Can anyone suggest good algorithms for CBIR?

Question

Project: Content Based Image Retrieval - Semi-supervised (manual tagging is done on images while training)

Description

I have 1000000 images in the database. The training is manual (supervised) - title and tags are provided for each image. Example: coke.jpg Title : Coke Tags : Coke, Can

Using the images and tags, I have to train the system. After training, when I give a new image (already in database/ completely new) the system should output the possible tags the image may belong to and display few images belonging to each tag. The system may also say no match found.

Questions:

1) What is mean by image fingerprint? What is the image fingerprint size expected ? (important because there will be millions of images to be inserted in database)

2) What is the field format of that fingerprint in the database ? (important because a fast search is needed … script should search in a 1M images database in less than 1 second)

3) What is the descriptors (algorithms) we use to analyze them ?

Thanks in advance

Waxplant

I suppose that fingerprint means the feature vector of the image. – Outbid

Yeah, but can you kindly tell me what is the size and how should I store the fingerprint...1 for every image or 1 for every tag or 1 for combination of tags...becoz there are millions of images...Also can you share which feature extraction methods to use... Thanks for your reply... – Waxplant

The "feature vector of the image" has to be computed for every image, obviously. Try to read some research papers on image classification. I think your question has no single correct answer. – Outbid

Thanks... As a start, can you propose some algorithm and the corresponding fingerprint size, fields.... I will take your suggestion and read some papers.. – Waxplant

Answer 1

Well, this topic is very large, but here is a brief overview of a possible solution

1. Image fingerprints are collections of SIFT descriptors These are quantized both to reduce size, and to allow indexing

2. Build an inverted index of your database to allow looking up an image by quantized descriptors (you can use any full text search engine \ DB for this)

3. Given an image, lookup images which share a large amount of common descriptors

4. For those potential candidates, you should validate that the spatial arrangement of descriptors is similar enough

Some articles to get you started:

Philbin, James, et al. "Object retrieval with large vocabularies and fast spatial matching." Computer Vision and Pattern Recognition, 2007. CVPR'07. IEEE Conference on. IEEE, 2007.

Philbin, James, et al. "Lost in quantization: Improving particular object retrieval in large scale image databases." Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on. IEEE, 2008.

Mikulík, Andrej, et al. "Learning a fine vocabulary." Computer Vision–ECCV 2010 (2010): 1-14.

Tacnaarica

Thank You for the response.... I will go through the above references and try for my project...\ – Waxplant

Answer 2

I would suggest to train SVM model on list of image features extracted from training images

Ovipositor

Answer 3

1. Image fingerprint: a meaningful representation of the image. You can't use the single pixels of course. The most rational way to do it is to minimise the correlation between basis. In simple words, if you take a 64x64 image probably the two pixels at the top left corner will be the same or similar. It's useless to use as input each single 64^2 pixels, you need something better. Try to have a look at what Principal Component Analysis does.
2. It's entirely up to you. Extremising it, you could use a bit, that tells you whether the image is dark or not. Better, you do PCA on the image and experiment with different numbers of features (it's not always the case that more features is better)
3. Whatever you want, there are a lot of algorithms you can use. I'd recommend Support Vector Machines. Easy to use and well supported. If you have a lot of different tags you probably have to tray one SVM for each tag. That may not be ideal and you may want to try something else.

Sanchez