top of page

Pixta AI solution
for Retail Customer's behaviors

Use case

The customer is a Japanese chain of general merchandise and department stores. During the outbreak of Covid-19, they start to apply a customer monitoring system to detect face mask wearing condition of consumers in shops.
To help testing the customer’s monitoring system, Pixta works on selection of 2,000 human face images in balance of mask wearing condition, age, gender and light condition; with bounding box of the face and label gender of image’s subject.


Face data & mask wearing data are initially selected from PixtaStock library automatically by a computer vision model. The review team then just need to double check and finalize the dataset with lower workload.


2,000 images are delivered in each subset under high satisfaction level. The customer could test & enhance their system to a higher accuracy.


  • The customer is sure that the dataset delivered on time to match with their project schedule, without any concern regarding legality of human data.
    To Pixta: Accuracy is maintained at 97% from planning to delivery, involve less human resource to fulfill the task


Easy steps to annotate, curate & manage Computer Vision data.

bottom of page