Remote Object Recognition Models for Self-Checkout Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Interactive information systems (IIS) face network latency and reliance on weighing or barcode scanning for commodity item identification in self-checkout transactions, leading to inefficiencies and increased costs.
Innovation Solution
Implementing a remote storage device that connects to IISs via a communication network, storing hierarchical object recognition models that match specific commodity items, reducing the need for powerful computing units at each IIS and minimizing network delays by processing images and preliminary features remotely.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If object recognition is performed locally at the IIS using traditional techniques, then commodity item identification can be achieved, but network latency increases and reliance on weighing or barcode scanning is required
Solution Approach 1:
The patent extracts the computationally intensive object recognition processing from the local IIS and relocates it to a remote server. The IIS only captures images and transmits them remotely, while the server performs the actual analysis using deep learning models. This separation reduces local computational burden and network latency.
Solution Approach 2:
The patent introduces a remote server as an intermediary between the IIS and the object recognition process. The server acts as a mediator that receives images from multiple IISs, processes them using pre-trained deep learning models, and returns identification results. This intermediary handles the computational complexity centrally.
2Measurement precision
If powerful computing units are installed at each IIS for local image processing, then object recognition accuracy improves, but system cost increases
Solution Approach 1:
The patent creates a universal remote server that serves multiple IISs with different computing capabilities. This single server performs object recognition for all connected IISs, eliminating the need for each IIS to have its own powerful computing unit. The server's deep learning models provide consistent high-accuracy recognition across the entire system.
Solution Approach 2:
The patent uses pre-trained deep learning models stored on the remote server that can be repeatedly applied to different images. Instead of requiring each IIS to have its own processing capability, the system copies the same sophisticated recognition algorithms from the server to process images from multiple sources, achieving high accuracy without duplicating expensive hardware.
3Productivity
If traditional object recognition techniques are used at the IIS, then commodity identification is possible, but additional equipment and labor are required
Solution Approach 1:
The patent enables the system to perform object recognition automatically without requiring additional weighing equipment or barcode scanners. The deep learning models on the remote server analyze images directly to identify commodities, allowing the IIS to serve itself by eliminating dependency on auxiliary devices and reducing the need for manual intervention.
Data Source
AI summary
A method for object recognition at an interactive information system (IIS) includes capturing, using an imaging device of the IIS, a first image of a first representative object which represents a first one or more object disposed about the IIS; analyzing, by a computer processor of the IIS and based on a category model, the first image to determine a first representative category of the first one or more object; retrieving, by the computer processor and based on the first representative category, a first representative object model of a plurality of object models that are stored on a remote server; and analyzing, by the computer processor and based on the first representative object model, the first image to determine a first representative inventory identifier of the first representative object, which represents a first one or more inventory identifier corresponding to the first one or more object respectively.