Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Correlation-Aided 3D Vector Distance Estimation-Based Quality Assessment of Indian Gooseberry

Correlation-Aided 3D Vector Distance Estimation-Based Quality Assessment of Indian Gooseberry In this paper, it has been developed a statistics-based method for the quality assessment and classification of amla (Indian gooseberry). The proposed binary classification of the amla fruits has been achieved using a simple statistical analysis incorporating the correlation coefficient of the image features. Here, the sample images were captured and analysed for the red green blue (RGB) and hue saturation (HS) layers. We have developed the histograms of these layers were developed and investigated the correlation coefficient between each of the layers taken pairwise. These cross-correlation values have been studied extensively to identify three of the most important and significant pairs of features which produced distinctive correlation coefficient values between the good and the bad sample of images. The three-dimensional scatter plot and the proximity analysis model are studied to develop the classification of the samples. The proposed model is simple in computation and contains no major complex mathematical analysis. Besides, the proposed model is able to classify amla samples with 96.43% accuracy. This high accuracy of classification, combined with the ease of analysis, and most importantly capturing fruit images using smartphone-based cameras enable the possibility of widespread use of the present scheme in developing application-based software, especially for low-memory devices. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of The Institution of Engineers (India):Series A Springer Journals

Correlation-Aided 3D Vector Distance Estimation-Based Quality Assessment of Indian Gooseberry

Loading next page...
 
/lp/springer-journals/correlation-aided-3d-vector-distance-estimation-based-quality-hTVvkhSkGv
Publisher
Springer Journals
Copyright
Copyright © The Institution of Engineers (India) 2022
ISSN
2250-2149
eISSN
2250-2157
DOI
10.1007/s40030-022-00616-6
Publisher site
See Article on Publisher Site

Abstract

In this paper, it has been developed a statistics-based method for the quality assessment and classification of amla (Indian gooseberry). The proposed binary classification of the amla fruits has been achieved using a simple statistical analysis incorporating the correlation coefficient of the image features. Here, the sample images were captured and analysed for the red green blue (RGB) and hue saturation (HS) layers. We have developed the histograms of these layers were developed and investigated the correlation coefficient between each of the layers taken pairwise. These cross-correlation values have been studied extensively to identify three of the most important and significant pairs of features which produced distinctive correlation coefficient values between the good and the bad sample of images. The three-dimensional scatter plot and the proximity analysis model are studied to develop the classification of the samples. The proposed model is simple in computation and contains no major complex mathematical analysis. Besides, the proposed model is able to classify amla samples with 96.43% accuracy. This high accuracy of classification, combined with the ease of analysis, and most importantly capturing fruit images using smartphone-based cameras enable the possibility of widespread use of the present scheme in developing application-based software, especially for low-memory devices.

Journal

Journal of The Institution of Engineers (India):Series ASpringer Journals

Published: Mar 6, 2022

Keywords: Freshness class; Centroid; Food safety; Postharvest management

References