I am using C# with asp.net for re-ranking images based on Content retrieval.
The concept of my work as:
1. Extracting visual features for all images.
2. Find the similarity between a query image and rest images.
3. Finally, re-ranking the images based on their similarity to the query image.
Now, I chosen (FCTH & SURF) for extracting visual feature of the images. But, I need another method to extract visual features.
What method is the best for this purpose?
Mustafa,
As said by Khan Muhammad, the current trend in classification and detection on images is motivated by Deep Learning, precisely, Convolutional Deep Neural Networks. In case you have an abundance of data to train, then go ahead with models like Alexnet but in case, you do not have sufficient data, then learn about already trained caffenet and retrain it with your data so that it adjusts itself to your problem domain.
You can train models on Caffe/Theano frameworks and use their wrappers in your C# application for inference(testing) phase.
Hope this helps.
kind regards,
Ankit Tripathi
Recently, Convolutional Deep Neural Networks achieved significant performance on the visual feature abstract extraction. Some open-source frameworks like: TensorFlow, Torch, Theano, MXNET, Caffe provide the C++ or python APIs. So you can build the visual feature extraction library and integrate with C# application.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Graphs