Classification of benign and malignant masses based on Zernike moments

Detection and classification of masses in mammographic images in a multi-kernel approach

“…Therefore, we can utilize them to describe shape characteristics of the main objects. Due to these qualities, Zernike moments have being used successfully to represent mammary regions of interest in mammograms [12] [13]. Fig.…”

“…Saki et al (2013) employed the spiculation index to represent the geometry of lesion boundary [12]. Rouhi et al (2015) uses CNN segmentation at the feature extraction stage [12]. In all these methods human segmentation is needed [12][13] [18] [19].…”

“…Rouhi et al (2015) uses CNN segmentation at the feature extraction stage [12]. In all these methods human segmentation is needed [12][13] [18] [19]. Table 1 shows the needing of human segmentation during training (learning phase) and/or using phases.…”

“…In other works, the radiologist is responsible to identify the mass edge [12][13] [18]. After edge detection, there is the study of area occupied by the mass and its neighborhood.…”

Offline Signature Verification System for Bank Cheques Using Zernike Moments, Circularity Property and Neural Network

“…Zernike moments are chosen because of its robustness towards image noise, geometrical invariance property and orthogonal property. Using Zernike moments reduces the false negative rate [21]. Algorithm I is used to extract the moment features.…”