Description

ABSTRACT

The quality of the food product we have a tendency to consume is of additional importance, as individuals are getting educated their demand for quality of grains is increasing. there’s risk of adulteration of food grains by the traders. usually, the standard assessment is carried by the visual review that is a manual method. during this work a picture process technique is employed as an endeavor to change {the method|the technique} that overcomes the drawbacks of manual process Associate in Nursing automatic analysis method for the determination of the standard of rice granules and grain kind identification is introduced victimization Neural Network. A model of quality testing and identification is constructed that is predicated on geometric options and color options with the technology of laptop image process and neural network. These options square measure conferred to the neural network for coaching functions. The trained network is then accustomed determine the unknown grain varieties and its quality. The grading of rice sample is finished in step with the dimensions of the grain kernel. This technique offers smart leads to an analysis of rice quality

DEMO VIDEO

INTRODUCTION

The demand for quality of food product we have a tendency to consume is increasing day by day. because the attainment rate is increasing in the Republic of India thus is that the would like for quality of food production is increasing. The Republic of India is that the second largest producer of rice grains 1st being China. because the production of rice is increasing thus is that the demand for its quality. This demand for quality of food grains is increasing as a result of a number of the traders cheat the shopkeepers by commerce poor quality food grains that contains the particles like stones, sand, leaf, broken and broken seeds etc. this type of inferiority of rice is sold  while not being noticed  even and furthermore there’s no special theme to search out such poor quality grains. thus it’s been a haul for each shopper and sellers. currently, days we have a tendency to square measure victimisation the chemical ways for the identification of rice grain seed varieties and quality. The chemical technique used additionally destructs the sample used and is additionally terribly time overwhelming technique. These will be avoided by employing a machine vision or the digital image process system. These technique may be a non harmful, in no time and low-cost compared to the chemical technique and additionally an endeavor to overcomes the drawbacks of the manual method. a picture process technique is applied to extract varied options of rice grains and classifies the grains supported geometrical options.

EXISTING SYSTEM

Before this we have a tendency to accustomed realize for color extraction and classifies by the Support vector machine by this we have a tendency to cant say at the acceptable granules square measure gift and what kind of  quality rice

PROPOSED SYSTEM

The process enrolls by the info set of pictures it segments the image by the completely different parts and applies the feature extraction to specifies the data of the granules and therefore the state of position to spot the magnitude relation in and this algorithms square measure coaching and testing. within the coaching section, properties of the image options square measure separated and, supported these, an exclusive clarification of every classification class. within the testing section, image options square measure classified by victimization the feature area partitions.

BLOCK DIAGRAM

CONCLUSION

This project is designed to provide a better approach for the identification of different types of grains and rice quality based on color and geometrical features using Probabilistic neural network and image processing concepts. Different food grains like wheat, corn, and rice are considered in the study. More than 120 images were used to test the system and it was found that the accuracy of identifying grain is 100%. Whereas the accuracy of identifying the quality of grains and its grade is 92% and 91% accurate for each grain type. Even though the problem being worked upon is not completely new, the earlier approaches employed a very large number of color, textural and morphological features which made the algorithm extremely slow because of the intensive computation. An efficient method is proposed for classification of food grains which require limited features and thus overcoming the disadvantages like tediousness and time consumption