Mobile application has been identified as the best platform for the expert system tool to reach as many users as possible. The main contribution of this paper is the development of an expert system tool for evaluating the ripeness of banana fruit. Utilizing Google Cloud Platform, the application sends the sample of banana image through Google Cloud Vision Application Programming Interface to get attribute readings from the sample image. The result of the analysis is compared with application's database of attributes datasets to determine the ripeness of the banana sample image. In this work, the ripeness of the banana is classified into three different class of maturity; unripe, ripe and overripe systematically based on their key attributes value. This work also involved the process of collecting samples of banana with different level of ripeness, application development and evaluation to improve the accuracy of the developed applications classification results using image processing and data mining techniques.
Abstract-This paper mainly aims to study the performance of objective assessment methods of image quality. It take into consideration the correlations between each objective assessment and the subjective assessment in order to determine objective test performance. Three objective assessment methods used in this study are the Structural Similarity (SSIM) index, the Peak Signal-to-Noise Ratio (PSNR) and the Mean Squared Error (MSE) calculating algorithm. The resulting data indicate what type of objective assessment was most suitable for which type of impairment imposed upon an image. This is clarified using the Pearson Correlation Coefficient as described in the paper. As an overall, SSIM index had the best correlation characteristics to the subjective assessment, followed by the MSE calculating algorithm. From this study, a better understanding of the requirements for developing an efficient image quality assessment method was gained.
Abstract-Fractal antennas have the characteristic of radiating in multiple frequencies through the property of self similarity that fractal shapes posses. By connecting fractal shaped antennas, wideband coverage can be achieved. Microstrip patch antennas with Sierpinski fractal geometry can be tuned, by design, to work exactly at the bands of interest, through judicious choice of the fractal designs and iteration. Therefore, a broadband dualfrequency microstip patch antenna with modified Sierpienski fractal geometry is designed by using Microwave Office 2002 simulation software. The broadband and multiple frequency characteristics of fractal antennas will be demonstrated. The performance of microstrip patch antenna with the classic and modified Sierpinski fractal geometries will be presented.
Nowadays, person recognition has received significant attention due to broad applications in the security system. However, most person recognition systems are implemented based on unimodal biometrics such as face recognition or voice recognition. Biometric systems that adopted unimodal have limitations, mainly when the data contains outliers and corrupted datasets. Multimodal biometric systems grab researchers’ consideration due to their superiority, such as better security than the unimodal biometric system and outstanding recognition efficiency. Therefore, the multimodal biometric system based on face and fingerprint recognition is developed in this paper. First, the multimodal biometric person recognition system is developed based on Convolutional Neural Network (CNN) and ORB (Oriented FAST and Rotated BRIEF) algorithm. Next, two features are fused by using match score level fusion based on Weighted Sum-Rule. The verification process is matched if the fusion score is greater than the pre-set threshold. The algorithm is extensively evaluated on UCI Machine Learning Repository Database datasets, including one real dataset with state-of-the-art approaches. The proposed method achieves a promising result in the person recognition system.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.