Variasi Thresholding untuk Segmentasi Pembuluh Darah Citra Retina

Desiani, Anita; Zayanti, Des Alwine; Primartha, Rifkie; Efriliyanti, Filda; Andriani, Nur Avisa Calista

doi:10.26418/jp.v7i2.47205

Cited by 7 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…𝐺(𝑥, 𝑦) = { 1, 𝑓(𝑥, 𝑦) > 𝑇 { 0, 𝑓(𝑥, 𝑦) ≤ 𝑇 (2) Dengan T nilai ambang batas, f (x,y) merupakan pasangan koordinat piksel pada citra dan G (x,y) adalah koordinat titik piksel pada citra biner. (Desiani et al, 2021)…”

Section: Tresholdingunclassified

Analisis Perbandingan Hasil Pengolahan Citra Asli Dan Cropping Untuk Mengidentifikasi Karakteristik Tanaman Selada Menggunakan Metode Morfologi Dan Ekstrasi Ciri

Fadjeri¹,

Kurniatin²,

Ariyanto³

et al. 2023

JIS

View full text Add to dashboard Cite

Penelitian ini bertujuan untuk mengetahui hasil perbandingan tanaman selada menggunakan metode morfologi dan ekstrasi ciri dari proses kroping pada citra dan citra asli. Teknik kroping merupakan teknik memperkecil ukuran citra. Sedangkan citra asli merupakan citra hasil dari tangkapan alat citra digital. Pada pengolahan citra digital terdapat teknik atau metode morfologi pada citra. Sebelum tahap morfologi, citra akan di proses menggunakan 2 metode yaitu metode kroping pada citra dan citra asi atau tanpa kroping. Setelah proses kroping atau tanpa kroping citra di olah menjadi citra abu-abu (grayscale), selanjutnya citra akan di proses menggunakan deteksi tepi untuk memperoleh hasil bagian tepi pada citra. Kemudian citra diubah menjadi bentuk biner (0 dan 1) atau sering disebut citra biner. Setelah pengolahan citra digital selesai kemudian tahap morfologi, dimana terdapat proses dilasi dan erosi. Proses ini bertujuan untuk mempertebal dan menipiskan hasil citra atau untuk meningkatkan hasil pendeteksian pada citra atau objek. Tahap selanjutnya yaitu proses ekstrasi ciri, dimana proses ini bertujuan untuk memperoleh nilai matematis pada sebuah citra.Proses ekstrasi ciri pada citra dilakukan sebanyak dua kali yaitu ekstrasi ciri citra asli dan ekstrasi ciri citra kroping. Dari hasil ekstrasi dapat diperoleh nilai matematis citra dengan ketentuan luas, keliling, kebundaran, kerampingan, panjang dan lebar. Proses ekstrasi ciri yang pertama atau citra asli didapatkan nilai matematis dengan rentang atau rata-rata luas 51.667.147.953.650.600, keliling 58.594.529.654.404.700, kebundaran 1.000.149.515.265.920, kerampingan 30.741.557.873.547.900, panjang 3.496.560.371.093.740 dan lebar 8.489.952.148.437.490. Sedangkan proses ekstrasi ciri kroping pada citra didapat nilai matematis citra dengan rentang atau rata-rata luas 83.364.228.960.567.300, keliling 26.081.033.779.659.700, kebundara 10.002.171.123.342.300, kerampingan 41.652.085.165.818.800, panjang 27.072.842.968.749.900 dan lebar 7.598.551.957.031.240.

show abstract

Section: Tresholdingunclassified

Analisis Perbandingan Hasil Pengolahan Citra Asli Dan Cropping Untuk Mengidentifikasi Karakteristik Tanaman Selada Menggunakan Metode Morfologi Dan Ekstrasi Ciri

Fadjeri¹,

Kurniatin²,

Ariyanto³

et al. 2023

JIS

View full text Add to dashboard Cite

show abstract

“…Hasil dari metode segmentasi berupa citra biner ditandai dengan tampilan warna putih atau disimbolkan 1 jika nilai piksel lebih besar dari nilai ambang (threshold), maka latar belakang gambar menjadi warna hitam atau 0. (Desiani et al, 2021)…”

