- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Evaluation of Hyperspectral Classification Maps in Heterogeneous Ecosystem
摘要： Ecosystem management and monitoring are essential to preserve natural resources. Hyperspectral imagery (HSI) is a useful tool to obtain accurate classification maps, providing significant level of detail. Thus, traditional and novel methodologies based on pixel and object classification approaches are compared and evaluated in a homogeneous and mixed vulnerable ecosystem. Considering the challenging ecosystem, all classifications successfully resulted in high OA (higher than 82%), showing that HSI is very useful providing accurate vegetation maps to evaluate and monitor the ecosystems in a faster and economic way.
关键词： Hyperspectral imagery,Binary Partition Tree,CASI sensor,ecosystem management,Support Vector Machine
更新于2025-09-09 09:28:46
-
Crop classification with WorldView-2 imagery using Support Vector Machine comparing texture analysis approaches and grey relational analysis in Jianan Plain, Taiwan
摘要： Crop production estimation is of crucial concern in Taiwan, and the government has invested much effort including employing manpower and technologies. Artificial intelligence or data mining technology have been successfully applied on land-cover recognition of remote-sensing imagery. Most studies are employing a pixel-based classification approach to generate the thematic map of land covers. Few studies consider the spatial correlation of adjacent pixels of the same category. Mixed pixel issues usually degrade the prediction accuracy according to previous studies. It is thus the main goal of the present study to explore the spatial effect of adjacent pixels on land-cover mapping. The study region is a WorldView-2 satellite image in Jianan Plain, Taiwan, taken in 2014. Support Vector Machine is used as the underlying classifier. In addition to the eight spectral band intensities, normalized difference vegetation index and grey-level co-occurrence matrix (GLCM) textures are included as ancillary attributes. Furthermore, grey relational analysis (GRA) is employed to assist in classifying croplands. The findings of this study can be summarized as follows: (1) GLCM texture information improves classification accuracy marginally and renders slightly better thematic map, (2) GRA is used to acquire the most important factors concerning discriminating land covers, (3) grey relational grade threshold, a metric designed through GRA, can be used to locate uncertain region of a specified crop, which is possibly caused by mixed pixels.
关键词： GLCM,land cover mapping,support vector machine,Mixed pixel
更新于2025-09-09 09:28:46
-
Shearlet-Based Feature Extraction for the Detection and Classification of Age-Related Macular Degeneration in Spectral Domain Optical Coherence Tomography Images
摘要： Age-related macular degeneration (AMD) is an eye disease that usually affects central vision in people older than 50 years owing to accumulation of fluid in the macular region of the retina. Optical coherence tomography (OCT) is an imaging modality that is being widely used nowadays for the detection of abnormalities in the eye. In this work, a shearlet transformYbased method is proposed for automated detection of AMD. The 2-dimensional horizontal slices of spectral domain OCT imaging data are used as input images. Images are first converted to gray scale and denoised using bilateral filter. Denoised images are decomposed by applying shearlet transform and 10 textural features are extracted from the cooccurrence matrices of high-frequency transform coefficients. Based on these features, the OCT images are classified as normal or AMD using support vector machine and k-nearest neighbor classifiers. Results obtained using shearlet-based features are compared with that of wavelet transformYbased features. Best results are obtained when shearlet-based features are classified using support vector machine.
关键词： Shearlet transform,Wavelet transform,Support vector machine,Optical coherence tomography,K-nearest neighbor,Age-related macular degeneration
更新于2025-09-09 09:28:46
-
[IEEE 2018 24th International Conference on Pattern Recognition (ICPR) - Beijing, China (2018.8.20-2018.8.24)] 2018 24th International Conference on Pattern Recognition (ICPR) - Early Diagnosis of Diabetic Retinopathy in OCTA Images Based on Local Analysis of Retinal Blood Vessels and Foveal Avascular Zone
摘要： This paper introduces a diagnosis system for detecting early signs of diabetic retinopathy (DR) using optical coherence tomography angiography (OCTA) images. We developed a segmentation technique that was able to extract blood vessels from both retinal superficial and deep maps. It is based on a higher order joint Markov-Gibbs random field (MGRF) model, which combines both current and spatial appearance information of retinal blood vessels. To be able to train/test a support vector machine (SVM) classifier, three local features were extracted from the segmented images. These extracted features are the density and appearance of the retinal blood vessels in addition to the distance map of the foveal avascular zone (FAZ). Then, we used SVM with linear kernel to distinguish sub-clinical DR patients from normal cases. By using 105 subjects, the presented computer-aided diagnosis (CAD) system demonstrated an overall accuracy (ACC) of 97.3% and a Dice similarity coefficient (DSC) of 97.9%.
