Background
Computer Vision is a field of Computer Science that enables computers to see, identify and process images in the same way that the human vision does. It then provides the appropriate outputs.
We, at SolCen are always excited to welcome new innovations in the tech industry. Providing business solutions with an X factor to one of the biggest fashion house in the world means that we must strengthen our technical capabilities at every step. Many of our projects require deep analysis of images through features such as comparison, text detection etc. To meet the deadlines and maintaining efficiency is what motivated us to explore the world of Computer Vision.
By the end of last year, we started digging deeper into the concepts of Computer Vision through Machine Learning by generating multiple proofs of the concepts in the field.
The goal of Computer Vision is to emulate human vision using digital images through three main processing components, executed one after the other:
Application
Computer vision @ SolCen
We also performed an Image Classification using the Faster RCNN Neural Network, to create a successful POC for the same.Here, we trained the model to identify different features of images and classified them based on their type of handbags.
Month- Long researches have helped us gain expertise on cloud environments for Deep Learning and Computer Vision and their API’s provided by tech giants like Google, Microsoft and Amazon. We often use Microsoft’s Azure Machine Learning Studio and Google Vision API’s to generate basic models on various concepts and to test accuracy.
Miles to Go
Here at SolCen, Innovation is greatly valued and themed events like Hackathon, are conducted every year. Computer Vision was this year’s theme, where employees were encouraged to come up with different ideas around it. Over the past few years, fashion brands and retailers have been keen to implement computer-vision-powered solutions. As we move along, we plan to connect multiple applications with image processing models to enable better decision-making capabilities for businesses and automate manual processes. The Innovation team is also working around ideas to connect the concept of Computer Vision with Augmented Reality, NLP (Natural Language Processing) and other aspects to have a future-ready innovative system.
