- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) - Chongqing, China (2018.10.12-2018.10.14)] 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) - Medical image segmentation based on improved watershed algorithm
摘要： The watershed segmentation algorithm has the problem of over-segmentation. The paper proposed an improved watershed algorithm for medical image segmentation. Combined with improved gray morphological reconstruction and watershed algorithm, the segmentation of medical cells and brain CT images is improved, which improves the accuracy of image segmentation of medical tissues and organs and assists doctors to diagnose the diseases. The simulation results show that the improved algorithm can effectively suppress the over-segmentation for two different medical tissue images.
关键词： watershed algorithm,medical image,segmentation,grayscale morphology
更新于2025-09-23 15:23:52
-
[ACM Press the 2nd International Conference - Chengdu, China (2018.06.16-2018.06.18)] Proceedings of the 2nd International Conference on Advances in Image Processing - ICAIP '18 - MIFNet
摘要： Sea-land segmentation is of great significance to coastline extraction and ship detection. Due to the complicated texture and intensity distribution of high resolution remote sensing images, traditional methods based on threshold and artificial features are difficult to perform well. This paper presents a new multi-information fusion network (MIFNet) based on convolutional neural network. MIFNet not only considers multi-scale edges and multi-scale segmentation information, but also introduces global context information, and fuses different scales and types of information through network learning. Experiments on a set of natural-colored images from Google Earth show that our model achieves better performance than the state-of-the-art methods.
关键词： semantic segmentation,Sea-land segmentation,global context,multi-information
更新于2025-09-23 15:22:29
-
[IEEE 2018 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS) - Beijing (2018.8.19-2018.8.20)] 2018 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS) - Instance Segmentation of Trees in Urban Areas from MLS Point Clouds Using Supervoxel Contexts and Graph-Based Optimization
摘要： In this paper, an instance segmentation method for tree extraction from MLS data sets in urban scenes is developed. The proposed method utilizes a supervoxel structure to organize the point clouds, and then extracts the detrended geometric features from the local context of supervoxels. Combined with the detrended features of the local context, the Random Forest (RF) classifier will be adopted to obtain the initial semantic labeling results of trees from point clouds. Afterwards, a local context-based regularization is iteratively performed to achieve global optimum on a global graphical model, in order to spatially smoothing the semantic labeling results. Finally, a graph-based segmentation is conducted to separate individual trees according to the semantic labeling results. The use of supervoxel structure can preserve the geometric boundaries of objects in the scene, and compared with point-based solutions, the supervoxel-based method can largely decrease the number of basic elements during the processing. Besides, the introduction of supervoxel contexts can extract the local information of an object making the feature extraction more robust and representative. Detrended geometric features can get over the redundant and in-salient information in the local context, so that discriminative features are obtained. Benefiting from the regularization process, the spatial smoothing is obtained based on initial labeling results from classic classifications such as RF classification. As a result, misclassification errors are removed to a large degree and semantic labeling results are thus smoothed. Based on the constructed global graphical model during the spatially smoothing process, a graph-based segmentation is applied to partition the graphical model for the clustering the instances of trees. The experiments on two test datasets have shown promising results, with an accuracy of the semantic labeling of trees reaching around 0.9. The segmentation of trees using graph-based algorithm also show acceptable results, with trees having simple structures and sparse distributions correctly separated, but for those cramped trees with complex structures, the points are over- or under-segmented.
关键词： local context,urban areas,supervoxels,MLS,Instance segmentation,graph-based segmentation,trees
更新于2025-09-23 15:22:29
-
[IEEE 2018 International Conference on Control, Power, Communication and Computing Technologies (ICCPCCT) - Kannur (2018.3.23-2018.3.24)] 2018 International Conference on Control, Power, Communication and Computing Technologies (ICCPCCT) - Identification of Melanoma in Dermoscopy Images Using Image Processing Algorithms
摘要： Skin cancer is the most common of all human cancers and is always misunderstood with other kind of skin diseases, so accurate early detection of skin cancer is essential. The main objective of this paper is to segment the lesion and identify melanoma from dermoscopy images. A total of 170 dermoscopy images are used in this research. Firstly, the input images are enhanced for better processing then, the lesion portion is segmented from the enhanced image by two methods 1.Otsu thresholding 2.Morphological operations. The descriptive features are extracted from the segmented lesion. The extracted feature values are used to compute the Total Dermatascopy Score (TDS), which is used to find the presence or absence of melanoma in dermoscopy images. Classification accuracy is calculated to assess the performance of the proposed algorithm.
关键词： Dermoscopy,Segmentation,Total Dermatoscopy Score(TDS),Feature Extraction,Melanoma,Skin cancer
更新于2025-09-23 15:22:29
-
[IEEE 2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC) - Mon Tresor, Plaine Magnien, Mauritius (2018.12.6-2018.12.7)] 2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC) - Optic Disc Segmentation Based on Correlation Feature Information
摘要： Glaucoma, one of the major causes of blindness, has been identified as a disease that causes the degeneration of the optic disc. An highly accurate automated detection of the optic disc (OD) has however been noted to be of great importance for the efficient diagnosis of the disease. This paper presents a study on an unsupervised approach usage of Haralick Correlation texture feature for the segmentation of optic disc in colored fundus retinal images. The grayscale and green channel of the colored fundus image are investigated. When compared with some methods in the literature, the experimental study of the proposed method achieved very high average accuracy rates of 98.59% and 98.36% using grayscale and green channel of the colored fundus image respectively on DRIVE database.
