GDL

Journal from gdlhub / 2022-02-12 14:20:40
Oleh : Meenakshi Pawar, Sanjay Talbar, King Saud University
Dibuat : 2022-02-12, dengan 0 file

Keyword : Mammogram, Contrast enhancement, Local entropy, DWT, Image fusion
Url : http://www.sciencedirect.com/science/article/pii/S1319157817304743
Sumber pengambilan dokumen : web

Early detection of breast cancer can enhance the chances of survival. Contrast enhancement provides improved visual information that can be used for accurate segmentation of mammogram images. This research work presents DWT coefficient fusion based on local entropy maximization algorithm for contrast enhancement. In this algorithm, the original image and CLAHE contrast-enhanced image are decomposed for three levels using Haar wavelet. At each level of decomposition, approximate coefficients are fused using averaging operation and detailed coefficients are fused by calculating entropy of 5x5 sliding window and choosing pixel value corresponding to maximum entropy. Finally, the mammogram image is reconstructed by combining approximate and detailed coefficients. The proposed algorithm is evaluated with performance metrics such as edge contents (EC), edge-based contrast measure (EBCM), featuresimilarity index measure (FSIM) and absolute mean brightness error (AMBE) with publically available MIAS (Mammographic Image Analysis Society) dataset comprising 322 images and TMCH (Tata Memorial Cancer Hospital)dataset consisting 100 images. The proposed algorithm shows improvement in EC value from 1.24 to 1.87, EBCM value from 64.24 to 120.1, FSIM 0.97 which is nearer to 1 and AMBE value of 2.01 which is very less. The proposed method is compared with most popular contrast enhancement methods HE, BBHE, CLAHE. The results showed that the proposed method offerssuperior results in terms of contrast and brightness.

Deskripsi Alternatif :

Early detection of breast cancer can enhance the chances of survival. Contrast enhancement provides improved visual information that can be used for accurate segmentation of mammogram images. This research work presents DWT coefficient fusion based on local entropy maximization algorithm for contrast enhancement. In this algorithm, the original image and CLAHE contrast-enhanced image are decomposed for three levels using Haar wavelet. At each level of decomposition, approximate coefficients are fused using averaging operation and detailed coefficients are fused by calculating entropy of 5x5 sliding window and choosing pixel value corresponding to maximum entropy. Finally, the mammogram image is reconstructed by combining approximate and detailed coefficients. The proposed algorithm is evaluated with performance metrics such as edge contents (EC), edge-based contrast measure (EBCM), featuresimilarity index measure (FSIM) and absolute mean brightness error (AMBE) with publically available MIAS (Mammographic Image Analysis Society) dataset comprising 322 images and TMCH (Tata Memorial Cancer Hospital)dataset consisting 100 images. The proposed algorithm shows improvement in EC value from 1.24 to 1.87, EBCM value from 64.24 to 120.1, FSIM 0.97 which is nearer to 1 and AMBE value of 2.01 which is very less. The proposed method is compared with most popular contrast enhancement methods HE, BBHE, CLAHE. The results showed that the proposed method offerssuperior results in terms of contrast and brightness.

Beri Komentar ?#(0) | Bookmark

Properti	Nilai Properti
ID Publisher	gdlhub
Organisasi	King Saud University
Nama Kontak	Herti Yani, S.Kom
Alamat	Jln. Jenderal Sudirman
Kota	Jambi
Daerah	Jambi
Negara	Indonesia
Telepon	0741-35095
Fax	0741-35093
E-mail Administrator	elibrarystikom@gmail.com
E-mail CKO	elibrarystikom@gmail.com