Fruit defect detection based on speeded up robust feature technique | IEEE Conference Publication | IEEE Xplore

Fruit defect detection based on speeded up robust feature technique


Abstract:

This paper elaborated the fruit quality detection technique which was based on external properties of fruits such as shape, size and color. Due to large demand, manual mo...Show More

Abstract:

This paper elaborated the fruit quality detection technique which was based on external properties of fruits such as shape, size and color. Due to large demand, manual monitoring of fruits are ineffectual for agriculture industry. So, it requires a competent technique which will help agriculture industry to full fill the demand of consumer. The proposed method is based on the use of speeded up robust feature. The method extracts the local feature of the segmented image and describes the object recognition. The objective is to design the defect detection algorithm which will be used for feature extraction and descriptor having less processing time.
Date of Conference: 07-09 September 2016
Date Added to IEEE Xplore: 19 December 2016
ISBN Information:
Conference Location: Noida, India

I. Introduction

Indian market ranks second in fruits production in the world. The fruit production of India is 81.285 million metric tons [1]. The immense production of fruit offers India remarkable opportunities for export. During 2014–15 India disseminated fruits of worth Rs. 2771.32 crores [1]. Therefore an effective and improved system is necessary to full fill the demand for agriculture industry. The proposed system will help agriculture industry for quality fruit detection and descriptor as it is robust, accurate and having fast response. The proposed system is used to identify the external disease of fruit based on the external property of the fruit such as shape, size and color. Speeded up robust feature a technique is used to extract the local features of fruits and its description [2], [3]. Manual computation will take lots of time and are inaccurate but our system will take less time with precise result. Occlusion of fruits by other fruits and leaves are also detected correctly. Based on shape, size, color, and texture of the fruit defected fruits are identified. The system subtracts the input image with the defect classified image and based on this fruit quality is revealed. Once the fruit is individualised, the following parameters are calculated using the information extracted from the boundaries such as: centroid, maximum and minimum diameter, surface, perimeter and circularity. Several experiments are carried out to test the accuracy of the system.

References

References is not available for this document.