딥러닝 기반 과일 선별 시스템 = Fruit Classification System Using Deep Learning

다국어 초록 (Multilingual Abstract)

Deep learning technology among artificial intelligence technologies has shown good results in image recognition field. In this paper, we use a learning model that is based on a Tensorflow based model that utilizes this deep learning technique and that has been repaired by Inception-v3 model. Based on the characteristics of the fruit, we construct a fruit classification system that classifies into four categories : Healthy apple, Damaged apple, Diseased apple and Discolored apple. To do this, we designed a learning model in which the number of learning iterations was 500 times based on 1,280 apple image data of four kinds and conducted a model evaluation experiment based on the fruit image data taken by the user. Experiments were based on images taken in three directions for accurate model evaluation. Experimental results show that the accuracy of the learning model is more than 90%. However, since fruit showed different classification results according to direction, it suggested the necessity of classification algorithm according to image direction in the future. If such a deep learning based fruit classification system is applied to farmers, fruit quality classifiers due to farm labor shortage are essential, and it will be possible to construct a fruit quality screening system with high accuracy and low cost.

참고문헌 (Reference)

1 M. Koike, "https://www.youtube.com/watch?tim e_continue=1&v=4HCE1P-m1l8"

2 "Solaris"

3 J. N. Park, "Rock image classification with deep convolutional neural network based on Tensorflow" Korean Institute of Information Scientists and Engineers 1121-1123, 2018

4 S. H. Jeong, "Retraining Inception-v3 for fruits quality classification" 64-67, 2018

5 J. T. Kim, "Machine vision technology using deep learning technique Recent application trends" 43 (43): 18-26, 2016

6 M. Baigvand, "Machine vision system for grading of dried figs" 119 : 158-165, 2015

7 Codelabs, "Image classification transfer learning with inception v3" Google Developers 2017

8 "Hvass-Lab : TensorFlow Tutorials"

9 "How a Japanese cucumber farmer is using de ep learning and TensorFlow"

10 "Face It – The Artificially Intelligent Hairstylist"

11 S. H. Jeong, "Development of machine vision based fruit quality screening system" Korean Institute of Communication Sciences 2017

12 Dong Hoon Lim, "Development of Apple Color Grading System by Statistical Color Image Processing" 한국통계학회 10 (10): 325-332, 2003

13 G. S. Juan, "Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques" 39 (39): 780-785, 2012

14 I. Sa, "DeepFruits : A fruit detection system using deep neural networks" 16 (16): 2016

15 W. Ding, "Automatic moth detection from trap images for pest management" 123 : 17-28, 2016