Description

Rice Grain Quality Detection

ABSTRACT:

                 The analysis of grain type, grading, and their quality attributes is still done by skilled persons manually. This method leads to complexity because it depends on several factors like human factors, working conditions, and the rate of cleaning and recovery of salvage. This may be overcome by using image processing techniques. Testing quality is gaining importance in the food industry for classifying and grading grains. Since manual testing is time-consuming, costly, and inaccurate, machine vision-based quality analysis of rice grains is preferred. In deep learning-based testing, we take both physical (grain shape and size) and chemical characteristics (amylose content, gel consistency) for the evaluation and grading of rice grains. In this proposed algorithm, the quality and grading of rice grains were analyzed using the average values of the features extracted from the network.

EXISTING SYSTEM:

      1. Image thresholding

2. Support vector machine

      3. Edge Detection methods

DRAWBACKS:

1. Inaccurate results

2. Time-consuming process

3. Require manual analysis

PROPOSED SYSTEM:

The growth in technology is making people more demanding towards the things they use and consume, this is the reason why everything is becoming automated. The use of Image processing techniques for testing the quality of rice grains is inexpensive and is less time-consuming. In this method, the quality of grain is tested based on its size and shape features.

ADVANTAGES:

1. Less time consumption

2. By using deep learning we can get the accurate results

3. High performance

APPLICATIONS:

1. Agricultural purposes

2. Research purposes.

BLOCK DIAGRAM:

Software Requirements:-

• Matlab 2018a and above
• Deep learning toolbox

REFERENCES:

[1] VidyaPatil, V. S. Malemath, Quality Analysis and Grading of Rice Grain Images, International Journal of Innovative Research in Computer & Communication Engineering (IJIRCCE) ISSN 2320-9801, Vol. 3, Issue 6, pp 5672-5678, June 2015

 [2] Neelamegam. P, Abirami. S, Vishnu Priya. K, RubalyaValantina.S, Analysis of rice granules using Image Processing and Neural Network, 978-1-4673-5758-6/13/$31.00 © 2013 IEEE

 [3] GurpreetKaur&BhupinderVerma, Measurement standards-based grading of rice      kernels by separating touching kernels for embedded imaging applications, International Journal of Electronics, Communication & Instrumentation Engineering Research and Development (IJECIERD) ISSN 2249-684X, Vol. 3, Issue 1, pp 127-134, Mar 2013 

[4] AbdellaouiMehrez, DOUIK Ali, Hybrid method for cereal grain identification using morphological and color features, 1-4244-03952/06/$20.00 ©2006 IEEE 

[5] Bhavesh B. Prajapati, Sachin Patel “Algorithmic Approach to Quality Analysis of Indian Basmati Rice Using Digital Image Processing” International Journal of Emerging Technology and Advanced Engineering Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 3, Issue 3, March 2013).

 [6] R. Kiruthika, S. Muruganand, AzhaPeriasamy “MATCHING OF DIFFERENT RICE GRAINS USING DIGITAL IMAGE PROCESSING” International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering Vol. 2, Issue 7, July 2013 

[7] Qing Yao, Jianhua Chen, Zexion Guan “Inspection of rice appearance quality using machine vision”, Global Congress on Intelligent Systems. 2009.