A Novel Method for Calculating Approximate Weight of an Object through its Image
DOI:
https://doi.org/10.14738/tmlai.26.733Keywords:
Algorithms, Approximation methods, Colour, Surface image, Weight, Weight per pixel, Weight approximation, Image subtraction, Threshold.Abstract
The field of computer science is capable of calculating approximate weight of an object through its image. It is new and challenging. The idea behind the weight of an object is nothing but approximation of the pixel carries some weight value which is specific for the corresponding specific object. It is a challenge for the computer science people to develop methods through pixel weight. The main focus of this paper is to find the approximate weight of an object through its digital image. Generally weight calculating machine is used to find out the weight of any object(s). To improve the process and to make it somehow digitized we have proposed a novel method that does not require any physical standard to calculate weight.
Initially, a surface image is captured by the system and whenever a newly taken image, i.e., the image of object placed over the same surface is input, it will be subtracted from our pre-existing surface image. Based on the features of colour attribute the weight of the object is estimated. From the experimental results, it is observed that the proposed model works perfectly on both training data as well as novel data. We believe this paper could form a base for future works on related topics.
References
J.Yao and J.Odobez, “Multi-layer background subtraction based on color and texture,” IEEE Conference on Computer Vision and PatternRecognition, pp.1–8, 2007.
A.K. Jain, “Fundamentals of Digital Image Processing”, Englewood cliffs, NJ: Prentice-Hall, 1980.
Yufang Zhang, Peijun Shi, Elizabeth G. Jones, and Qiuming Zhu ” Robust Background Image Generation and Vehicle 3D Detection and Tracking”. 2004 IEEE Intelligent Transpoltation Systems Conference Washington, D.C., USA, October 36,2004.
Ruihua MA, Liyuan LI, Weimin HUANG, QiTlAN, “On Pixel Count Based Crowd DensityEstimation for Visual Surveillance” Proceedings of the 2004 lEEE Conference on Cybernetics and Intelligent Systems Singapore, 1-3 December,2004
Saad Choudri, James M. Ferryman, Atta Badii, “Robust Background Model for Pixel Based People Counting using a Single Uncalibrated Camera”, 978-1-4244-5504-1/09/$25.00 ©2009 IEEE
