One of the most incentive thing to learn any new topic or acquire a new skill is to find it solves a problem that may be difficult to solve with your existent knowledge.
Today, Machine learning is a trending topic concerning about find patterns in data and use it to predict the future or analysis the past.
Recognizing objects in images is a fascinating thing in computer vision. It may be a trivial task for human but for a machine not.
In the last few years the field of machine learning specially, convolutional neural networks has made a huge progress on solving difficult problems like visual recognition and voice recognition. Researchers have demonstrated steady progress in computer vision by validating their work against ImageNet which is an academic benchmark for computer vision.
Using TensorFlow and Inception-v3 model, I built this small demo in Java to recognize objects in images and classify it into 1000 classes like Lion, Frog, Flowers, ....etc. The model I used Inception-v3 is trained for the ImageNet Large Visual Recognition Challenge using the data from 2012.Requirements: