- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 Fourth International Conference on Biosignals, Images and Instrumentation (ICBSII) - Chennai, India (2018.3.22-2018.3.24)] 2018 Fourth International Conference on Biosignals, Images and Instrumentation (ICBSII) - Examination of Digital Mammogram Using Otsu's Function and Watershed Segmentation
摘要： Breast malignancy is one of dangerous illness among the women community and premature detection may facilitate to diminish/eliminate breast cancer. Digital Mammogram (DM) is a commonly approved imaging scheme to record and scrutinize the breast cancer. This paper implements a novel hybrid approach based on the combination Otsu’s multi-thresholding and Water Shed Segmentation (WSS) to mine the suspicious sections from the DM. Initially, the multi-level thresholding using the Bat Algorithm (BA) driven Otsu with a bi-, tri- and four-level thresholding is implemented to pre-process the DM. Afterward, a marker controlled WSS is implemented to mine the infected division of DM. The mined section is then evaluated using the Haralick texture feature in order to know the severity of the disease by examining its texture feature. In this paper, DM dataset with dense, medium, low and normal breast regions are analyzed independently with the proposed approach. The experimental result of this paper confirms that, proposed method is very proficient in extracting the breast malignancy from the considered DM database.
关键词： Digital mammogram,Watershed segmentation,Bat algorithm,Otsu,GLCM features
更新于2025-09-10 09:29:36
-
[IEEE 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Chongqing (2018.6.27-2018.6.29)] 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Low Resolution Cell Image Edge Segmentation Based on Convolutional Neural Network
摘要： An low-resolution cell images captured by a lens-free imaging system is presented in this paper. The resolution of this cell images is impacted by the low and experimental cell segmentation methods to solve the original cell images is not robust and sensitive to noise. So based on the convolutional neural network, an optimized CSnet method is proposed in this paper for automatically segmenting cell. In the proposed method, the produced data set will be sent into the convolutional neural network firstly for training to obtain an optimized convolution neural network segmentation model. And then, the pre-divided images acquired by the lens-free imaging system are loaded into the segmentation model to get the segmentation images. Finally, our proposed method in this paper is tested in a neural network framework built in keras. The experimental results show that the accuracy of our proposed method can reach about 96%. At the same time, it also can implement batch segmentation automatically and make the problem of heavy task for segmentation better.
关键词： convolutional neural network,cell segmentation,Lensfree imaging,microfluidic chip
更新于2025-09-10 09:29:36
-
[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 - Flooded Area Detection from Uav Images Based on Densely Connected Recurrent Neural Networks
摘要： The emergence of small unmanned aerial vehicles (UAV) along with inexpensive sensors presents the opportunity to collect thousands of images after each natural disaster with high flexibility and easy maneuverability for rapid response and recovery. Despite the ease of data collection, data analysis of the big datasets remains a significant barrier for scientists and analysts. Here we propose an integration of densely connected CNN and RNN networks, which is able to accurately segment out semantically meaningful object boundaries with end-to-end learning. The proposed network is applied on UAV aerial images of flooded areas in Houston, TX. We achieved 96% accuracy in detecting flooded areas on a large UAV dataset.
