Show attend and tell, a communication system

Show, attend and tell: Fine details of how state-of-the-art deep learning systems generate image captions

by koustubh • January 13, 2017

How would YOU communicate with Aliens ? How would you teach them your language ? The way we teach children right ? By showing them pictures of various objects and their names. Basically Associating the Image and the Text. That’s the goal of automatic image captioning. It is an extensive topic and decades of research has gone into […]

Continue Reading

Case-Study: Better HAAR feature-based Eye Detector using OpenCV

by koustubh • January 11, 2017

Motivation behind this post: Opencv object detectors which are built using Haar feature-based cascade classifiers is at least a decade old. OpenCV framework provides a default pre-built haar and lbp based cascade classifiers for face and eye detection which are very good quality detectors. However, I had never measured the accuracy of these face and […]

Continue Reading
Object detection for image search and computer vision using deep larning

Object Detection using Deep Learning for advanced users (Part-1)

by koustubh • December 24, 2016

Prologue:This is a three part series which will elaborate on Object Detection in images using Convolutional Neural Networks (CNN). First part will deal with groundbreaking papers in detection. Second part will give an overview on some of the fancier methodologies that have been published recently. Third part will be about one of our more sophisticated methods […]

Continue Reading