关键词： Markov-Gibbs random field,support vector machine,diabetic retinopathy,optical coherence tomography angiography,computer-aided diagnosis
更新于2025-09-09 09:28:46
-
Events detection and recognition by the fiber vibration system based on power spectrum estimation
摘要： One of the important successes of optical fiber sensor established for the security system is the detection and the recognition of any type of events. The performance parameters (event recognition, event detection position, and time of detection) are unavoidable and describe the validity of any perimeter detection system. An event recognition is any signal detected within the protected area, and it is related to a non-intrusion event and an intrusion event. To achieve the detection and the recognition events at the real time, an effective two-level vibration recognition method and a technique are proposed and presented in this article. The signal characteristics (short-term energy and short-time over-threshold) have been used and compared to the dynamic threshold to judge the type of event. Then the extraction of the power distribution features on the frequency domain through power spectral estimation on the suspected intrusion signal samples is carried out and finally combined with the time-domain characteristics as feature vector through Support Vector Machine to determine the efficiency and effectiveness of the proposed vibration recognition method. The experimental simulation results show that the proposed method is effective and reliable. With collected data, it can detect and recognize the type of event in real time.
关键词： Support Vector Machine,event detection and recognition,power spectral estimation,Optical fiber sensor,dynamic threshold,short-time over-threshold,short-term energy
更新于2025-09-09 09:28:46
-
Robust automatic classification of benign and malignant microcalcification and mass in digital mammography
摘要： Breast cancer is the most dangerous cancer among women and second mortality among them. Mammography is the efficient methodology used in early finding of breast cancer. However, mammograms requires high amount of skill and there is a possibility of radiologist to misunderstand it. Hence, computer aided diagnosis are used for finding the abnormalities in mammograms. Automated classification of mass and microcalcification system is proposed in this work using NSCT and SVM. The classification of abnormalities is achieved by extracting the microcalcification and mass features from the contourlet coefficients of the image and the results are used as an input to the SVM. The proposed automated system classifies the mammogram as normal or abnormal and result is abnormal, then it classifies the abnormal severity as benign or malignant. The evaluation of the proposed system is conceded on MIAS database. The experimentation result shows that the proposed system contributes improved classification rate.
关键词： mammogram,mass,non-subsampled contourlet transform,SVM,support vector machine,NSCT,benign,microcalcifications,malignant
更新于2025-09-09 09:28:46
-
A Portable, Wireless Photoplethysomography Sensor for Assessing Health of Arteriovenous Fistula Using Class-Weighted Support Vector Machine
摘要： A portable, wireless photoplethysomography (PPG) sensor for assessing arteriovenous fistula (AVF) by using class-weighted support vector machines (SVM) was presented in this study. Nowadays, in hospital, AVF are assessed by ultrasound Doppler machines, which are bulky, expensive, complicated-to-operate, and time-consuming. In this study, new PPG sensors were proposed and developed successfully to provide portable and inexpensive solutions for AVF assessments. To develop the sensor, at first, by combining the dimensionless number analysis and the optical Beer Lambert’s law, five input features were derived for the SVM classifier. In the next step, to increase the signal-noise ratio (SNR) of PPG signals, the front-end readout circuitries were designed to fully use the dynamic range of analog-digital converter (ADC) by controlling the circuitries gain and the light intensity of light emitted diode (LED). Digital signal processing algorithms were proposed next to check and fix signal anomalies. Finally, the class-weighted SVM classifiers employed five different kernel functions to assess AVF quality. The assessment results were provided to doctors for diagonosis and detemining ensuing proper treatments. The experimental results showed that the proposed PPG sensors successfully achieved an accuracy of 89.11% in assessing health of AVF and with a type II error of only 9.59%.