关键词： semantic segmentation,RNN,flooded area detection,UAV,CNN
更新于2025-09-09 09:28:46
-
A Spectral–Temporal Patch-Based Missing Area Reconstruction for Time-Series Images
摘要： Clouds, cloud shadows (CCS), and numerous other factors will cause a missing data problem in passive remote sensing images. A well-known reconstruction method is the selection of a similar pixel (with an additional clear reference image) from the remaining clear part of an image to replace the missing pixel. Due to the merit of filling the missing value using a pixel acquired on the same image with the same sensor and the same date, this method is suitable for time-series applications when a time-series profile-based similar measure is utilized for selecting the similar pixel. Since the similar pixel is independently selected, the improper reference pixel or various accuracies obtained by different land covers causes the problem of salt-and-pepper noise in the reconstructed part of an image. To overcome these problems, this paper presents a spectral–temporal patch (STP)-based missing area reconstruction method for time-series images. First, the STP, the pixels of which have similar spectral and temporal evolution characteristics, is extracted using multi-temporal image segmentation. However, some STP have Missing Observations (STPMO) in the time series, which should be reconstructed. Next, for an STPMO, the most similar STP is selected as the reference STP; then, the mean and standard deviation of the STPMO is predicted using a linear regression method with the reference STP. Finally, the textural information, which is denoted by the spatial configuration of color or intensities of neighboring pixels, is extracted from the clear temporal-adjacent STP and “injected” into the missing area to obtain synthetic cloud-free images. We performed an STP-based missing area reconstruction experiment in Jiangzhou, Chongzuo, Guangxi with time-series images acquired by wide field view (WFV) onboard Chinese Gao Fen 1 on 12 different dates. The results indicate that the proposed method can effectively recover the missing information without salt-and-pepper noise in the reconstructed area; also, the reconstructed part of the image is consistent with the clear part without a false edge. The results confirm that the spectral information from the remaining clear part of the same image and textural information from the temporal-adjacent image can create seamless time-series images.
关键词： missing area reconstruction,cloud-free time-series image,cloud and cloud shadow,multi-temporal image segmentation
更新于2025-09-09 09:28:46
-
[Advances in Intelligent Systems and Computing] Recent Findings in Intelligent Computing Techniques Volume 709 (Proceedings of the 5th ICACNI 2017, Volume 3) || Performance Analysis of Classifiers and Future Directions for Image Analysis Based Leaf Disease Detection
摘要： Plants play a very important role in the environment to maintain ecosystem, so this is our responsibility to protect it by detected disease which appears in it. In the plant disease, most symptoms appear on leaf, so by performing some image analysis we can detect these diseases very fast and accurately. This paper includes survey of different techniques which are used in leaf disease detection. To detect plant disease color conversion, Canny and Sobel edge detectors are used initially and then some segmentation techniques, i.e., Otsu and k-means, are used; after then, feature extraction takes place and is classified with classification techniques.
关键词： K-means segmentation,Edge detection,GLCM and classification technique
更新于2025-09-09 09:28:46
-
[Advances in Intelligent Systems and Computing] First International Conference on Artificial Intelligence and Cognitive Computing Volume 815 (AICC 2018) || Bioinformatics and Image Processing—Detection of Plant Diseases
摘要： This paper gives an idea of how a combination of image processing along with bioinformatics detects deadly diseases in plants and agricultural crops. These kinds of diseases are not recognizable by bare human eyesight. First occurrence of these diseases is microscopic in nature. If plants are affected with such kind of diseases, there is deterioration in the quality of production of the plants. We need to correctly identify the symptoms, treat the diseases, and improve the production quality. Computers can help to make correct decision as well as can support industrialization of the detection work. We present in this paper a technique for image segmentation using HSI algorithm to classify various categories of diseases. This technique can also classify different types of plant diseases as well. GA has always proven itself to be very useful in image segmentation.
