|Fruit Ripeness Detection with Machine Learning using Raspberry Pi|
|ATAL TIWARI, ANMOL SHARMA, AVINASH PATIL|
|Cite This Article:|
Fruit Ripeness Detection with Machine Learning using Raspberry Pi, International Journal of Innovative Research in Technology(www.ijirt.org) ,ISSN: 2349-6002 ,Volume 6 ,Issue 1 ,Page(s):781-785 ,June 2019 ,Available :IJIRT148372_PAPER.pdf
|Machine Learning, Computer Vision, Clustering Algorithm, Fruit Ripeness, Digital Image Processing, Agriculture, etc|
|The term Machine Learning refers to the field of study that gives computer the ability to learn without being explicitly programmed. It is a boon to various fields that basically depends on the reliability of the product. When it comes to agriculture field, like quality of the fruit or we can say ripeness of the fruit, machine learning plays an important role in making it happen to identify the ripeness of the fruits based on the training datasets we fed. With the help of computer vision and digital image processing we can find the ripeness of a fruit. In this paper we are basically focusing on computer vision strategies used to recognize a fruit which rely on four basic features which characterize the object: intensity, color, shape and texture. The methodology bestowed is ready to acknowledge fruits in natural condition facing troublesome situations: shadows, bright areas, occlusions and overlapping fruits. Every technique uses coloured pictures of fruits from totally different positions as input file. In these techniques we have a tendency to set some threshold levels. By examination the input file image with these threshold levels we are able to realize the maturity level of fruits. The fruit ripeness detection technique can play a vital role in the large scale industrial applications for detecting the quality of the fruits. Businesses like bigbasket, Grofers, Amazon Now, etc. which deals with the import and export of the fruits can adapt the technology in order to not only reduce the labour cost but also time. It is also useful for agriculture field.|
|Unique Paper ID: 148372|
Publication Volume & Issue: Volume 6, Issue 1
Page(s): 781 - 785
|Article Preview & Download|
Enhanced PAD Neural Based Approach for Forgery Det...
Paper ID : IJIRT148940
A Comparative Study on Various Dairy Co-operative ...
Paper ID : IJIRT148939
ENHANCED DISTRIBUTED ENERGY EFFICIENT CLUSTERING P...
Paper ID : IJIRT148938
A Photovoltaic Modeling module with different Conv...
Paper ID : IJIRT148936
A Partial Replacement of Ceramic Tiles Waste in Co...
Paper ID : IJIRT148935