Computer vision

Lingaro’s Research and Development teams have made computer vision a key field of focus since 2000. As a result, they are proficient in

  • optical character recognition and simple pattern scanning technologies used in document identification systems, and
  • a wide range of the most important computer vision and artificial intelligence technologies based on algorithms related to boosting, support vector machine, locality-sensitive hashing, and discrete phase models, among others.

Applications span a wide variety of business use cases including people tracking, object detection, parking lot vacancy detection, 3D scanning, global content based image retrieval, and contextual document scanning, to name just a few.

Business-ready computer vision systems from Lingaro allow you to:

Optimize on-shelf visibility

Verify the location of products and ensure their optimal presentation, proper categorical placement, and proportional share of shelf space. PSE (Product Search Engine) is a patented multi-object multi-detection system build as part of a project financed by the European Union Regional Development Fund. The PSE’s novel approach to image analysis involves providing a graphical vote space presentation, generating a proposition, aggregating votes in two iterative passes, and verifying the proposition with two cascade filters containing all minor algorithms necessary for effective object detection. Its accuracy is exceptionally high in comparison to that of systems taking the classic clustering approach to analysis.

Check the visual coherence of products' packaging

Identify similar product packaging, check the similarity of one product’s packaging vs. that of others, and design packaging that is consistent across multiple products. NEOS is a content-based image retrieval system that can perform advanced similarity analysis of the colors, shapes, and textures in thousands of images.

Maximize retail operational performance

Ensure forecast accuracy, location marketing effectiveness, scheduling efficiency, low-hassle queuing, and good sales results for your retail location. PTBA (People Tacking and Behavior Analysis) monitors customer engagement and location during time spent in a store.

Keep your product visually competitive

Judge the visual symmetry of your product’s packaging and ensure that it is not overshadowed by that of other products on the same shelf. VSA (Visual Saliency Analysis) performs deep spectral analysis of a product image in many scales to represent observational distances, identifies its most important and visually appealing graphical elements such as its logo, and then then compares the elements to others within the same image as well as to those of nearby competing products.

Hello!

Request feedback

Data Science Business Domain Leader

Szymon Urbański

Szymon is the Data Science Business Domain Leader at Lingaro. He has spent over 10 years working with data and has built Data Science teams serving clients in the CPG, OTC, automotive, telecom, banking, and insurance industries, among others. He believes there is only one truth – to be discovered in the data!