Feature Extraction of Cervical Pap Smear Images Using Fuzzy Edge Detection Method

Hemalatha, K.; Rani, K. Usha

doi:10.1007/978-981-10-3223-3_8

Cited by 9 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Proses image processing dengan teknik deteksi tepi merupakan proses yang digunakan untuk menghasilkan garis batas atau tepi-tepi dari objek citra untuk menandai bagian citra secara lebih detail dan memperbaiki detail citra yang kabur sehingga dapat menentukan jenis informasi awal terkait suatu penyakit [12]. Penelitian mengenai deteksi tepi sudah dilakukan [13] dimana proses deteksi dapat memudahkan dalam melakukan segmentasi, penelitian lain juga dilakukan [14] dimana menghasilkan segmentasi yang bagus setelah dilakukan deteksi tepi.…”

Section: Pendahuluanunclassified

Klasifikasi Alexnet dan Deteksi Tepi Canny untuk Identifikasi Citra Repomedunm

Riana

Saputri

Hadianti

2023

jidt

View full text Add to dashboard Cite

Deteksi dini kanker serviks dapat mencegah dan menunda kematian, salah satunya dengan memanfaatkan teknologi komputer untuk mendiagnosa berbagai jenis sel kanker serviks. Penelitian dilakukan terhadap citra Pap smear yang diambil dari RepomedUNM dengan tujuan mengklasifikasikan citra Pap smear menjadi dua kelas yaitu sel normal dan sel abnormal dengan menggunakan metode AlexNet. Proses awal klasifikasi citra terdiri dari mengubah ukuran dan mengubah citra asli menjadi skala abu-abu. Penelitian ini juga bertujuan untuk mendeteksi tepi citra pap smear yang terdiri dari dua kelas yaitu sel normal dan sel koilocyt. Deteksi tepi menggunakan metode Canny untuk mendapatkan nilai luas, keliling dan diameter sel sitoplasma dan inti sel (nukleus). Proses deteksi tepi Canny terdiri dari proses cropping, mengubah citra asli menjadi grayscale, dan segmentasi citra menggunakan metode thresholding. Hasil klasifikasi 2000 citra Pap smear menghasilkan akurasi sebesar 97,66% dan hasil deteksi tepi dari 50 citra Pap smear dengan metode Canny mampu memberikan hasil yang baik dengan mendeteksi tepi citra sebenarnya dan hasilnya.

show abstract

Section: Pendahuluanunclassified

Klasifikasi Alexnet dan Deteksi Tepi Canny untuk Identifikasi Citra Repomedunm

Riana

Saputri

Hadianti

2023

jidt

View full text Add to dashboard Cite

show abstract

“…Edge detection with a fuzzy system is used to segment cytoplasm and nucleus. Hemalatha and Rani [11] suggested that the proposed enhanced edge detection technique based on a fuzzy approach gives better accuracy for cervical cancer detection. Bhargava et al [12] extracted histogram of oriented gradients features from segmented cervical cells and performed classification to categorize the cervical cells into cancer and non-cancerous using artificial neural network, k-nearest neighboring and support vector machine.…”

Section: Literature Surveymentioning

confidence: 99%

Cervical cancer diagnosis based on cytology pap smear image classification using fractional coefficient and machine learning classifiers

Kalbhor¹,

Shinde²,

Jude

2022

TELKOMNIKA

View full text Add to dashboard Cite

Doctors and pathologists have long been concerned about determining the malignancy from cell images. This task is laborious, time-consuming and needs expertise. Due to this reason, automated systems assist pathologists in providing a second opinion to arrive at accurate decision based on cytology images. The classification of cytology images has always been a difficult challenge among the various image analysis approaches due to its extreme intricacy. The thrust for early diagnosis of cervical cancer has always fuelled the research in medical image analysis for cancer detection. In this paper, an investigative study for the classification of cytology images is proposed. The proposed study uses the discrete coefficient transform (DCT) coefficient and Haar transform coefficients as features. These features are given as a input to seven different machine learning algorithms for normal and abnormal pap smear images classification. In order to optimize the feature size, fractional coefficients are used to form the five different sizes of feature vectors. In the proposed work, DCT transform has given the highest classification accuracy of 81.11%. Comparing the different machine learning algorithms the overall best performance is given by the random forest classifier.

show abstract

“…Author name Description Methods used Xu, Tao, et al [3] For the purpose of testing image-based cervical disease classification algorithms, this paper offered a brand-new picture dataset coupled with expert-annotated diagnoses.…”

Section: Table 1: Related Work On the Detection Of Cervical Cancer By...mentioning

confidence: 99%

Image processing techniques for the segmentation of cervical cancer

Poornappriya

Gopinath

2022

ijhs

View full text Add to dashboard Cite

The most prevalent type of cancer in women worldwide is uterine cervical cancer. The majority of cervical cancer (CC) cases can be avoided by participating in screening programmes that look for precancerous lesions. Colposcopic cervigrams or images from digital colposcopy have been acquired in raw form. This study presents a novel framework that combines image enhancement, pre-processing, and image segmentation to identify cervical cancer. Three phases make up this framework: the Dual Tree Discrete Wavelet Transform (DTDWT) for pre-processing, the Curvelet transform and Contour Transform (CC) for image improvement, and the K-means clustering for segmentation.

show abstract

Feature Extraction of Cervical Pap Smear Images Using Fuzzy Edge Detection Method

Cited by 9 publications

References 11 publications

Klasifikasi Alexnet dan Deteksi Tepi Canny untuk Identifikasi Citra Repomedunm

Klasifikasi Alexnet dan Deteksi Tepi Canny untuk Identifikasi Citra Repomedunm

Cervical cancer diagnosis based on cytology pap smear image classification using fractional coefficient and machine learning classifiers

Image processing techniques for the segmentation of cervical cancer

Contact Info

Product

Resources

About