Analysis of produce recognition system with taxonomist's knowledge using computer vision and different classifiers

被引:3
作者
Chaw, Jun-Kit [1 ]
Mokji, Musa [1 ]
机构
[1] Univ Teknol Malaysia, Dept Elect & Comp Engn, Skudai 81310, Johor, Malaysia
关键词
object recognition; computer vision; learning (artificial intelligence); image classification; statistical analysis; agricultural products; produce recognition system; barcode scanners; checkout process; object classification; attribute classification; statistical approaches; semantic models; attribute learning; FRUIT CLASSIFICATION; DECISION TREE; SELECTION; ENSEMBLE;
D O I
10.1049/iet-ipr.2016.0381
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Supermarkets nowadays are equipped with barcode scanners to speed up the checkout process. Nevertheless, most of the agricultural products cannot be pre-packaged and thus must be weighted. The development of produce recognition system based on computer vision could help the cashiers in the supermarkets with the pricing of these weighted products. This work proposes a hybrid approach of object classification and attribute classification for the produce recognition system which involves the cooperation and integration of statistical approaches and semantic models. The integration of attribute learning into the produce recognition system was proposed due to the fact that attribute learning has emerged as a promising paradigm for bridging the semantic gap and assisting in object recognition in many fields of study. This could tackle problems occurred when less training data are available, i.e. less than 10 samples per class. The experiments show that the correct classification rate of the hybrid approach were 60.55, 75.37 and 86.42% with 2, 4 and 8 training examples, respectively, which were higher than other individual classifiers. A well-balanced specificity, sensitivity and F-1 score were achieved by the hybrid approach for each produce type.
引用
收藏
页码:173 / 182
页数:10
相关论文
共 34 条
[1]  
[Anonymous], 2013, ICCV
[2]  
[Anonymous], 2012, ECCV
[3]  
[Anonymous], EUR C COMP VIS ECCV
[4]   VeggieVision: A produce recognition system [J].
Bolle, RM ;
Connell, JH ;
Haas, N ;
Mohan, R ;
Taubin, G .
THIRD IEEE WORKSHOP ON APPLICATIONS OF COMPUTER VISION - WACV '96, PROCEEDINGS, 1996, :244-251
[5]   A hybrid ensemble for classification in multiclass datasets: An application to oilseed disease dataset [J].
Chaudhary, Archana ;
Kolhe, Savita ;
Kamal, Raj .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2016, 124 :65-72
[6]  
Chaw J. -K., 2016, ENG AGR ENV FOOD, V9, P224
[7]   Evaluating classification and feature selection techniques for honeybee subspecies identification using wing images [J].
da Silva, Felipe Leno ;
Grassi Sella, Marina Lopes ;
Francoy, Tiago Mauricio ;
Reali Costa, Anna Helena .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2015, 114 :68-77
[8]   Dynamic cattle behavioural classification using supervised ensemble classifiers [J].
Dutta, Ritaban ;
Smith, Daniel ;
Rawnsley, Richard ;
Bishop-Hurley, Greg ;
Hills, James ;
Timms, Greg ;
Henry, Dave .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2015, 111 :18-28
[9]  
Dzeroski S, 2004, MACH LEARN, V54, P255, DOI 10.1023/B.MAC.0000015881.36452.6e
[10]  
Fan RE, 2008, J MACH LEARN RES, V9, P1871