In recent years many face recognition algorithms were used for the identification and authentication of a person to a system. However, still, feature extraction from multispectral images was considered to be a challenging task. Feature extraction, including highlight location and portrayal, assumes a significant job in real-time security-based applications. In this paper, a novel Geometric Algebra-based Multivariate Regression Feature Extraction (GA-MVRFE) algorithm was proposed to extract features from a huge dataset stored in the cloud efficiently. This proposed algorithm works with the supreme expedient deep learning approach - Convolutional Neural Network (CNN) for image classification. CNN will automatically detect significant features from the multispectral images without any human intrusion from a huge database. Real-time images were captured with three different cameras and applied filters over the images and were created as a dataset. To show the competence of the proposed algorithm, an exclusively created dataset with a set of 14,400 image data was applied in the proposed and other existing algorithms, and their efficiency and robustness were noted. Providentially, GA-MVRFE produced better accuracy in ‘Face Recognition’ with a less time fraction compared with former algorithms. Obtained accuracy % for Geometric Algebra Oriented fast and Rotated Brief (GA-ORB), Geometric Algebra Fast Retina key-point Extraction Algorithm (GA-FREAK), Trilateral Smooth Filtering (TRSF), Cross Regression Multiple View Features extraction (CRMVF) and GA-MVRFE was 87.81, 83.23, 90.72, 91.67 and 97.57 respectively.
Chennai has had the longest coastline over other major cities of India. It is decidedly vital to monitor seawater quality due to the increased coastline population. This study presents an Android mobile application based on a machine learning approach to perform basic testing parameters of seawater by applying convolutional neural network concepts. A commercially available “saltwater master test kit” was used in this study to test the level of pH, Ammonia, Nitrite, Nitrate, and Total Phosphate (T.P.) in seawater. Six water samples collected from every 10 regions, including the coastline and coastal estuaries, were tested with the test kit in a microplate. Images were captured in the solely designed mobile app, and they were pre‐processed, and RGB (Red, Green, and Blue) were recorded from the Region of Interest (R.O.I.) of the image. A supervised Convolutional Neural Network Image Classifier (SCNNIC) algorithm was developed to classify the RGB pixel values. CIEDE2000 (C2K) color difference algorithm was applied over the recorded RGB values with the datasets stored previously to result in the nearest color match between the ideal dataset and R.O.I. of the captured image. Grayscale and RGB methods results were compared with the standard APHA method. This C2K color difference algorithm produced a percent accuracy of over 98% compared with other methods used, and R2 recorded by curve fitting method for pH, T.N. and T.P. were above 0.98. Disquieting results were reported in this study, especially in Muttukkadu backwater and Adayar river backwater estuaries, reported high values of pH (7.82 and 8.17), TN (13.74 mg/L and 13.45 mg/L) and T.P. (0.266 μg/L and 0.724 μg/L). The mean for all 10 regions of 110 km chosen in this study for the 2 years was calculated, and values were obtained as pH‐8.33, TN‐5.321 mg/L, and TP‐0.143 μg/L.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.