Download
1 / 23
230 likes | 272 Views
A practical system to enhance efficiency in selling and managing produce inventory in grocery stores developed by IBM researchers. The system, tested in small markets, recognizes up to 400 produce types and operates seamlessly within the checkout process while incorporating barcode scanning, weighing, accounting, and inventory management. Engineering solutions overcome environmental challenges, such as lighting and background segmentation, to ensure accurate product recognition. Features color, texture, shape, and size analysis through histograms to match unknown samples to stored data for quick identification. The system also includes learning and adaptation mechanisms for ongoing improvement.
E N D
Veggie Vision by IBM Ideas about a practical system to make more efficient the selling and inventory of produce in a grocery store. CSE 803 Fall 2008 Stockman
Problem is recognizing produce CSE 803 Fall 2008 Stockman
15+ years of R&D now This information was shared by IBM researchers. Since that time, the system has been tested in small markets and has been modified according to that experience. CSE 803 Fall 2008 Stockman
Up to 400 produce types CSE 803 Fall 2008 Stockman
Practical problems of application environment CSE 803 Fall 2008 Stockman
Engineering the solution CSE 803 Fall 2008 Stockman
System to operate inside the usual checkout station • together with bar code scanner • together with scale • together with accounting • together with inventory • together with employee • within typical store environment • * figure shows system asking for help from the cashier in making final decision on touch screen CSE 803 Fall 2008 Stockman
Modifying the scale CSE 803 Fall 2008 Stockman
Need careful lighting engineering CSE 803 Fall 2008 Stockman
Need to segment product from background, even through plastic CSE 803 Fall 2008 Stockman
Previously published thresholding decision CSE 803 Fall 2008 Stockman
Quality segmented image obtained CSE 803 Fall 2008 Stockman
Design of pattern recognition paradigm (from 1997) FEATURES are: color, texture, shape, and size all represented uniformly by HISTOGRAMS Histograms capture statistical properties of regions – any number of regions. CSE 803 Fall 2008 Stockman
Matching procedure • Sample product represented by concatenated histograms: about 400 D • 350 produce items x 10 samples = 3500 feature vectors of 400D each • Have about 2 seconds to compare an unknown sample to 3500 stored samples (3500 dot products) • Analyze the k nearest: if closest 2 are from one class, recognize that class (sure) CSE 803 Fall 2008 Stockman
HSI for pixel color: 6 bits for hue, 5 for saturation and intensity For each pixel quantify H HIST[H]++ same for S&I CSE 803 Fall 2008 Stockman
Histograms of 2 limes versus 3 lemons • Distribution or population concept adds robustness: • to size of objects • to number of objects • to small variations of color (texture, shape, size) CSE 803 Fall 2008 Stockman
Texture: histogram results of LOG filter[s] on produce pixels Leafy produce B Leafy produce A CSE 803 Fall 2008 Stockman
Shape: histogram of curvature of boundary of produce CSE 803 Fall 2008 Stockman
Banana versus lemon or cucumber versus lime Small range of curvatures indicates roundish object Large range of curvatures indicates complex object CSE 803 Fall 2008 Stockman
Size is also represented by a histogram CSE 803 Fall 2008 Stockman
Each pixel gets a “size” as the minimum distance to boundary Chinese eggplants Purple grapes CSE 803 Fall 2008 Stockman
Learning and adaptation • System “easy” to train: show it produce samples and tell it the labels. • During service: age out oldest sample; replace last used sample with newly identified one. • When multiple labeled samples match the unknown, system asks cashier to select from the possible choices. CSE 803 Fall 2008 Stockman
