dataset. Our method gave higher performance than CNN with the same network architecture and is comparable to the state-of-the-art methods.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129689789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Character-position-free on-line handwritten Japanese text recognition 字符位置自由的在线手写日语文本识别
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486500
Jianjuan Liang, Bilan Zhu, Taro Kumagai, M. Nakagawa
{"title":"Character-position-free on-line handwritten Japanese text recognition","authors":"Jianjuan Liang, Bilan Zhu, Taro Kumagai, M. Nakagawa","doi":"10.1109/ACPR.2015.7486500","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486500","url":null,"abstract":"The paper presents a recognition method of character-position-free (CPF) on-line handwritten Japanese text patterns to allow a user to overlay characters freely without confirming previously written characters. To develop this method, we prepared large sets of CPF handwritten Japanese text patterns artificially from normally handwritten text patterns. The proposed method sets each off-stroke between real strokes as undecided and evaluates the segmentation probability by SVM model. Then, the optimal segmentation-recognition path can be effectively found by the Viterbi search in the candidate lattice, combining the scores of character recognition, geometric features, linguistic context, as well as the segmentation scores by SVM classification. We test this method on variously overlaid sample patterns, and verify that it produces competing recognition rates as the latest recognizer for normally handwritten horizontal Japanese text without the serious problem in speed for practical applications.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120923607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Segmentation of 3D image of a rock sample supervised by 2D mineralogical image 基于二维矿物学图像的岩样三维图像分割
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486523
I. Varfolomeev, I. Yakimchuk, B. Sharchilev
{"title":"Segmentation of 3D image of a rock sample supervised by 2D mineralogical image","authors":"I. Varfolomeev, I. Yakimchuk, B. Sharchilev","doi":"10.1109/ACPR.2015.7486523","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486523","url":null,"abstract":"We present an approach for 2D-to-3D mineralogical information propagation and preliminary results of its implementation. An X-ray microtomography (microCT) scanner is used to obtain a 3D microstructural image of the sample. A scanning electron microscope (SEM) equipped with an energy-dispersive X-ray (EDX) detector provides a supervising 2D mineral map of a rock sample cross section. The 2D and 3D images are then registered using a surface-based algorithm, naturally taking into account specifics of said data. The overlapping area of the images is then used as a training set for supervised mineralogical segmentation of the full 3D sample.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116481560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Supervised topology preserving hashing 监督拓扑保持哈希
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486510
Shu Zhang, Man Zhang, Qi Li, T. Tan, R. He
{"title":"Supervised topology preserving hashing","authors":"Shu Zhang, Man Zhang, Qi Li, T. Tan, R. He","doi":"10.1109/ACPR.2015.7486510","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486510","url":null,"abstract":"Learning based hashing is gaining traction in large-scale retrieval systems. It aims to learn compact binary codes that can preserve semantic similarity in the hamming space. This paper presents a supervised topology hashing (SPTH) algorithm to learn compact binary codes that can exploit both the supervisory information as well as the local topology structure of datasets. To build a connection between the original space and the resultant hamming space, we minimize the quantization errors together with a classification error term and a topology preserving term. A nonlinear kernel feature space is further used to improve the generalization power. An alternating iterative algorithm is developed to minimize the complex objective function that contains both continuous and discrete variables. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed method on image retrieval tasks.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116126034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Mixture model based color clustering for psoriatic plaque segmentation 基于混合模型的银屑病斑块颜色聚类分割
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486529
A. Pal, A. Roy, K. Sen, R. Chatterjee, Utpal Garain, Swapan Senapati
{"title":"Mixture model based color clustering for psoriatic plaque segmentation","authors":"A. Pal, A. Roy, K. Sen, R. Chatterjee, Utpal Garain, Swapan Senapati","doi":"10.1109/ACPR.2015.7486529","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486529","url":null,"abstract":"This paper presents a mixture model based color clustering and then applies this technique for psoriatic plaque segmentation in skin images. For clustering image pixels, two mostly relevant colorspaces namely, CIE Luv(cubic) and CIE Lch(equivalent cylindrical) are considered. Gaussian Mixture Model(GMM) is used for clustering in Luv space. However, Lch space being a circular-linear space does not support the use of GMM. Hence, clustering in Lch makes use of a novel mixture model known as Semi-Wrapped Gaussian Mixture Model(SWGMM). The performance of these clustering methods is evaluated for psoriatic plaque segmentation and results are compared with those obtained by the commonly used Fuzzy C-Means (FCM) clustering algorithm. The comparative study shows that the clustering in Lch using SWGMM outperforms the other approaches. For localizing the plaques, we consider von Mises distribution to find a suitable confidence interval and thereby defining skin and non-skin models. The UCI Skin Segmentation dataset is used for this purpose. This localization approach achieves an average accuracy 79.53%. A real clinical dataset of Psoriasis images is used in this experiment.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"65 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123249151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 8
Robust feature matching via multiple descriptor fusion 基于多描述子融合的鲁棒特征匹配
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486508
Yuan-Ting Hu, Yen-Yu Lin
{"title":"Robust feature matching via multiple descriptor fusion","authors":"Yuan-Ting Hu, Yen-Yu Lin","doi":"10.1109/ACPR.2015.7486508","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486508","url":null,"abstract":"We present a novel approach to boost image matching performance by fusing multiple local descriptors in the homography space. Traditional matching methods find correspondences based on a single descriptor and the performance becomes unstable due to the goodness of the chosen descriptor To address this problem, our method uses multiple descriptors and select a good descriptor for matching each feature point. Specifically, we project every correspondence into the homography space, where correct correspondences tend to gather together due to the similarity of their homographies. Then kernel density estimation is applied to measure the density in the homography space and verify the correctness of correspondences. The proposed approach is comprehensively compared with the state-of-the-art methods and the promising results manifest its effectiveness.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122547610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信