Icon

02_​Guided_​Analytics

Store layout and product placement has always been a key aspect for retailers for increasing product sales. Managing product placement of over hundreds of products is a challenging task performed using realograms and planograms. Previously, creating realograms was a difficult task often requiring manual activities.

With image recognition the only manual input to the process are the photos taken of the products themselves and of the store shelves. Deep Convolutional Neural Networks automatically recognize the products and their visibility to the customer, helping achieve an increased sales revenue. The decision maker can use the results to generate realograms.

A potential added benefit of the solution, if repeated periodically, is the improved shelf stock management. The neural network can learn when a product is in danger of falling out of stock and can raise the necessary alerts to commence a stock refill.

This business case demonstrates the product recognition capabilities of a machine learning model.

Image Recognition Use CaseGuided Analytics WorkflowStore layout and product placement has always been a key aspect for retailers for increasing product sales.Managing product placement of over hundreds of products is a challenging task performed using realograms andplanograms. Previously, creating realograms was a difficult task often requiring manual activities.With image recognition the only manual input to the process are the photos taken of the products themselves andof the store shelves. Deep Convolutional Neural Networks automatically recognize the products and their visibilityto the customer, helping achieve an increased sales revenue. The decision maker can use the results to generaterealograms.A potential added benefit of the solution, if repeated periodically, is the improved shelf stock management. Theneural network can learn when a product is in danger of falling out of stock and can raise the necessary alerts tocommence a stock refill.This business case demonstrates the product recognition capabilities of a machine learning model. Guided Analytics Required Environment and Required KNIME ExtensionsTo run this workflow, you have to have Python 3 environment and Keraslibrary on your local machine.Before running the workflow, following extensions of KNIME should beinstalled properly:- KNIME Deep Learning - Keras Integration (Labs)- KNIME Image Processing (Community Contributions Trusted)- KNIME Image Processing - Deep Learning Extension (CommunityContributions Trusted) Ask for method Upload Image predict and output Select from List predict and output Image Recognition Use CaseGuided Analytics WorkflowStore layout and product placement has always been a key aspect for retailers for increasing product sales.Managing product placement of over hundreds of products is a challenging task performed using realograms andplanograms. Previously, creating realograms was a difficult task often requiring manual activities.With image recognition the only manual input to the process are the photos taken of the products themselves andof the store shelves. Deep Convolutional Neural Networks automatically recognize the products and their visibilityto the customer, helping achieve an increased sales revenue. The decision maker can use the results to generaterealograms.A potential added benefit of the solution, if repeated periodically, is the improved shelf stock management. Theneural network can learn when a product is in danger of falling out of stock and can raise the necessary alerts tocommence a stock refill.This business case demonstrates the product recognition capabilities of a machine learning model. Guided Analytics Required Environment and Required KNIME ExtensionsTo run this workflow, you have to have Python 3 environment and Keraslibrary on your local machine.Before running the workflow, following extensions of KNIME should beinstalled properly:- KNIME Deep Learning - Keras Integration (Labs)- KNIME Image Processing (Community Contributions Trusted)- KNIME Image Processing - Deep Learning Extension (CommunityContributions Trusted) Ask for method Upload Image predict and output Select from List predict and output

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: Csaba_Brunner
Created at: 2018-06-21
On NodePit since: 2019-07-12
Last update: 2024-04-25
Created with KNIME version: v3.6.0

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!