Color canals modification with canny edge detection and morphological reconstruction for cell nucleus segmentation and area measurement in normal Pap smear images

Author(s):  
Dwiza Riana ◽  
Dyah Ekashanti Octorina Dewi ◽  
Dwi H. Widyantoro ◽  
Tati Latifah R. Mengko
2018 ◽  
Vol 8 (2) ◽  
pp. 31-42
Author(s):  
Ahmad Ahsanudin Syafawi

Dalam menentukan luas objek persegi, persegi panjang, dan lingkaran diperlukanlah sebuah penggaris untuk mendapatkan nilai luasannya, agar lebih mudah dan praktis dapat dibantu dengan sebuah web camera dengan cara mengcapture gambar sampel objek yang ingin diketahui luasnya. Image Prosessing adalah suatu proses yang digunakan untuk mengolah citra atau gambar untuk mendapatkan citra yang lebih bagus mengunakan perangkat sistem komputer. Untuk mendapatkan perolehan panjang (X,Y) dari gambar dapat diukur setelah melewati beberapa tahapan di image prosessing yaitu dengan konversi citra dari RGB, HSV dan deteksi tepi canny, lalu terdapatlah nilai luasan dari hasil pengukuran objek. Metode Canny sendiri merupakan deteksi tepi paling baik ketika digunakan untuk mendeteksi tepi objek,  sehingga hasil deteksi tepi tersebut dapat diambil informasi yang berguna dari citra tersebut. Dengan pengukuran luas secara manual dan secara otomatis terdapat presentase error kurang lebih 5%, hasil luas objek tersebut sudah cukup akurat namun terdapat masalah jika dalam pembuatan objek kurang presisi, peletakan objek yang miring/kurang tegap dan pencahayaan yang kurang mengakibatkan kurangnya tingkat akurasi.In determining the area of a square, rectangle, and circle object a ruler is needed to get the area value, so that it can be easier and more practical to be assisted by a web camera by capturing the image of the object sample that you want to know the area. Image Prosessing is a process used to process images or images to get better images using computer system devices. To get the long gain (X, Y) from the image can be measured after passing through several stages in image processing that is by image conversion from RGB, HSV and canny edge detection, then there is an area value from the object measurement results. The Canny method itself is the best edge detection when used to detect the edge of an object, so that the useful information of the edge detection can be retrieved from the image. With the area measurement manually and automatically there is a percentage error of approximately 5%, the object's width results are quite accurate but there is a problem if the object is less precise in making objects, sloping / less robust object laying and less lighting result in a lack of accuracy.


2018 ◽  
Vol 8 (2) ◽  
pp. 31-42
Author(s):  
Ahmad Ahsanudin Syafawi

Dalam menentukan luas objek persegi, persegi panjang, dan lingkaran diperlukanlah sebuah penggaris untuk mendapatkan nilai luasannya, agar lebih mudah dan praktis dapat dibantu dengan sebuah web camera dengan cara mengcapture gambar sampel objek yang ingin diketahui luasnya. Image Prosessing adalah suatu proses yang digunakan untuk mengolah citra atau gambar untuk mendapatkan citra yang lebih bagus mengunakan perangkat sistem komputer. Untuk mendapatkan perolehan panjang (X,Y) dari gambar dapat diukur setelah melewati beberapa tahapan di image prosessing yaitu dengan konversi citra dari RGB, HSV dan deteksi tepi canny, lalu terdapatlah nilai luasan dari hasil pengukuran objek. Metode Canny sendiri merupakan deteksi tepi paling baik ketika digunakan untuk mendeteksi tepi objek,  sehingga hasil deteksi tepi tersebut dapat diambil informasi yang berguna dari citra tersebut. Dengan pengukuran luas secara manual dan secara otomatis terdapat presentase error kurang lebih 5%, hasil luas objek tersebut sudah cukup akurat namun terdapat masalah jika dalam pembuatan objek kurang presisi, peletakan objek yang miring/kurang tegap dan pencahayaan yang kurang mengakibatkan kurangnya tingkat akurasi.In determining the area of a square, rectangle, and circle object a ruler is needed to get the area value, so that it can be easier and more practical to be assisted by a web camera by capturing the image of the object sample that you want to know the area. Image Prosessing is a process used to process images or images to get better images using computer system devices. To get the long gain (X, Y) from the image can be measured after passing through several stages in image processing that is by image conversion from RGB, HSV and canny edge detection, then there is an area value from the object measurement results. The Canny method itself is the best edge detection when used to detect the edge of an object, so that the useful information of the edge detection can be retrieved from the image. With the area measurement manually and automatically there is a percentage error of approximately 5%, the object's width results are quite accurate but there is a problem if the object is less precise in making objects, sloping / less robust object laying and less lighting result in a lack of accuracy.


2012 ◽  
Vol 220-223 ◽  
pp. 1279-1283 ◽  
Author(s):  
Li Hong Dong ◽  
Peng Bing Zhao

The coal-rock interface recognition is one of the critical automated technologies in the fully mechanized mining face. The poor working conditions underground result in the seriously polluted edge information of the coal-rock interface, which affects the positioning precision of the shearer drum. The Gaussian filter parameters and the high-low thresholds are difficult to select in the traditional Canny algorithm, which causes the information loss of gradual edge and the phenomenon of false edge. Consequently, this paper presents an improved Canny edge detection algorithm, which adopts the adaptive median filtering algorithm to calculate the thresholds of Canny algorithm according to the grayscale mean and variance mean. This algorithm can protect the image edge details better and can restrain the blurred image edge. Experimental results show that this algorithm has improved the edge extraction effect under the case of noise interference and improved the detection precision and accuracy of the coal-rock image effectively.


Optik ◽  
2014 ◽  
Vol 125 (15) ◽  
pp. 3946-3953 ◽  
Author(s):  
Fei Hao ◽  
Jinfei Shi ◽  
Zhisheng Zhang ◽  
Ruwen Chen ◽  
Songqing Zhu

Sign in / Sign up

Export Citation Format

Share Document