Optic disc (OD) localization plays an important role in the automatic screening of ocular fundus diseases. However, it is still a challenge at present to balance the accuracy and efficiency of the OD localization for various of retinal fundus images. In this paper, we propose a new framework to integrate two classes methods based on image intensity and vascular information to obtain the OD location. The classification algorithm within the framework is based on a verification model. Firstly, an OD candidate region is obtained by image intensity. Secondly, the candidate region is validated by verification model. If the verification is passed, the corresponding position of the region is determined as the OD center. Otherwise, the OD is located by the parabola fitting of the main blood vessels and the relocation. The proposed method was evaluated on four public databases STARE, DRIVE, DIARETDB0 and DIARETDB1, and the accuracy rate was 96.3%, 100%, 100% and 100%, respectively. The running time is 0.05 s, 0.03 s, 0.13 s and 0.12 s per image through the validation in each database, while the time spent on images failed in verification is about 0.49 s, 0.38 s, 2.21 s and 2.15 s, individually. (C) 2017 Elsevier Ltd. All rights reserved.
Zou Beiji;Mohammed, Nurudeen;Zhu Chengzhang*;Zhao Rongchang
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS,2017年10(1):962-969 ISSN：1875-6891
[Zou Beiji; Zhao Rongchang; Mohammed, Nurudeen] Cent S Univ, Sch Informat Sci & Engn, South Lushan Rd, Changsha 410083, Hunan, Peoples R China.;[Zhu Chengzhang] Cent S Univ, Coll Literature & Journalism, South Lushan Rd, Changsha 410083, Hunan, Peoples R China.
[Zhu Chengzhang] Cent S Univ, Coll Literature & Journalism, South Lushan Rd, Changsha 410083, Hunan, Peoples R China.
Video Event Detection;Neuro-Fuzzy Inference;Crime Mapping;Hotspot Analysis
This paper presents a new approach to crime hotspot detection and monitoring. The approach consists of three phases' namely: video analysis, crime prediction and crime mapping. In video analysis, crime indicator events are modelled using statistical distribution of semantic concepts. In crime prediction, a neuro-fuzzy method is used to model indicator events. In crime mapping, kernel density estimation is used to detect crime hotspots. This approach is tested in a simulated platform using violent scene detection (VSD) 2014 dataset.
[Xiao, Yalong] Cent S Univ, Coll Literature & Journalism, Changsha, Hunan, Peoples R China.;[Wang, Haodong; Zhang, Shigeng; Wang, Jianxin] Cent S Univ, Sch Informat Sci & Engn, Changsha, Hunan, Peoples R China.;[Cao, Jiannong] Hong Kong Polytech Univ, Dept Comp, Kowloon, Hong Kong, Peoples R China.;[Wang, Haodong] Cleveland State Univ, Dept Elect Engn & Comp Sci, Cleveland, OH 44115 USA.
[Wang, Jianxin] Cent S Univ, Sch Informat Sci & Engn, Changsha, Hunan, Peoples R China.
Indoor localization;Fingerprinting method;Channel state information;KL divergence
Wi-Fi fingerprint based wireless indoor localization has received increasing research attention in recent years. Most existing works utilize the received signal strength (RSS) as the fingerprint of a particular position. However, RSS provides only very coarse-grained property of the received signal and thus cannot achieve high localization accuracy. Recently, some works attempt to improve the localization accuracy of Wi-Fi fingerprinting by utilizing the fine-grained channel state information (CSI) that can be obtained on commercial-off-the-shelf (COTS) network interface cards. These studies, however, use only the summation of the received signals to distinguish different positions, which limits their performance gain over the existing RSS-based methods. Our observations show that the distribution of CSI amplitude on individual subcarriers rather than the summation over all subcarriers can provide much finer-grained differentiation among different positions. In this paper, we propose a new localization method that exploits the distribution of CSI as the fingerprint of positions. Our approach makes better use of the frequency diversity with different subcarriers and the spatial diversity with multiple antennas, and thus effectively improves the localization accuracy. The Kullback–Laibler divergence is used to calculate the similarity between different fingerprints, based on which the best matched position is calculated in the localization phase. The experiment results obtained in two typical indoor environments demonstrate that, compared with the state-of-the-art approach, the proposed approach improves localization accuracy by 30%.
Journal of Computer Science and Technology,2017年(6):1222-1230 ISSN：1000-9000
[Chen, Zai-Liang; Zhang, Zi-Qian; Zou, Bei-Ji; Chen, Yao] Cent S Univ, Sch Informat Sci & Engn, Changsha 410083, Hunan, Peoples R China.;[Chen, Zai-Liang; Zhang, Zi-Qian; Zhu, Cheng-Zhang; Zou, Bei-Ji; Chen, Yao] Cent S Univ, Mobile Hlth Minist Educ China Mobile Joint Lab, Changsha 410083, Hunan, Peoples R China.;[Zhu, Cheng-Zhang] Cent S Univ, Coll Literature & Journalism, Changsha 410083, Hunan, Peoples R China.
[Zhu, Cheng-Zhang] Cent S Univ, Mobile Hlth Minist Educ China Mobile Joint Lab, Changsha 410083, Hunan, Peoples R China.;[Zhu, Cheng-Zhang] Cent S Univ, Coll Literature & Journalism, Changsha 410083, Hunan, Peoples R China.
Arterial-venous classification of retinal blood vessels is important for the automatic detection of cardiovascular diseases such as hypertensive retinopathy and stroke. In this paper, we propose an arterial-venous classification (AVC) method, which focuses on feature extraction and selection from vessel centerline pixels. The vessel centerline is extracted after the preprocessing of vessel segmentation and optic disc (OD) localization. Then, a region of interest (ROI) is extracted around OD, and the most efficient features of each centerline pixel in ROI are selected from the local features, grey-level co-occurrence matrix (GLCM) features, and an adaptive local binary patten (A-LBP) feature by using a max-relevance and min-redundancy (mRMR) scheme. Finally, a feature-weighted K-nearest neighbor (FW-KNN) algorithm is used to classify the arterial-venous vessels. The experimental results on the DRIVE database and INSPIRE-AVR database achieve the high accuracy of 88.65% and 88.51% in ROI, respectively.