Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
ABSTRAK
Dalam penelitian ini dirancang sebuah sistem multi-frequency microwave tomography berbasis PocketVNA  dan sistem mekanik stepper motor dan Arduino board yang digunakan untuk menggeser posisi sudut sepasang Vivaldi antenna dalam proses scanning pengukuran koefisien refleksi (S11), magnitude dan fase dari gelombang mikro setelah berinteraksi dengan objek yang diamati dalam eksperimen.  Antenna Vivaldi yang digunakan dapat bekerja pada range frekuensi 1.5 GHz sampai 9 GHz, PocketVNA beroperasi pada range frekuensi 500 kHz-4 GHz. Eksperimen untuk menguji unjuk kerjanya dengan berbagai jenis material yang berbeda bentuk dan ukuran. Data koefisien refleksi (S11) yang telah diperoleh di resolved dan direkonstruksi menjadi sebuah citra melalui MATLAB berbasis pendekatan Born. Rekonstruksi citra per single frequency dilakukan satu per satu secara berurutan dari frekuensi rendah-tinggi, dengan total 6 nilai frekuensi berbeda. Setelah itu dilakukan pendekatan multi frekuensi mengkombinasikan unsur stabilitas dari efek penggunaan frekuensi rendah dan unsur resolusi tinggi dari efek penggunaan frekuensi yang lebih tinggi. Penggunaan multi-frekuensi mereduksi masalah nonlinearitas dan menaikkan stabilitas sistem untuk hasil rekonstruksi citra yang lebih optimal menggunakan algoritma image fusion berbasis wavelet. Citra hasil proses algoritma image fusion cukup signifikan menaikkan kualitas image dibandingkan dengan individual image yang diperoleh dari hasil rekonstruksi pada penggunaan frekuensi tunggal tanpa proses image fusion.

---

ABSTRACT
A PocketVNA-based multi-frequency microwave tomography system and stepper motor and Arduino board-based mechanical system were used to shift the position of Vivaldi antenna pair angle in the scanning process of reflection coefficient (S11), magnitude and phase measurements of the microwaves interacted with observed objects. Vivaldi antenna works in the range of 1.5 GHz-9 GHz, while the PocketVNA operates in range of 500 kHz-4 GHz. Experiments were done to test the performance of the system with types of materials of different shapes and sizes. The reflection coefficient data (S11) resolved and reconstructed into an image via MATLAB based on Born approximation reconstruction algorithm. Image reconstruction per single frequency is done sequentially from low frequency-high frequency, with a total of 6 different frequency values. A multi-frequency approach will be done by combining the element of stability from the effect of using low frequencies and high-resolution element from the effect of relatively higher frequency usage. The use of multi-frequency reduces nonlinearity problem and increases the stability to get an optimal image reconstruction,. The image results from the image fusion algorithm process increase image quality compared to the individual images from the reconstruction results on single frequency usage without the image fusion process.

Abstrak :
Tomografi terkomputasi/CT memiliki keterbatasan dalam mendiferensiasikan material heterogen. Diantara solusinya adalah menggunakan CT dengan sinar-X bervariasi, lalu melakukan image fusion untuk menggabungkan citra proyeksi beda energi tersebut. Dalam penelitian ini, digunakan algoritma image fusion berupa Discrete Wavelet Transform (DWT) dan Non Subsampled Contourlet Transform (NSCT) untuk mengamati performanya dalam meningkatkan kualitas sistem CT sinar-X di BRIN. Digunakan tiga jenis sampel: threaded pipe union PVC, busi, dan set sampel multimaterial berupa lima silinder beda material. Dihasilkan 7 set slice citra yang difusi menggunakan MATLAB. Dari hasil fusi, didapat bahwa algoritma DWT dengan aturan fusi max-max memberikan hasil fusi dengan kontras tertinggi, dengan rerata STD 0.1852 ± 0.0002. Metode NSCT memberikan kesamaan per piksel tertinggi antara citra sumber dan citra fusi, dengan rerata FMI 0.9284 ± 0.0016 dan PSNR takhingga dari kalkulasi MATLAB. Algoritma DWT dengan aturan fusi mean-mean memberikan kesamaan struktural terbaik dengan rerata SSIM 0.9221 ± 0.0004. Namun, evaluasi visual menunjukkan kedua algoritma tersebut kurang efektif menghilangkan noise dan artifact. Oleh karena itu, diperlukan peningkatan kualitas pra-pemrosesan citra hasil rekonstruksi sebelum fusi, pemilihan sampel yang lebih sesuai dari tipe material hingga geometri sampel, serta bereksperimen dengan bermacam-macam algoritma fusi lainnya ......Computed tomography/CT has limitations in differentiating heterogeneous materials. Among the solutions is to use CT with varying X-rays and image fusion to combine the different energy projection images. In this study, Discrete Wavelet Transform (DWT) and Non Subsampled Contourlet Transform (NSCT) image fusion algorithms were used to observe their performance in improving the quality of the X-ray CT system at BRIN. Three types of samples were used: PVC threaded pipe union, spark plugs, and a multimaterial sample set of five cylinders of different materials. Seven sets of image slices were fused using MATLAB. From the fusion results, it was found that the DWT algorithm with max-max fusion rule gave the highest contrast fusion results, with a mean STD of 0.1852 ± 0.0002. The NSCT method provides the highest per-pixel similarity between the source image and the fused image, with a mean FMI of 0.9284 ± 0.0016 and infinite PSNR from MATLAB calculations. The DWT algorithm with mean-mean fusion rule provided the best structural similarity with a mean SSIM of 0.9221 ± 0.0004. However, visual evaluation showed that both algorithms were less effective at removing noise and artifacts. Therefore, it is necessary to improve the pre-processing quality of the reconstructed image before fusion, select more suitable samples from material type to sample geometry, and experiment with various other fusion algorithms.