Section: Tresholdingunclassified

Karakteristik Morfologi Tanaman Selada Menggunakan Pengolahan Citra Digital

Fadjeri

Saputra

Ariyanto

et al. 2022

JIS

View full text Add to dashboard Cite

The aim of this study is to find out characteristics of Green Rapid lettuce with digital image processing using morphological technique on image and first order statistical feature extraction. In digital image processing, the original images were processed to be RGB image and then processed again to be grayscale one. The grayscale images were processed to be biner image so that the image can be changed into biner form (0 and 1). In morphological process, this study used edge detection, dilation, and erosion. The final stage of morphological process used feature extraction process to find out image morphological characteristics which can be described mathematically. The result of extraction showed its samples within range or average area about 9.593.622.205.915.820 pixels, perimeter about 8.427.724.410.694.360 pixels, length about 829.877.174.308.893 pixels, and width about 1.654.002.663.010.820 pixels

show abstract

“…If the point (r1, s1) shifts, there would be a change in the gray color gradient. The Equation obtained from the curve can be seen in Equation (2) [10].…”

Section: Contrast Stretchingmentioning

confidence: 99%

“…The disadvantage of the Adaptive Thresholding method is that it can be only segmented bright quality images, so that the diversity of light intensity can affect this method [6]. Several studies performed segmentation of blood vessels in retinal images, including [7][8][9][10]. Research [7] applied the Otsu Thresholding method with image enhancement using the Frangi Filter, which produced an average accuracy and sensitivity value of 96.58% and 97.03% in the DRIVE dataset, while in the STARE dataset, it is 93.76% and 49.7%.…”

Section: Introductionmentioning

confidence: 99%

“…Then research [9] applied Hessian Matrix, and Random walks with the results of accuracy and specificity of 93.76% and 98.24%, respectively. In addition, research [10] applied Adaptive Thresholding with image enhancement using CLAHE and 2D-Gabor Filter resulted in an average accuracy and specificity of 91% and 97% on the STARE dataset, respectively. Unfortunately, the four studies still had a low sensitivity value below 65%.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combination Contrast Stretching and Adaptive Thresholding for Retinal Blood Vessel Image

Desiani,

Irmeilyana,

Cahyono

et al. 2022

matrik

View full text Add to dashboard Cite

To diagnose diabetic retinopathy is to segment the blood vessels of the retinal, but the retinal images in the DRIVE and STARE datasets have varying contrast, so the enhancement is needed to obtain a stable image contrast. In this study, image enhancement was performed using the Contrast Stretching and continued with segmentation using the Adaptive Thresholding on retinal images. The image that has been extracted with green channels will be enhanced with Contras Stretching and segmented with Adaptive Thresholding to produce a binary image of retinal blood vessels. The purpose of this study was to combine image enhancement techniques and segmentation methods to obtain valid and accurate retinal blood vessels. The test results on DRIVE were 95.68 for accuracy, 65.05% for sensitivity, and 98.56% for specificity. The test results of Adam Hoover’s ground truth on STARE were 96.13% for, 65.90% for sensitivity, and 98.48% for specificity. The test results for Valentina Kouznetsova’s ground truth on the STARE were 93.89% for accuracy, 52.15% for sensitivity, and 99.02% for specificity. The conclusion obtained is that the processing results on the DRIVE and STARE datasets are very good with respect to their accuracy and specificity values. This method still needs to be developed to be able to detect thin blood vessels with the aim of being able to improve and increase the sensitivity value obtained.

show abstract

Variasi Thresholding untuk Segmentasi Pembuluh Darah Citra Retina

Cited by 7 publications

References 18 publications

Analisis Perbandingan Hasil Pengolahan Citra Asli Dan Cropping Untuk Mengidentifikasi Karakteristik Tanaman Selada Menggunakan Metode Morfologi Dan Ekstrasi Ciri

Analisis Perbandingan Hasil Pengolahan Citra Asli Dan Cropping Untuk Mengidentifikasi Karakteristik Tanaman Selada Menggunakan Metode Morfologi Dan Ekstrasi Ciri

Karakteristik Morfologi Tanaman Selada Menggunakan Pengolahan Citra Digital

Combination Contrast Stretching and Adaptive Thresholding for Retinal Blood Vessel Image

Contact Info

Product

Resources

About