• M.Sesha Sai
• K.Rohith
• G.S.Praneeth
• D.Nikhila
• N.Pavan Kalyan

Superimposing a component from a photograph into a painting is a difficult assignment. Applying photograph compositing methods using existing painterly stylization computations, which are worldwide to outcome a photomontage, are performed ineffectively when applied locally. We address these issues with the appropriate rules that cautiously decides the neighbourhood measures need to be considered. We guarantee both spatial and in- scale measurable consistencies to show that the two properties are critical in producing quality outcomes. To adapt to the decent variety of deliberation levels and kinds of canvases, we present a procedure to change the parameters of the exchange contingent upon the artistic creation. We show that our calculation delivers essentially preferable outcomes over photograph compositing or worldwide stylization procedures and that it empowers imaginative painterly alters that would be in any case hard to accomplish

Convolutional Neural Networks (CNN), Visual Geometry Groups (VGG), Gram Matrix

"Image Composition Using Deep Painterly Harmonization ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 4, page no.537-542, April-2020, Available :http://www.jetir.org/papers/JETIR2004077.pdf

"Image Composition Using Deep Painterly Harmonization ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 4, page no. pp537-542, April-2020, Available at : http://www.jetir.org/papers/JETIR2004077.pdf