Name
Abstract | ||
|---|---|---|
Checking out produce poses an enormous problem for grocery stores and supermarkets. Essentially, the technology of produce checkout has not changed in the last 1,000 years: the checker visually identifies the produce and weighs it to determine the price. It is a well-established fact that the produce department is a significant factor in how customers rate the quality of a store. Produce is also associated with many problems, including: 1) shrinkage [losses], 2) slow checkout, 3) checker training, 4) affixing price look-up code labels, 5) expensive packaging, 6) solid waste. Because of these problems, most grocers and supermarket chains will admit in private that they would rather not carry produce. We present an automatic produce ID system ("VeggieVision''), intended to ease the produce checkout process. The system consists of an integrated scale and imaging system with a user-friendly interface. When a produce item is placed on the scale, an image is taken. A variety of features, color, texture (shape, density), are then extracted. These features are compared to stored "signatures'' which were obtained by prior system training (either on-line or off-line). Depending on the certainty of the classification, the final decision is made either by the system or by a human from a number of choices selected by the system. Over 95\% of the time, the correct produce classification is in the top four choices. |
Year | DOI | Venue |
|---|---|---|
1996 | 10.1109/ACV.1996.572062 | WACV |
Keywords | Field | DocType |
prior system training,produce department,recognition system,automatic produce id system,imaging system,produce checkout,affixing price look-up code,slow checkout,produce item,correct produce classification,produce checkout process,image segmentation,color,image classification,machine vision,prototypes,shape,texture,feature extraction,hardware,image recognition | Computer vision,Automatic image annotation,Recognition system,Pattern recognition,Segmentation,Image texture,Feature (computer vision),Computer science,Feature extraction,Artificial intelligence,Contextual image classification,Cognitive neuroscience of visual object recognition | Conference |
ISBN | Citations | PageRank |
0-8186-7620-5 | 13 | 2.67 |
References | Authors | |
5 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ruud M. Bolle | 1 | 2116 | 230.26 |
| Jonathan H. Connell | 2 | 712 | 60.10 |
| Norman Haas | 3 | 100 | 46.34 |
| Rakesh Mohan | 4 | 17 | 4.84 |
| G Taubin | 5 | 2471 | 228.93 |