关键词： Optic disc,Segmentation,Correlation,Haralick Feature,image processing,Glaucoma
更新于2025-09-23 15:22:29
-
[IEEE 2018 5th International Conference on Systems and Informatics (ICSAI) - Nanjing, China (2018.11.10-2018.11.12)] 2018 5th International Conference on Systems and Informatics (ICSAI) - An Improved Image Segmentation Method Based on Maximum Fuzzy Entropy and Quantum Genetic Algorithm
摘要： Image segmentation is a key technology in the image processing field. In the traditional image segmentation method, the selection of the threshold is the core of the image segmentation. In the fuzzy set theory, the fuzzy entropy is used to find the optimal threshold of the image segmentation. In this paper, the maximum fuzzy entropy is used to determine the optimal threshold of the image segmentation. The quantum genetic algorithm is used to find the optimal threshold of the image segmentation. The experimental results show that the image segmentation method based on maximum fuzzy entropy and quantum genetic algorithm has better segmentation effect and higher efficiency.
关键词： Quantum genetic algorithm,Fuzzy entropy,Image segmentation
更新于2025-09-23 15:22:29
-
[IEEE 2018 4th International Conference on Science and Technology (ICST) - Yogyakarta (2018.8.7-2018.8.8)] 2018 4th International Conference on Science and Technology (ICST) - Segmenting Retinal Vessels with a Multi-scale Modified Dolph-Chebyshev Type I Function Matched Filter
摘要： In this paper, a new algorithm for retinal vessels segmentation is proposed. The algorithm is based on a multi-scale modified Dolph-Chebyshev type I function matched filter. Fundus images from the DRIVE and STARE databases are utilized to evaluate the performance of the proposed algorithm. Several performance indicators, such as specificity, sensitivity, and accuracy are used for performance evaluation. Experimental results show that for the DRIVE database, the results of the proposed algorithm are superior to those produced by all compared algorithms. When tested on pathological images from the STARE database, the proposed algorithm also performs better than all competing methods. This indicates that the proposed algorithm is suitable to be used in automatic retinal diseases diagnosis tools.
关键词： multi-scale matched filter,retinal vessels segmentation,fundus image,modified Dolph-Chebyshev function
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Krakow, Poland (2018.10.16-2018.10.18)] 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Renal Vessels Segmentation for Preoperative Planning in Percutaneous Nephrolithotomy
摘要： Kidney stones are a common clinical problem that affects up to 20% of the population. For larger kidney stones a percutaneous nephrolithotomy (PCNL) is the first line treatment. The procedure begins with a percutaneus puncture of the kidney to gain an access to intrarenal part of urinary tract, where the stone is located. Needle must reach precisely the targeted spot, passing through retroperitoneal cavity and kidney parenchyma without collision with adjacent organs or larger intrarenal blood vessels. In this paper, an algorithm dedicated for kidney arterial system segmentation is proposed. For validation, its’ results were compared with manual segmentations of ten exemplary 3D images providing satisfactory outcomes. The effectiveness and reliability of this algorithm was also demonstrated by incorporating its results into 3D anatomical model prepared as an image-guidance for real PCNL procedure. The description of the proposed algorithm and methodology of the construction of aforementioned model is presented in this paper. It consists of a registration of different phases of CT images together with segmentation of particular structures of interest (kidney, stones, urinary tract, kidney vasculature). The proposed solution allows to obtain 3D patient-specific models in a far more efficient manner than manually or by the use of semiautomated methods giving excellent and reliable visualization of intrarenal structures and by thus can stand clinically useful add in preoperative planning and intraoperative support in minimally invasive urological interventions.
关键词： personalized surgery,image guidance,intrarenal vessels segmentation,preoperative planning,percutaneous nephrolithotomy,kidney
更新于2025-09-23 15:22:29
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Extraction of Structural and Mineralogical Features from Hyperspectral Drill-Core Scans
摘要： For vein hosted mineralization such as encountered in porphyry systems, the documentation of the main alteration assemblages associated with specific vein generations is essential in understanding the geometry of the mineralized body. Hence, mineralogical and structural information are highly relevant for characterizing the system. In this paper, we present an approach for the extraction of both mineralogical and structural information from hyperspectral scans. We propose a parallel framework which includes a typical mineral mapping technique for the extraction of mineralogical information as well as a ridge detection method, for the extraction of veins, applied on mineral abundance maps. In the proposed framework, the abundance maps are obtained from hyperspectral VNIR-SWIR drill-core scans using a linear spectral unmixing technique. Drill cores hosting porphyry stockwork type mineralization are used for the evaluation of the proposed technique and the experimental results show that the method offers a tool for accurately characterizing the mineralized body.
关键词： Core scanning,feature extraction,hyperspectral imaging,mineral mapping,image segmentation
更新于2025-09-23 15:22:29
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - A Novel Fine Registration Technique for Very High Resolution Remote Sensing Images
摘要： This paper presents a novel registration noise (RN) estimation technique for fine registration of very high resolution (VHR) images. This is accomplished by using a two-step strategy to estimate and mitigate residual local misalignments in standardly registered VHR images. The first step takes advantages of the superpixel segmentation and frequency filtering to generate sparse superpixels as the basic objects for RN estimation. Then local rectification is employed for fine registration of the input image under the aid of RN information. More factors are taken into consideration in order to enhance the RN estimation performance. The proposed approach is designed in a fine registration strategy, which can effectively improve the pre-registration result. The experimental results obtained with real datasets confirm the effectiveness of the proposed method.
关键词： local rectification,superpixel segmentation,Fine registration,VHR image,sparse representation
更新于2025-09-23 15:22:29