Search

Clinical diagnosis has increased marvelous significance in current day healthcare systems. This article proposes a brain tumor detection method using edge detection based fuzzy logic and U-NET Convolutional Neural Network (CNN) classification method. The proposed tumor segmentation system is based on image enhancement, fuzzy logic based edge detection, and classification. The input images are pre-processed using the contrast enhancement and fuzzy logic-based edge detection method is applied to identify the edge in the source images and dual tree-complex wavelet transform (DTCWT) is used at different scale levels. The features are calculated from the decayed sub-band images and these features are then categorized using U-NET CNN classification which recognizes the meningioma and non-meningioma brain images. The proposed method is evaluated using accuracy, sensitivity, specificity, and dice coefficient index. Simulation study demonstrates that the proposed technique achieves better performance, both visually and quantitatively in comparison with other approaches.

All civil infrastructure units demand regular inspection to avoid functional and structural damages. Periodic examinations are in accordance with classification society’s standards which contain both non-destructive tests and visual surveys, to search structural damage, reliability, cracks, thickness measurement, and Water dripping generally documented by manually or with measurements tape. But, it is very hard to search cracks by visually monitoring much larger structures. Hence, the advent of crack detecting and monitoring systems has been a major issue. In this proposed study a crack detection algorithm in reference to digital image processing technology is suggested. Obtaining information of a surface crack by using an image pre-processing pipeline and to estimate the failure is proposed which helps and detects the structure cracks and body health information. It provides the identification system more portable and integrated, estimates the crack more precisely and reduction in expenditure as well. The proposed algorithm accuracy is 93.8% as compared to the traditional and recent work.