Harvey Mudd College
Computer Science 153
Problem Set 2
Due Friday, Sept 23, 11:59pm

Back to Problem Set 2 top-level page

Section 1: Pictures!

The goal of this part of the assignment is to build up our database of different pictures. We will then use these pictures to test object recognition strategies in future assignments.

At some point before September 23, each person should borrow the digital camera from me. With it, take a set of (at least) 20 pictures per person. (That way we will end up with about 200 pictures in our database.) Use the low resolution setting on the camera. This will keep the camera from filling up too fast.

At least 12 of your images should contain a single dominant object. The remainder of the images are up to you (keep in mind that these will be seen...). To get the 12 pictures of specific objects, you should pick three objects, place them in various environments, and take four pictures of each.

When you have taken your images, I will put them in the directory /cs/cs153/Images/a3/objectsF05 and email you a list of the file names. (Note that there is already a database of images in cs/cs153/Images/a3/objects from when this course was offered in the fall of 2000.) For each of your images, do the following:

Create a text file, with the same name as the image but a .lab suffix, that indicates something about the content of the file. Use the following format for your text file.



Save the text file in the same directory with the same name as the image, but the suffix .txt. Here is an example text file for the following picture:

Next section on Segmentation via Thresholding