Image Aesthetics Assessment
One of the biggest challenge facing any user generated content driven platform is to showcase high quality images to users. Our work focuses on the automatic assessment of image aesthetics using Convolutional Neural Network (ConvNet). The constraint of fixed size input in ConvNet compromises the aesthetics of original image. We incorporated the Adaptive Spatial Pooling technique to address this problem by fixing the layer size just before the Fully Connected Layers in ConvNet. This preserves the original image composition and enables the model to learn aesthetic features without any transformations. NLP classification and sequence pattern recognition problems also falls under the purview of this work.
Amit Kushwaha is a Machine Learning Engineer at Zomato. His major areas of interests are Deep Learning and Natural Language Processing. He completed his undergrad from IIIT-Allahabad with major in Electronics and Communication.. Some of his notable projects in the Deep Learning includes Synthesizing Insights and actionable items from user opinions and reviews , Photo Classification tailored to Food search and Discovery platforms and EyeQ (Image Quality and Aesthetics determination). He dreams to pursue Artificial Intelligence as an independent researcher in future.