Grocery product detection and recognition

作者：

Highlights：

• An approach for candidate pre-selection based on corners and color information.

• A robust approach for object detection and recognition; Bag of Words and Deep Neural Networks are compared.

• A post-processing step, used to combine multiple detection of the same object.

• A deep experimental evaluation on the complex Grozi-120 public dataset.

摘要

• An approach for candidate pre-selection based on corners and color information.•A robust approach for object detection and recognition; Bag of Words and Deep Neural Networks are compared.•A post-processing step, used to combine multiple detection of the same object.•A deep experimental evaluation on the complex Grozi-120 public dataset.

论文关键词：Bag of visual words,DNN features,SURF keypoint descriptors,Color histogram,Object detection,Object recognition

论文评审过程：Received 26 September 2016, Revised 2 February 2017, Accepted 19 February 2017, Available online 21 March 2017, Version of Record 30 March 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.02.050