scholarly journals Gaussian Mixture Model for MRI Image Segmentation to Build a Three-Dimensional Image on Brain Tumor Area

MATEMATIKA ◽  
2020 ◽  
Vol 36 (3) ◽  
pp. 217-234
Author(s):  
Anindya Apriliyanti Pravitasari ◽  
Nur Iriawan ◽  
Siti Azizah Nurul Solichah ◽  
Irhamah Irhamah ◽  
Kartika Fithriasari ◽  
...  
Keyword(s):  
Brain Tumor ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Three Dimensional ◽  
Region Of Interest ◽  
Gaussian Mixture ◽  
Magnetic Resonance Imaging Mri ◽  
Healthy Part ◽  
Mri Image ◽  
Tumor Area

A brain tumor is one of the deadly diseases that attack the central and nervoussystem. The treatment of brain tumor, need high accuracy and precision. Brain tumordetection through Magnetic Resonance Imaging (MRI) has two-dimensional output withthree perspectives, namely sagittal, coronal, and axial. These different perspectives needto be seen one by one to determine the location and size of the tumor. Tosolve the problem, this study constructs the three-dimensional visualization perspective ofMRI images. The tumor area in MRI image is segmented as a region of interest (ROI) byemploying the Gaussian Mixture Model (GMM) with Expectation-Maximization as theoptimization technique. These couple segmentation methods have revealed significant gainas a clear boundary of the tumor area to separate from the healthy part of the brain andan estimated tumor volume from sagittal, coronal, and axial perspectives. Furthermore,these findings have been successfully visualized in 3D construction of the tumor positionon the left side of the patient’s head with an estimated volume of 749mm3.

Moving Objects Detection Algorithm Based on Three-Dimensional Gaussian Mixture Codebook Model Using XYZ Color Model

2013 ◽  
Vol 347-350 ◽  
pp. 3505-3509 ◽  
Author(s):  
Jin Huang ◽  
Wei Dong Jin ◽  
Na Qin
Keyword(s):  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Moving Objects ◽  
Three Dimensional ◽  
Gaussian Mixture ◽  
Detection Algorithm ◽  
Color Model ◽  
Moving Objects Detection ◽  
Objects Detection ◽  
Model Algorithm

In order to reduce the difficulty of adjusting parameters for the codebook model and the computational complexity of probability distribution for the Gaussian mixture model in intelligent visual surveillance, a moving objects detection algorithm based on three-dimensional Gaussian mixture codebook model using XYZ color model is proposed. In this algorithm, a codebook model based on XYZ color model is built, and then the Gaussian model based on X, Y and Z components in codewords is established respectively. In this way, the characteristic of the three-dimensional Gaussian mixture model for the codebook model is obtained. The experimental results show that the proposed algorithm can attain higher real-time capability and its average frame rate is about 16.7 frames per second, while it is about 8.3 frames per second for the iGMM (improved Gaussian mixture model) algorithm, about 6.1 frames per second for the BM (Bayes model) algorithm, about 12.5 frames per second for the GCBM (Gaussian-based codebook model) algorithm, and about 8.5 frames per second for the CBM (codebook model) algorithm in the comparative experiments. Furthermore the proposed algorithm can obtain better detection quantity.

Algorithm of Moving Vehicle Detection by Improved Gaussian Mixture Model Based on ROI

2015 ◽  
Vol 734 ◽  
pp. 463-467 ◽  
Author(s):  
Pan Pan Zhang ◽  
Chun Yang Mu ◽  
Xing Ma ◽  
Fu Lu Xu
Keyword(s):  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Region Of Interest ◽  
Gaussian Mixture ◽  
Background Model ◽  
Morphological Filter ◽  
Improved Method ◽  
Moving Vehicle ◽  
Model Based ◽  
Moving Vehicle Detection

Detection of moving object is a hot topic in computer vision. Traditionally, it is detected for every pixel in whole image by Gaussian mixture background model, which may waste more time and space. In order to improving the computational efficiency, an advanced Gaussian mixture model based on Region of Interest was proposed. Firstly, the solution finds out the most probably region where the target may turn up. And then Gaussian mixture background model is built in this area. Finally, morphological filter algorithm is used for improving integrity of the detected targets. Results show that the improved method could have a more perfect detection but no more time increasing than typical method.

scholarly journals Research on Panoramic Stitching Algorithm of Lateral Cranial Sequence Images in Dental Multifunctional Cone Beam Computed Tomography

