JETIREXPLORE- Search Thousands of research papers



Published in:

Volume 5 Issue 12
December-2018
eISSN: 2349-5162

Unique Identifier

JETIREB06128

Page Number

1083-1090

Share This Article


Title

Discrete Wavelet Transform and gray-scale image analysis for real time estimation of calorific energy in food products

ISSN

2349-5162

Cite This Article

"Discrete Wavelet Transform and gray-scale image analysis for real time estimation of calorific energy in food products", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 12, page no.1083-1090, December 2018, Available :http://www.jetir.org/papers/JETIREB06128.pdf

Abstract

Computer vision techniques have demonstrated great success in being able to classify complex food products. The challenge, however, lies in extracting any further information, such as the nutritional value in these products. We propose a method using grayscale features of the image to classify and extract information from an image. The discrete wavelet transform is used to create 4 combinations of high pass & low pass filters through which we are able to enhance the features by edge detection and fine-grain analysis at different levels. Outputs from the filters are coupled together to achieve a compressed image with enhanced features from which we extract our required grayscale feature data. The various vectors obtained are coupled as a singular tensor which is fed into a neural network to perform the classification task in form of a supervised learning, where we make use of the ingredients as our labels. Our solution assumes that the targets are clearly separable from the background which must be plain. Humans describe food items and their differences in terms of the ingredients contained within and the way these ingredients are arranged, so it makes sense that we should be able to learn extra information by extracting features at an intermediate ingredient level instead of just the pixel level. Our goal with this method is to achieve a good balance between classification accuracy as well as the time and processing power required to perform the same. Our largest challenge is the differences in volume of raw ingredients as well as the high intra-class variations within similar groups.

Key Words

Machine Learning, Food, Calorie, Computer Vision, GLCM, Discrete Wavelet Transform, Neural Networks

Cite This Article

"Discrete Wavelet Transform and gray-scale image analysis for real time estimation of calorific energy in food products", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 12, page no. pp1083-1090, December 2018, Available at : http://www.jetir.org/papers/JETIREB06128.pdf

Publication Details

Published Paper ID: JETIREB06128
Registration ID: 233802
Published In: Volume 5 | Issue 12 | Year December-2018
DOI (Digital Object Identifier):
Page No: 1083-1090
ISSN Number: 2349-5162

Download Paper

Preview Article

Download Paper




Cite This Article

"Discrete Wavelet Transform and gray-scale image analysis for real time estimation of calorific energy in food products", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 12, page no. pp1083-1090, December 2018, Available at : http://www.jetir.org/papers/JETIREB06128.pdf




Preview This Article


Downlaod

Click here for Article Preview