× Business
TelecomHealthcareDigital MarketingERPRetailMedia and EntertainmentOil and GasFood and BeveragesMarketing and AdvertisingBanking and InsuranceMetals and MiningLegalComplianceCryptocurrency
Big DataCloudIT ServiceSoftwareMobileSecurityNetworkingStorageCyber SecuritySAPData AnalysisloTBio TechQuality AssuranceEducationE-commerceGaming and VFXArtificial Intelligencescience-and-technology
Cisco DATABASE Google IBM Juniper Microsoft M2M Oracle Red hat Saas SYMANTEC
CEO ReviewCMO ReviewCFO ReviewCompany Review
Startups Opinion Yearbook Readers Speak Contact Us

Watch out for AI technology in video editing!

siliconreview Watch out for AI technology in video editing!

Video editing can be made interesting. There is no doubt that artificial intelligence has gained popularity in the recent years. There is yet another addition to the same. Spektral, a Danish startup, is the latest venture-backed visual effects company is announcing a $2.8 million round today from Litecap and Amp Ventures to continue development of its machine learning-powered, real-time, green screen technology.  The augmented reality and its influence have already made big giants to invest more into the same. This new initiative is all about combining the machine language with spectral graph theory to separate people and objects from their original backgrounds and overlay them in a new stream. We can add a totally different background to those selected images thereby making it more interesting. The technology is termed as Green Screen Technology

But the technology is not easy as it looks. Toke Jansen, the founder and CTO of Spektral has expressed his views on the topic. The process of separating video and image, which are two entirely different monsters is difficult to handle, he said.  Though technology is rich with deep learning technologies and AI, still it is harder to separate and to bring an entirely different view. Recent years there has been a growing interest in developing effective methods for Content-Based Image Retrieval (CBIR). Image clustering and categorization is a means for high-level description of image content. The goal is to find a mapping of the archive images into classes (clusters). Spektral, as the name implies, is experimenting with spectral clustering for image segmentation within a video frame by through AI technology.