Shelf Image Recognition for Precise Price Tag Area Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately identify and process the area of a display shelf for goods identification and price tag reading, often including adjacent shelves and goods due to imprecise imaging angles, leading to inefficient and inaccurate processing.
Innovation Solution
An information processing system utilizing machine learning and image correction techniques to detect and correct the area of interest, including a learning processing unit for generating a network and a detection processing unit for precise area recognition, with correction and placement processing to align images to a facing position.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If capturing is performed with a margin on the left and right of the angle of view to ensure the display shelf fits within the frame, then the display shelf is fully captured, but adjacent display shelves and goods are also included in the captured image information
Solution Approach 1:
The patent extracts and removes adjacent display shelves from the captured image information by detecting shelf boundaries and selectively excluding regions belonging to adjacent shelves. This allows the system to process only the target display shelf while ignoring extraneous adjacent shelves that were captured due to the margin approach.
Solution Approach 2:
The patent segments the captured image information into distinct display shelf regions by detecting boundary lines between adjacent shelves. This segmentation enables the system to identify and process only the relevant target shelf area while separating it from adjacent shelves.
2Measurement precision
If manual setting of processing area is performed to exclude adjacent shelves, then processing accuracy is improved, but processing time and operational complexity increase
Solution Approach 1:
The patent implements self-service by enabling the system to automatically detect display shelf boundaries, identify the target shelf area, and exclude adjacent shelves without requiring manual intervention. The imaging device and processing system autonomously perform the area definition task that would otherwise require manual setting.
Solution Approach 2:
The patent replaces the manual mechanical process of setting processing areas with an automated image processing system that uses boundary line detection and coordinate analysis to automatically define and exclude adjacent shelf regions.
3Manufacturing precision
If the imaging angle is adjusted to exactly include the left and right ends of the display shelf, then the captured area is precise, but the time to adjust the imaging angle increases
Solution Approach 1:
The patent applies preliminary action by performing post-capture processing to correct and refine the detected display shelf area. Instead of requiring precise initial imaging angle adjustment, the system captures images with margins and then uses image processing to accurately identify and extract the target shelf boundaries, effectively correcting the capture area after the fact.
Data Source
Figure 1
Figure 2~4
Figure 5
AI summary
An object is to provide an information processing system that detects an area of a display shelf to be processed in processing of identifying goods displayed on the display shelf/reading price tags. The information processing system includes a learning processing unit that generates a network of machine learning, and a detection processing unit that performs processing of detecting a predetermined area from image information using the network, the learning processing unit including an annotation data reception processing unit that receives an input of annotation data obtained by annotating a goods display area and/or a price tag area in the display shelf, and a learning processing unit that performs learning processing using the received annotation data and generates a network of machine learning, and the detection processing unit including an image information reception processing unit that receives an input of image information in which a display shelf to be processed is captured, and a recognition processing unit that recognizes the goods display area and/or the price tag area in the display shelf captured in the image information using the generated network.