The Last Summer Holiday at IIIT-D

"The holidays are about to end."

Those are the 6 words I'm literally dreading for the first time. It's 27th today and my institute reopens on the 1st of August. That leaves 4 days. 4 days to switch from the relaxed holiday routine to the strict demanding life of a student. 4 days to complete all the sleep I want and some extra for the next 4 months. 4 days to decide which subjects I have to take next semester. 4 days to think and finalize my B.Tech Project (BTP). 4 days to go over the entire summer once again in my mind...

This summer was so much different than the previous two of my college life. I did not do multiple projects like the previous summers. I tended to sit at home most of the time and remain online. I didn't go to IIIT-D as frequently as in the previous summers. Yet whenever I went, I made sure to have a glass of Nestea (Nescafe's Lemon Iced Tea). This was my last summer of undergraduate life and it is painful to accept the fact that there might not be anything called "Summer Holidays" ever again.

I tried out some things this summer which I hadn't done for a while or which were completely new. Web designing and image editing was something I had last done in school. That time I had used Dreamweaver and Photoshop. This time it was Microsoft Expression Studio and GIMP. It was a different feeling to do something like this, when all I had ever done here was programming and making presentations. A new thing which I started was learning the Japanese language. I had a keen interest in all things Japanese since a long time, and decided to learn the language on the suggestion of a friend. Hopefully I will not be needing subtitles for watching anime in the near future.

One of the best experiences was volunteering for the B.Tech counselling. This time it was done over two days. It was fun advising the parents and students who had mixed opinions about IIIT Delhi. Once again, I realize painfully that this is something which I will miss next year. I also applied to be a mentor to the first years (another last time). The orientation is tomorrow and unfortunately I have a bad cold since yesterday. I'm not sure if I will be able to attend. I hope I can.

I had a lot of sleep this summer too. Well, next 4 months are going to be pretty heavy. Might as well stock up on some sleep. And I loved this slow and relaxed way of life and wished I had spent the previous summers like this too. That's a regret I have. I wish I hadn't been a workaholic.

There were lots of things I couldn't figure out even in these 3 months. I still don't know what to do after this year when I pass out. Should I go for higher studies or do a job? I haven't yet figured out my true area of interest in computer science. There are a group of areas I like but none as of now which I can say is my true interest. I haven't yet finalized my BTP. More important, I couldn't decide which courses to take the coming semester. For the time being though I have decided to stop thinking of all these. This summer I had to face a lot of disappointments (other than the ones above). Thinking about them constantly makes it worse. I don't want to do that. I just want to forget it.

Overall, this summer was far from being a perfect summer. There were islands of happiness surrounded by the sea of gloom all around. It can hardly be called productive (in the workaholic sense of the word). Yet I still think it was the best I have had. I learnt lots of important lessons which I wouldn't have had otherwise. Some of it was painful though and I still mentally wince when I think about it.

I'm reminded of a quote (and the main theme) of an anime called Kino no Tabi (Kino's Journey). It says, "The world is not beautiful, therefore it is". I can apply the same here.

This summer was not beautiful, and therefore it was.

Search using Images is now a Reality

(This post was written some weeks earlier but somehow I never published it and it remained in the drafts. Some references might be a bit outdated)

Finally it has happened! We can now search for an image using another image. Yes, Content Based Image Retrieval (CBIR) has finally been rolled out by Google. You can try it out on Google Image Search.

I can't express how it felt when I saw it has been released. Indeed, it was like a dream come true. A new and long awaited dimension has been added to search. No longer are we constrained by words. Indeed, a picture is worth a thousand words.
I was (and still am) fascinated with this idea. So I thought of writing about it

Since my fourth semester (around Jan 2010) I had been fascinated with this idea. At that time it was something new to me, something I had never thought about. Basically it was this - "how would it be, if we could search using images?". Now what got me into thinking this? At that time I was taking a course named Research Methods. Our instructor (Dr. PK) had created a mailing list for discussing about interesting research. One day, he posted a link. 

Picture-driven computing: New research could enable computer programming based on screen shots, not just code.

This got me thinking. If they could program using images, then why not search using images? That's when I started getting excited about this topic. I replied enthusiastically to this post and I described CBIR in brief. At that time however I didn't know much. On searching more I found out about Google Goggles and Tineye. During the summer holidays, I devoted my spare time to find out more about this topic. The ACM Chapter at IIIT Delhi releases a half yearly newsletter called Kaleidoscope. I was part of the editorial board and wrote an article on CBIR. (You can download it here)

After going through some research papers, I felt like creating a working prototype. The Next Semester (5th sem Aug-Dec 2010) I took the Image Analysis course. That's when I thought of doing this. I and my friend Vibhas took up this as our course project.

Needless to say, we did not even aim for creating a web image search engine with CBIR. Our aim was only to create a working prototype with somewhat good accuracy. The image would be stored locally in the computer. We worked on it throughout the semester (and gradually realized that CBIR is not an easy thing to implement). Every research paper we read, gave us a new idea but at the same time pointed out the problem with another. We decided to focus only on colour, shape and texture out of which only the colour based algorithms worked with a relatively good accuracy. Even then there were problems - a search with red apple turned up images of a red Ferrari.

A Screenshot of our Image Search Engine using CBIR

Even though our implementation did not use any sophisticated algorithms, it was a wonder for many. When it was showcased in the Research Showcase, lots of people were excited to try it.

Now that I understand how difficult it is to implement on a large scale, I give me heartiest congratulations to the Google Team. You guys did what I could only dream of!