关键词： support vector machine (SVM),arteriovenous fistula (AVF),photoplethysmography (PPG) sensor
更新于2025-09-09 09:28:46
-
Multi-scale LBP and SVM Classification to Identify Diabetic Retinopathy in Lesions
摘要： Diabetic Retinopathy (DR) is the most common disease induced by the complication of diabetes, causing blindness. In many rural areas, the contributions of ophthalmologists are predicatively less to treat the disease. Detection of lesions in the early stage is a progressive measure to diagnose DR. Initially, a preprocessing method is performed to detect the Optic Nerve Head (ONH) in the lesion. Based on the degree of reflectance in ONH, feature extraction is computed using multi-scale Local Binary Pattern (LBP) algorithm. Here, Gabor convolution is estimated and the structure of ONH is encoded. This extends to a statistical computation in terms of the moment and standard deviation. A Support Vector Machine (SVM) classification is formulated to locate the hemorrhages and exudates and an effective probabilistic multi-label lesion classification is performed to acquire five sets of results representing the diabetic retinopathy: 1) Grade-1 Exudates, 2) Grade-2 Exudates, 3) Micro aneurysms, 4) Hemorrhages, 5) Neovascularization. Finally, the affected area of lesions is used to diagnose the disease.
关键词： statistical computation,Gabor convolution,local binary pattern,optic nerve head,support vector machine
更新于2025-09-09 09:28:46
-
Subspace-based multitask learning framework for hyperspectral imagery classification
摘要： Subspace-based models have been widely applied for hyperspectral imagery applications, especially for classification. The main principle of these methods is based on the fact that the original image can approximately lie on a lower-dimensional subspace. However, due to the existence of mixed samples, the subspace projection is unstable and affected by the selection of training samples, such that may lead to poor characterization and classification performances. In order to improve the robustness and characterization ability of the subspace-based classification models, this paper proposes a novel subspace-based multitask learning framework. In particular, the original image is first projected to the multiple subspaces in different branches. Then, the support vector machine (SVM) classifier is applied in each branch to deal with the projected data sets. With a consideration of integrating the spatial information, an extended step is provided including the process of a Markov Random Field (MRF) based on the result of SVM. Finally, the classification result is obtained by a decision fusion process. Experimental results on three real hyperspectral data sets demonstrate the improvements on classification performance of the proposed methods over other related methods.
关键词： Classification,Subspace projection,Support vector machine,Hyperspectral image
更新于2025-09-09 09:28:46
-
Multi-parametric Optic Disc Segmentation Using Superpixel Based Feature Classification
摘要： Glaucoma along with diabetic retinopathy is a major cause of vision blindness and is projected to affect over 80 million people by 2020. Recently, expert systems have matched human performance in disease diagnosis and proven to be highly useful in assisting medical experts in the diagnosis and detection of diseases. Hence, automated optic disc detection through intelligent systems is vital for early diagnosis and detection of Glaucoma. This paper presents a multi-parametric optic disk detection and localization method for retinal fundus images using region-based statistical and textural features. Highly discriminative features are selected based on the mutual information criterion and a comparative analysis of four benchmark classifiers: Support Vector Machine, Random Forest (RF), AdaBoost and RusBoost is presented. The results of the proposed RF classifier based pipeline demonstrate its highly competitive performance (accuracies of 0.993, 0.988 and 0.993 on the DRIONS, MESSIDOR and ONHSD databases) with the state-of-the-art, thus making it a suitable candidate for patient management systems for early diagnosis of the Glaucoma.
关键词： Random forest,AdaBoostM1,RusBoost,Glaucoma,Support vector machine
更新于2025-09-09 09:28:46