The Common Edible Shellfish Recognition System Applying Laser Measurement

Abstract

Image recognition has been widely applied to sorts of fields. Nevertheless, the most common characteristics of image recognition, such as color, corner and texture, are liable to be affected by illumination and the light of background leading to bias the recognized consequences. In recent years the technology of three-dimensional scanning has developed increasingly mature which could precisely measure the contour of fixed-shape objects. We take the three-dimensional contour as characteristics in the project. The comparative sample which will be used as for recognition was scanned every 1 millemeter from the leftmost to the rightmost in order to establish the three-dimensional object database, besides we sampled 540 dots for each scanning line. In order to shorten the testing time, we merely scanned two scanning lines while doing testing. The edible shellfish was taken as example in the research so we examined the characteristic for recognition feasibility. There were nine edible shellfishes used for the experiment. Each category has individual thirty samples. We take leave-one-out for recognition mechanism that the rate of recognition could reach 89.69 and the average recognition time was 5 seconds. The three-dimensional scanning is a new option for characteristic capturing. Furthermore, we will do our best to continue increasing the rate and speed of recognition to improve the practicality in the future.



Author Information
Mei-Jin Wang, Kun Shan University, Taiwan
Ling-Chin Ko, Kun Shan University, Taiwan
Yuan-Tsun Chen, Kun Shan University, Taiwan
Jer-Min Tsai, Kun Shan University, Taiwan
Yi-Ling Chen, Kun Shan university, Taiwan

Paper Information
Conference: CHER-HongKong2018
Stream: Innovation/entrepreneurship and graduate employment

This paper is part of the CHER-HongKong2018 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window

Posted by amp21