2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)最新文献_第8页

A novel feature reduction framework for digital mammogram image classification 一种新的数字乳房x光图像分类特征约简框架

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486498

Hajar M. Alharbi, G. Falzon, P. Kwan

{"title":"A novel feature reduction framework for digital mammogram image classification","authors":"Hajar M. Alharbi, G. Falzon, P. Kwan","doi":"10.1109/ACPR.2015.7486498","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486498","url":null,"abstract":"The visual similarity between normal breast tissues and abnormal lesions in digital mammogram images makes computer-aided diagnosis of breast cancer using automatically detected features a highly error-prone task. Our contribution in this paper is a novel feature reduction framework for selecting the most discriminative features that achieves both efficiency and classification accuracy. Our approach applies five individual feature-ranking methods including Fisher score, minimum redundancy-maximum relevance, relief-f, sequential forward feature selection, and genetic algorithm for sorting the extracted features and selecting the features with highest ranking to setup a classifier. Our method achieves an accuracy of 94.27% and a sensitivity of 98.36% with a specificity of 99.27% on a set of 1,100 mammogram patches taken from image retrieval in medical applications database using a neural network classifier, which competes with state-of-the-art classification accuracy 93.11%. Furthermore, we demonstrate that only 49 out of the 119 extracted features are sufficient to achieve the reported accuracy of normal vs. abnormal classification.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"2573 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":"128787869","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

Noise-resistant local binary pattern based on random projection 基于随机投影的抗噪声局部二值模式

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486614

Shasha Li, Yukai Tu, Weihong Deng, Jiwen Lu

引用次数: 0

Multi-pruning of decision trees for knowledge representation and classification 基于知识表示和分类的决策树多重剪枝

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486574

Mohammad Azad, I. Chikalov, Shahid Hussain, M. Moshkov

引用次数: 10

Discriminant statistical analysis of local facial geometrical regions 局部面部几何区域的判别统计分析

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486524

Misae Nakatsu, R. Kimura, X. Han, Yenwei Chen

{"title":"Discriminant statistical analysis of local facial geometrical regions","authors":"Misae Nakatsu, R. Kimura, X. Han, Yenwei Chen","doi":"10.1109/ACPR.2015.7486524","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486524","url":null,"abstract":"The residences of Japanese Archipelago mainly include the three human populations; the Ainu, the Mainland Japanese and the Ryukyuan, which can be inferred by genome-wide single-nucleotide polymorphism (SNP) data and characterized by generic base sequences. In the other hand, the genetic association of human facial morphological variation recently becomes a more and more active research field, which aims to quantitatively analyze the possible relation measure between the gene base and a kind offacial morphological variations. This study attempts to explore the discriminated phenotype features of the common facial morphological variations between the Mainland Japanese and the Ryukyuan; the difference of phenotype features between these two populations is prospected to infer different gene base sequences. In order to explore the facial phenotype features, we propose a framework of local statistical analysis for adjacent geometrical regions of 3D facial images. Therein, we firstly select the surface points with higher distinguishable values based fisher linear discriminate analysis as discriminated coordinate vectors, and further cluster them into local geometrical groups for morphological analysis. The extracted local phenotype features are applied for identification of two populations, and achieve the comparable or better performances than the global phenotype feature, which manifests the possibility for association analysis between local morphological phenotype and the genes.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"54 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":"129763516","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

Generating unsupervised models for online long-term daily living activity recognition 生成在线长期日常生活活动识别的无监督模型

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486491

Farhood Negin, S. Coşar, F. Brémond, Michal Koperski

引用次数: 11

Locality-constrained group sparse coding regularized NMR for robust face recognition 位置约束群稀疏编码正则核磁共振鲁棒人脸识别

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486601

Hengmin Zhang, W. Luo, Jian Yang, Lei Luo

引用次数: 1

Human action recognition in the fractional Fourier domain 分数傅里叶域的人体动作识别

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486585

Jia-xin Cai, G. F. Sun

引用次数: 4

Towards a segmentation and recognition-free approach for content-based document image retrieval of handwritten queries 面向基于内容的手写查询文档图像检索的无分割和无识别方法

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486483

Houssem Chatbri, K. Kameyama, P. Kwan

{"title":"Towards a segmentation and recognition-free approach for content-based document image retrieval of handwritten queries","authors":"Houssem Chatbri, K. Kameyama, P. Kwan","doi":"10.1109/ACPR.2015.7486483","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486483","url":null,"abstract":"We introduce a method for content-based document image retrieval (CBDIR) of handwritten queries that is both segmentation and recognition-free. We first demonstrate that our method is underpinned by a theoretical model that exploits the Bayes' rule. Next, we present an algorithmic implementation that takes into account real world retrieval challenges caused by handwriting fluctuations and style variations. Our algorithm operates as follows: First, a number of connected components of the query are matched against the connected components of the document image using shape features. A similarity threshold is used to select the connected components of the document image that are most similar to the query components. Then, the selected components are used to detect candidate occurrences of the query in the document image by using size-adaptive bounding boxes. Finally, a score is calculated for each candidate occurrence and used for ranking. We conduct a comparative evaluation of our method on a dataset of 200 printed document images, by executing 40 printed and 200 handwritten queries of mathematical expressions. Experimental results demonstrate competitive performances expressed by P-Recall = 100%, A-Recall = 99.95% for printed queries, and P-Recall = 73.5%, A-Recall = 57.92% for handwritten queries, outperforming a state-of-the-art CBDIR algorithm.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"11 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":"131141383","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: 6

Face recognition with occlusion 遮挡下的人脸识别

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486587

Yingcheng Su, Yujiu Yang, Zhenhua Guo, Weiguo Yang

{"title":"Face recognition with occlusion","authors":"Yingcheng Su, Yujiu Yang, Zhenhua Guo, Weiguo Yang","doi":"10.1109/ACPR.2015.7486587","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486587","url":null,"abstract":"Facial occlusion, such as sunglasses, scarf, mask etc., is one critical factor that affects the performance of face recognition. Unfortunately, faces with occlusion are quite common in the real world, especially in uncooperative scenario. In recent years, regression analysis becomes a hotspot of dealing with face recognition under different illuminations and facial occlusions. The basic idea of regression analysis is to recover clean images from degraded images or occluded images by using the clean training samples. Then the reconstructed images are used for face recognition. However noise would be introduced in the recovery procedure. So whether reconstructed image help face recognition is still worth studying. Note that the residual image which is a difference between the raw and reconstructed image containing most of the occluded information. We can use it for occlusion detection. In this paper we make two contributions: i) we present a new occlusion detection method by combining the information of both raw image and residual image; ii) we empirically show that using the non-occluded part for face recognition has a better result than using reconstructed image.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"21 1 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":"123270360","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: 16

Global and local consistent multi-view subspace clustering 全局和局部一致性多视图子空间聚类

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486566

Yanbo Fan, R. He, Bao-Gang Hu

引用次数: 8