Iris Detection on Faces

If you want to find a distance between two eyes or two eyelids in mm, you can have difficult in this. Because, you can measure iris in pixel but you can't in mm. You need have a reference. So, we chose iris as a reference point. The reason of selecting iris is all people have mostly same iris diameter which is 11,8 mm. So, we tried to detect iris on human faces. Firstly, we cropped eyes on each face photo and carried out circle detection. Here are some results.

Comments

New Method to Take an Correctly Images

To take a correct images are very important to get good results.We have tested a lot of photos. We couldn't get correct result some photos to detect types of eyes. So, most important thing, it must be straight face pose when you take a photo. We are trying to avoid to take a picture with wrong angle.

Creating a Database for Wide-Close-Normal Eyes

In this stage, we are trying to classify different eyes shapes. The most important thing in this classification is distance between of two eyes. For example, if the space between two eyes is smaller than the width of one eye, this is close set eye or if vice versa, this is wide set eye. For normal set eyes, we specified a tolerance value and tested over approx. a hundred images. Then, we classified these images which called wide-close- normal eyes. In next stage, we will try in our program each image and make a histogram to get a correct result for classification. For instance this is close set eyes. Normal Set Eyes Wide Set Eyes Close Set Eyes

This my second day in this university. Today, we went to science center with Dr.Waleed in the campus center. Waleed showed me fish eggs. I will develop smart app that can counting fish eggs. I am gonna use IOS platform this application. It is impossible to devolop an app witout Mac computer. I haven't got a Mac but will setup MacOS on Windows via virtual machine. Actually I have never worked with IOS platform but I will try it.

Internship Daily

Search This Blog