After segmenting, how can I do uncompleted fruit image?

Dear Sir, I am doing Fruit Recognition System.Now I segmented fruit images.But I have a problem.Some segmented fruits are not completed.Which function can I use for uncompleted images.Thank you so much.

[Image Analyst]

There are hundreds of functions you can use, especially in the Image Processing Toolbox. I don't really know what uncompleted means, nor can I see your images because you forgot to attach them, so that's the best answer I can offer given what little you've shared with us. You might try searching for fruit since people ask about it about every month or two here.

http://www.mathworks.com/matlabcentral/answers/6200-tutorial-how-to-ask-a-question-on-answers-and-get-a-fast-answer

[Yuki Zue]

Thank you so much sir. I have example image (apple). This image is segmented using k-means clustering and threshold. But it has two color and final result is not completed.So I want to know which function can I add in this system.Most fruit images are completed.But some images are not ok. Thank you so much for your guidelines sir.

[Yuki Zue]

This image is final result sir.

[Yuki Zue]

Original image

Answer 1

[Image Analyst]

The problem is your segmentation algorithm is no good. It's better to fix that than to try to repair a bad segmentation with bwconvhull() or activecontour() or something.

I don't know what you want, but if you want just the apple, you can simply threshold. Just get any color channel and see if it is not 255 (pure white).

I don't know what you did for kmeans, but if you want the whole apple you should use k=2, though like I said that is not necessary. But for what it's worth, I'm attaching my color segmentation by kmeans demo to this post.