Search

EP-4525425-B1 - SYSTEM AND METHOD FOR GENERATING RECOMMENDATIONS DURING IMAGE CAPTURE OF A PRODUCT

EP4525425B1EP 4525425 B1EP4525425 B1EP 4525425B1EP-4525425-B1

Inventors

  • Lui, Benjamin
  • SAI NIHAS, Guduru
  • BATLOUNI, SALIM

Dates

Publication Date
20260513
Application Date
20210330

Claims (15)

  1. A computer-implemented method comprising: obtaining a camera live stream from a camera in a user device, the camera live stream including image data of a particular product; processing the image data of the particular product to identify image features specific to the product; determining that one or more of the identified image features are outside of a threshold of one or more of baseline image features common to images of one or more products of a collection, wherein the baseline image features include at least one of image resolution, pixel density, image brightness, depth of field, focus, size of product in the image, angle of product in the image, orientation of product in the image, or contrast between the product and the background; generating one or more recommendations to adjust one or more settings of the camera; and automatically using the recommendations to adjust the one or more settings of the camera in a series of repeating of the determining and generating steps until the one or more of the identified image features of the image data of the particular product are within a threshold value of the one or more baseline image features.
  2. The computer-implemented method of claim 1 further comprising generating, for display together with the camera live stream on the user device, the one or more recommendations.
  3. The computer-implemented method of claim 1, wherein the one or more recommendations are recommendations to adjust the one or more image features of the image data of the particular product.
  4. The computer-implemented method of claim 1, further comprising: responsive to the one or more of the identified image features of the image data of the particular product being within the threshold value of the one or more baseline image features, causing the user device to capture one or more images of the particular product.
  5. The computer-implemented method of any of the preceding claims, further comprising: analyzing the image data of the particular product to identify the particular product; and obtaining images of the one or more products of the collection based on the identified particular product.
  6. The computer-implemented method of any of the preceding claims, further comprising: prior to obtaining the camera live stream, obtaining information regarding the particular product; and obtaining images of the one or more products of the collection based on the information regarding the particular product.
  7. The computer-implemented method of any of the preceding claims, wherein the images of the one or more products of the collection are images previously captured by the user.
  8. The computer-implemented method of any of the preceding claims, wherein the recommendations are generated for capturing a further image of the particular product more consistent with the baseline image features.
  9. The computer-implemented method of any of the preceding claims, wherein the one or more recommendations include at least one of a shape, text, image of a related product, or an animation.
  10. The computer-implemented method of claim 1 further comprising initiating a capture event to capture an image of the particular product using the camera.
  11. The computer-implemented method of claim 10, wherein the capture event is initiated in response to a received instruction.
  12. The computer-implemented method of claim 11, wherein the received instruction is provided via one or more of a button press on a button associated with the user device or a screen tap gesture performed on a touch screen of the user device.
  13. A system comprising: one or more processors; processor-readable storage medium containing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to carry out the method of any one of the preceding claims.
  14. The system of claim 13, further comprising: a user device, the user device comprising: the one or more processors; a display coupled to the one or more processors; and a camera, the camera including an image sensor and being configured to provide the live camera stream to the one or more processors.
  15. A computer program which, when executed on one or more processors, is configured to carry out the method of any one of claims 1 to 11.

Description

FIELD The present disclosure relates to capturing images of products and, in particular, to generating recommendations during image capture of a product. BACKGROUND In some online catalog platforms, a user may be tasked with taking photos of one or more products. The products and/or photos may be related to one another and, as such, consistency amongst the photos is crucial. For example, photos may be taken of different products being sold at the same store or in the same collection. As another example, photos may be taken of different variants (colour, size, etc.) of the same product. A customer may view multiple related photos at the same time or may view the related photos in quick succession. Any visual differences in the related photos may result in a poor experience for the customer and may lead to reduced brand appeal and/or sales. BRIEF DESCRIPTION OF THE DRAWINGS Embodiments will be described, by way of example only, with reference to the accompanying figures wherein: FIG. 1 is a block diagram of an example e-commerce platform according to an embodiment;FIG. 2 is an example of a home page of an administrator according to an embodiment;FIG. 3 is a block diagram of another example e-commerce platform according to an embodiment;FIG. 4 is a block diagram illustrating an example system for generating recommendations during image capture of a product according to an embodiment;FIG. 5 is a diagram illustrating an example product image feature model in the form of a look-up table according to an embodiment;FIG. 6 is a flowchart illustrating an example method for generating recommendations during image capture of a product according to an embodiment;FIG. 7 is a flowchart illustrating an example method for obtaining images of one or more products in a collection according to an embodiment;FIG. 8 is a flowchart illustrating another example method for obtaining images of one or more products in a collection according to an embodiment;FIG. 9 illustrates a screen page according to an embodiment;FIG. 10 is a flowchart illustrating an example method capturing one or more images according to an embodiment;FIG. 11 illustrates a screen page according to an embodiment; andFIG. 12 illustrates a screen page according to an embodiment. DETAILED DESCRIPTION In some online catalog platforms, a user may be tasked with taking photos of one or more products. The products and/or photos may be related to one another and, as such, consistency amongst the photos is crucial. For example, photos may be taken of different products being sold at the same store or in the same collection. As another example, photos may be taken of different variants (colour, size, etc.) of the same product. A customer may view multiple related photos at the same time or may view the related photos in quick succession. Any visual differences in the related photos may result in a poor experience for the customer and may lead to reduced brand appeal and/or sales. Visual differences may result from a difference in aspect ratio, product view angle, camera angle, depth between foreground and background, lighting, background objects, background clutter, background composition, positioning of the product in the frame, etc. A user may take photos of related products and may attempt to correct any inconsistencies amongst these photos using post-processing actions. At this point, the user may realize that inconsistent photos may not be editable to achieve the desired consistency and thus will need to restart the entire process. This can be difficult and frustrating for an ordinary user and may lead to multiple wasted attempts. In accordance with one aspect, the present application provides system and methods for generating recommendations during image capture of a product. The systems and methods may obtain a camera live stream from a camera in a user device, the camera live stream including image data of a particular product. One or more baseline image features common to images of one or more products of a collection may be determined based at least on image analysis of image data of the images of the one or more products of the collection. The one or more baseline image features may be compared to one or more image features of the image data of the particular product and one or more recommendations may be generated. The one or more recommendations may be displayed together with the camera live stream on the user device. In this manner, recommendations may instruct the user to make adjustments to ensure the one or more image features are consistent with image features of one or more images in the same collection. In one aspect there may be provided a computer-implemented method. The computer-implemented method may comprise obtaining a camera live stream from a camera in a user device, the camera live stream including image data of a particular product; determining one or more baseline image features common to images of one or more products of a collection based