Abstrak :
Breast cancer is mostl deaddly disease for women. In oreder to cure the breast cancer disease, the location of the cancer should be exactly determined for futher treatments. Its location can be determined by using nuclear diagnosis technique utilizing a gamma camera....

Abstrak :
Pada penelitian ini dilakukan penggabungan citra dari dua sumber energi yang berbeda berdasarkan kerangka kerja deep learning. Tujuannya untuk menghasilkan citra objek dengan material penyusun lebih dari satu yang lebih baik dan lebih informatif. Hasil penelitian menunjukkan bahwa metode yang diajukan dapat menghasilkan citra yang lebih minim noise, kontras yang baik, dan dapat mempertahankan struktur objek. Evaluasi kualitas citra menggunakan metrik objektif, seperti FMIdct, FMIpixel, FMIw, Nabf, dan SSIM, menunjukkan peningkatan dibandingkan dengan metode tradisional. Rata-rata nilai FMI yang lebih tinggi menunjukan bahwa keterkaitan informasi hasil fusi dengan kedua sumber lebih baik dibanding kedua metode pembanding. Nilai Nabf yang lebih rendah menunjukan noise yang muncul akibat dari proses fusi lebih minim dibanding kedua metode lainnya. Nilai SSIM pada hasil fusi menggunakan metode ini juga memiliki nilai yang lebih tinggi dibanding dengan kedua metode yang dibandingkan. Sampel yang memiliki rata-rata nilai metrik terbaik adalah busi dengan nilai tertinggi metrik evaluasi FMIdct adalah 2,96×10^(-1), nilai FMIpixel adalah 9,70×10^(-1), nilai FMIw adalah 3,69×10^(-1), nilai SSIM adalah 9,92×10^(-1), dan nilai Nabf terrendah adalah 3,82×10^(-3). Kesimpulannya, penelitian ini berhasil mengembangkan pendekatan baru dalam penggabungan citra CT menggunakan framework VGG19. Metode ini memiliki potensi untuk meningkatkan diagnosis dan analisis non-medis seperti pada evaluasi kualitas produksi pada industri manufaktur dengan menghasilkan citra yang lebih informatif dan akurat. ......In this research, images from two different energy sources are combined based on a deep learning framework. The goal is to produce better and more informative images of objects with more than one constituent material. The results show that the proposed method can produce images with less noise, good contrast, and can maintain the structure of the object. Evaluation of image quality using objective metrics, such as FMIdct, FMIpixel, FMIw, Nabf, and SSIM, shows improvement compared to traditional methods. The higher average FMI value indicates that the fused information is better related to the two sources than the two comparison methods. The lower Nabf value indicates that the noise arising from the fusion process is more minimal than the other two methods. The SSIM value in the fusion results using this method also has a higher value than the two methods compared. The sample that has the best average metric value is the spark plug with the highest value of FMIdct evaluation metric is 2.96×10-1, FMIpixel value is 9.70×10-1, FMIw value is 3.69×10-1, SSIM value is 9.92×10-1, and the lowest Nabf value is 3.82×10-3. In conclusion, this study successfully developed a new approach in CT image fusion using the VGG19 framework. This method has the potential to improve non-medical diagnosis and analysis such as production quality evaluation in the manufacturing industry by producing more informative and accurate images.

Abstrak :
This book offers a comprehensive introduction to advanced methods for image and video analysis and processing. It covers deraining, dehazing, inpainting, fusion, watermarking and stitching. It describes techniques for face and lip recognition, facial expression recognition, lip reading in videos, moving object tracking, dynamic scene classification, among others. The book combines the latest machine learning methods with computer vision applications, covering topics such as event recognition based on deep learning，dynamic scene classification based on topic model, person re-identification based on metric learning and behavior analysis. It also offers a systematic introduction to image evaluation criteria showing how to use them in different experimental contexts. The book offers an example-based practical guide to researchers, professionals and graduate students dealing with advanced problems in image analysis and computer vision.