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2200
Author(s):  
Junyuan Liu ◽  
Xi Li ◽  
Siwan Shen ◽  
Xiaoming Jiang ◽  
Wang Chen ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Cone Beam Computed Tomography ◽  
Region Of Interest ◽  
Gaussian Mixture ◽  
Block Matching ◽  
Cone Beam ◽  
Fusion Algorithm ◽  
Panoramic Images

In the design of dental multifunctional Cone Beam Computed Tomography, the linear scanning strategy not only saves equipment cost, but also avoids the demand for patients to be repositioned when acquiring lateral cranial sequence images. In order to obtain panoramic images, we propose a local normalized cross-correlation stitching algorithm based on Gaussian Mixture Model. Firstly, the Block-Matching and 3D filtering algorithm is used to remove quantum and impulse noises according to the characteristics of X-ray images; Then, the segmentation of the irrelevant region and the extraction of the region of interest are performed by Gaussian Mixture Model; The locally normalized cross-relation is used to complete the registration with the multi-resolution strategy based on wavelet transform and Particle Swarm Optimization algorithm; Finally, image fusion is achieved by the weighted smoothing fusion algorithm. The experimental results show that the panoramic image obtained by this method has significant performance in both subjective vision and objective quality evaluation and can be applied to preoperative diagnosis of clinical dental deformity and postoperative effect evaluation.

scholarly journals Sistem Pengukur Kecepatan Kendaraan Berbasis Pengolahan Video

2015 ◽  
Vol 5 (2) ◽  
pp. 177
Author(s):  
Satrio Sani Sadewo ◽  
Raden Sumiharto ◽  
Ika Candradewi
Keyword(s):  
Light Intensity ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Background Subtraction ◽  
Region Of Interest ◽  
Gaussian Mixture ◽  
Average Speed ◽  
Speed Measurement ◽  
Measurement Validation ◽  
Model Region

AbstrakSistem pengukur kecepatan kendaraan berbasis pengolahan video ini merupakan salah satu sistem yang memanfaatkan sistem pengolahan citra digital sebagai pendeteksi kendaraan dan mengukur kecepatannya. Metode yang digunakan dalam sistem ini adalah background subtraction dengan algoritma Gaussian Mixture Model (GMM). Background subtraction akan memisahkan antara background dengan objek yang dideteksi, yaitu kendaraan. Koordinat titik tengah objek dijadikan sebagai nilai perpindahan objek dalam satuan piksel. Jarak sesungguhnya diukur dalam satuan meter. Jarak pada citra dibatasi dengan region of interest (ROI) sebesar 160 piksel. Setelah diperoleh waktu perpindahan tiap pikselnya maka nilai piksel/detik dikonversikan menjadi km/jam.Uji coba sistem dilakukan pada validasi kecepatan, pengukuran kecepatan, dan pengaruh intensitas cahaya. Proses validasi kecepatan menggunakan nilai kecepatan rata-rata 3 frame awal sebagai acuan untuk pengukuran kecepatan di frame berikutnya. Akurasi nilai kecepatan rata-rata 3 frame awal ini memberikan  persentase eror 1,92 % - 15,75 % sedangkan ketika validasi tersebut dilakukan pada pembacaan keseluruhan frame video menghasilkan rentang eror 1,21 % - 21,37 %. Sistem bekerja dengan baik pada kondisi pagi, siang, dan sore hari dengan rentang intensitas cahaya 600-1900 lux,  sedangkan pada malam hari dengan rentang intensitas cahaya 0-5 lux, sistem tidak bisa bekerja dengan baik. Kata kunci— pengolahan video, pengukuran kecepatan, background subtraction, gaussian mixture model, region of interest  AbstractThis system is implemented by digital image processing to detect the objects and measure the speed. This system using background subtraction method with Gaussian Mixture Model (GMM) algorithm. Background subtraction will separate background and detected objects. Coordinates of the objects midpoint used as the the object moving value in pixel. The actual distance also measured in meters where the distance is limited by region of interest (ROI). The ROI is 160 pixel. Having obtained the moving objects time from previous frame to current frame so the value of pixel/s can converted to km/h.System testing the measurement validation, calculate the speed after being validated, and the influence of light intensity. The speed validation process uses average speed of early three frames speed as the reference for the speed measurement in the next frame. The average speed accuracy of 3 frames early gives a percentage error about 1,92% - 15,75%. When validation is performed on the entire reading frame of video, it produces an error range 1,21% - 21,37%. The system works well in the morning, afternoon, and evening conditions with light intensity about 600-1900 lux. While at night with 0-5 lux light intensity range, the system can’t work properly. Keywords— video processing, speed measurement, background subtraction, gaussian mixture model, region of interest

Sign in / Sign up

Export Citation Format

Share Document