Planogram Compliance Checking Based on Detection of Recurring Patterns

TL;DR

This paper introduces an unsupervised method for automatic planogram compliance checking in retail, which detects recurring product patterns without needing template images, improving accuracy and efficiency.

Contribution

The proposed approach is the first to use unsupervised recurring pattern detection combined with graph matching for planogram compliance without product templates.

Findings

Higher accuracy than template-based methods across various products

Effective in real retail environments

Faster due to divide and conquer strategy

Abstract

In this paper, a novel method for automatic planogram compliance checking in retail chains is proposed without requiring product template images for training. Product layout is extracted from an input image by means of unsupervised recurring pattern detection and matched via graph matching with the expected product layout specified by a planogram to measure the level of compliance. A divide and conquer strategy is employed to improve the speed. Specifically, the input image is divided into several regions based on the planogram. Recurring patterns are detected in each region respectively and then merged together to estimate the product layout. Experimental results on real data have verified the efficacy of the proposed method. Compared with a template-based method, higher accuracies are achieved by the proposed method over a wide range of products.