現在この質問をフォロー中です
- フォローしているコンテンツ フィードに更新が表示されます。
- コミュニケーション基本設定に応じて電子メールを受け取ることができます。
エラーが発生しました
ページに変更が加えられたため、アクションを完了できません。ページを再度読み込み、更新された状態を確認してください。
古いコメントを表示
I am able to find pupil circle but not able to find iris circle from these images. I'm using Iris Recognition Libor Masek code for segmentation. http://www.csse.uwa.edu.au/~pk/studentprojects/libor/sourcecode.html Can anyone tell me if it is possible to segment iris from these images


採用された回答
Image Analyst
2013 年 4 月 13 日
No, this eye pretty much has no iris. Best you can do is to find the center of the pupil and go out a predetermined radius from the center, assuming this iris will be the average diameter iris.
8 件のコメント
Harish
2013 年 4 月 13 日
Thanks, i'm fixing distance from cam to eye constant so eye iris radius will be constant. Will I be able to do Iris recognition by this method?
Image Analyst
2013 年 4 月 13 日
Probably. Unless you have lots of people with no irises, or white irises, in which case it might be hard to distinguish between them. But I've never seen an eye like that so that person is probably fairly unique and rare. Or else they have a very blue iris and you're looking at only the blue channel.
Yes its on blue channel, Actually I modded webcam by removing ir filter and placed an ir source on webcam to get this image on completely dark room. If this isn't good enough i might put an visible led at some distance for clearer iris boundary. Will that be good?

this is original image obtained without processing
Image Analyst
2013 年 4 月 13 日
Why do you want to do iris recognition on images without any visible structure in the iris? I don't see what that gained you. In the visible there would be more visible structure and it should be easier to characterize the iris and compare them in different people.
So is it best to do in visible light than in infrared? Thats my eye i guess thats the pattern i have. Image taken in visible light. My eye is not blue but i'm getting blue eye but other people get it right.

Image Analyst
2013 年 4 月 13 日
I would think so, but you'd better check how people do it in section 21.5.3 and subsections here: http://iris.usc.edu/Vision-Notes/bibliography/contentspeople.html#Face%20Recognition,%20Detection,%20Tracking,%20Gesture%20Recognition,%20Fingerprints,%20Biometrics. You're not pioneering new ground here (that I can see, at least not yet), so you might as well follow the examples of people who have done it successfully before you and published working results.
Harish
2013 年 4 月 13 日
Thanks for the reference. I was able to segment the 1st eye.

and this is normalised and polar form image


Will this be useful for Iris recognition? I mean the information will be enough for performing matching?
Image Analyst
2013 年 4 月 13 日
I would guess not. You have clutter from the upper eyelashes, a line from the lower lid, and no structure in the iris. But I'm not an expert in iris recognition. I expect you'll learn a lot more from those papers I referred you to than from me, once you get around to looking at them, which I hope you will do.
その他の回答 (0 件)
カテゴリ
ヘルプ センター および File Exchange で Object Detection についてさらに検索
参考
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!Web サイトの選択
Web サイトを選択すると、翻訳されたコンテンツにアクセスし、地域のイベントやサービスを確認できます。現在の位置情報に基づき、次のサイトの選択を推奨します:
また、以下のリストから Web サイトを選択することもできます。
最適なサイトパフォーマンスの取得方法
中国のサイト (中国語または英語) を選択することで、最適なサイトパフォーマンスが得られます。その他の国の MathWorks のサイトは、お客様の地域からのアクセスが最適化されていません。
南北アメリカ
- América Latina (Español)
- Canada (English)
- United States (English)
ヨーロッパ
- Belgium (English)
- Denmark (English)
- Deutschland (Deutsch)
- España (Español)
- Finland (English)
- France (Français)
- Ireland (English)
- Italia (Italiano)
- Luxembourg (English)
- Netherlands (English)
- Norway (English)
- Österreich (Deutsch)
- Portugal (English)
- Sweden (English)
- Switzerland
- United Kingdom (English)