关键词： Image processing,Classification,Plant diseases,Image segmentation,Bioinformatics
更新于2025-09-09 09:28:46
-
[Lecture Notes in Electrical Engineering] Microelectronics, Electromagnetics and Telecommunications Volume 521 (Proceedings of the Fourth ICMEET 2018) || Extraction of Lesion and Tumor Region in Multi-modal Images Using Novel Self-organizing Map-Based Enhanced Fuzzy C-Means Clustering Algorithm
摘要： Analyzing the medical images and segmenting the same for detecting the tumor and lesion regions embedded within the images are quite a tedious process. On performing the task of tumor and lesion region detection, several intricacies arise and two of the major hindrances are time complexity and accuracy level sustainment. Resolving these two issues is the major concern of this paper and the authors have achieved it, which could be veri?ed from the ?gures of this paper. If the examination of the medical images obtained through modalities such as MRI and CT is clearly processed using an algorithm, preplanning of surgical procedures could be made with ease. The development of such an algorithm is focused by the authors, and the algorithm framed in this research ensemble the working of self-organizing map (SOM) and enhanced fuzzy C-means (EnFCM), and the authors have collectively named the algorithm as SOM-based EnFCM. The proposed algorithm has produced a high peak signal-to-noise ratio (PSNR) value of 60 dB and mean square error (MSE) of 0.06. The time required by the algorithm for processing 71 input slice images acquired through CT and MRI scans is around 6 s, and the overall accuracy exhibited by the algorithm is 48%. This has given a new and a dynamic approach, which could be greatly used by the radiologists in clinical practices. To contest and prove the ef?ciency of the SOM–EnFCM algorithm, the segmentation results of SOM and EnFCM algorithms while operating individually are compared.
关键词： Tumor identi?cation,Self-organized map algorithm,Enhanced fuzzy C-means algorithm,Tissue segmentation
更新于2025-09-09 09:28:46
-
[IEEE 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI) - Bangalore, India (2018.9.19-2018.9.22)] 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI) - Detection of Exudates in Diabetic Retinopathy
摘要： Diabetic Retinopathy (DR) is an eye abnormality in which the human retina will get affected and is becoming one of the leading cause of preventable blindness. In the world, it is found that nearly 4.8% of blindness is caused due to DR. Preliminary symptoms include the formation of microaneurysms, exudates and hemorrhages. Early detection of DR can save the vision of diabetes patients and manual diagnosis takes time and effort for confirmation. In this paper, a Computer-aided Automated Diagnosis (CAD) is developed to solve this problem. The proposed approach uses edge-based segmentation method for segmenting the optic disc and blood vessels more accurately than region-based methods, followed by extraction of most probable exudates regions, feature extraction and the classifier stage to detect the presence of exudates. This system achieved sensitivity 82.61%, specificity 92.31% and moreover an accuracy of 87.75% for DIARETDB dataset.
关键词： Blindness,edge-based segmentation,Diabetic Retinopathy,CAD,exudates,NPDR,PDR
更新于2025-09-09 09:28:46
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Cell Segmentation Via Region-Based Ellipse Fitting
摘要： We present a region based method for segmenting and splitting images of cells in an automatic and unsupervised manner. The detection of cell nuclei is based on the Bradley’s method. False positives are automatically identified and rejected based on shape and intensity features. Additionally, the proposed method is able to automatically detect and split touching cells. To do so, we employ a variant of a region based multi-ellipse fitting method that makes use of constraints on the area of the split cells. The quantitative assessment of the proposed method has been based on two challenging public datasets. This experimental study shows that the proposed method outperforms clearly existing methods for segmenting fluorescence microscopy images.
关键词： Bradleys method,Ellipses Fitting,Shape Analysis,Nuclei Segmentation
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) - Fully convolutional network and graph-based method for co-segmentation of retinal layer on macular OCT images
摘要： Retinal layer segmentation in optical coherence tomography (OCT) images is crucial for the diagnosis and study of retinal diseases. Graph-based methods are commonly used in layer segmentation. However, most of these methods require a lot of human efforts for determining an appropriate model to compute good edge weights. In this paper, we propose a novel automatic method for segmenting retinal layers in macular OCT images. Specially, we propose a new fully convolutional deep learning architecture with a side output layer to directly learn optimal graph-edge weights from raw pixels. The architecture can automatically learn multi-scale and multi-level features to generate accurate boundary probabilities as good edge weights without hand-crafted appropriate models. The boundaries are finalized by using graph segmentation method. The proposed method is evaluated on a dataset with 130 OCT B-scans. The experimental results show the mean absolute boundary positioning differences are 1.48±0.34 pixel.
关键词： fully convolutional network,retinal layer segmentation,graph-based framework,Optical coherence tomography (OCT)
更新于2025-09-09 09:28:46