We Keep Coding

What is algorithm to detect a shape on some image? [duplicate]

I want to detect a circle, rectangle shaped object in an image and read the information from that object. Is there any api in java which will be helpful to me?
Ex: Detect a round shaped coin in a white background and obtain information about that that coin like ( value of a coin, etc.)
Thanks.

Here's an answer to a similar question for C++.
For Java, you can use the OpenCV wrappers. However, once you understand the essence of the approach you should be able to solve your problem using whichever framework is available.

Circles are perfect targets for the Hough transform. Check this out Detect circles with HT and OpenCV
Rectangles are a bit harder since the Hough Transform is not rotation invariant. You can go into edge detection and fast fitting (Fast line and rectangle detection by clustering and grouping)

Collision detection on a rotated Image

How would you go about detecting collision on a rotated Image in a game? I am making an asteroids game an I cannot figure out how to make the asteroids properly collide with the rotated spaceship.

If the rotated object is one that implements the Shape interface, it may have a useful implementation of the contains() method.

In paint(), as you prepare to draw the in-motion image, check the pixel colors of the destination points and look for the target object's color(s). The in-motion image and the target object must be, of course, different colors.

Pixel-perfect collision detection, ie. collision detection between images, is generally really hard to do efficiently. For that reason, it is generally a good idea to use an existing, optimized library built for that purpose.
Since you also need support for rotated images, I recommend PoxelColl. It supports pixel-perfect collision detection as well as basic transformations such as scaling and rotation. It provides a Scala port, which is compatible with Java.

What exactly are you using for collision boundaries of your asteroid?
Simplest might be that you can just use circles for everything and implement a circle-circle collision detection (just google it). This may not visually pleasing if your images are not very circle like.
Otherwise, if you have rotating rectangles colliding with other rotating rectangles then you'll have to implement an algorithm using Separating Axis Theorem for 2D Rotated Rectangle Collision.
Another option might be pixel perfect collision detection which is what Chuck was talking about. A quick search turned up this forum post. Proceed with caution though, this method's performance degrades with the size of your images.

Rasterizing a triangle in Java

Is there a Java graphics library that will rasterize a triangle given the coordinates of the vertices?
I'm trying to analyse the pixel values of an image for the triangular region defined by three points. I have the pixel values in memory, so I just want to figure out which pixels are in the triangle and iterate through them. The order of iteration is irrelevant, so long as I visit each pixel once.
I've done some searching for algorithms, and I think I could implement my own code based on Triangle Rasterization for Dummies, or an Introduction to Software-based Rendering, but I'd feel stupid if I overlooked some library that already implements this.
I briefly looked at getting Java to talk to the GPU, but that seems to be too much hassle.

You can use Polygon Shape to represent the tringle. Then use one of the contains() method passing Point2D or just two doubles params.

converting a 2d window point to a 3d point

i am writing a 3d modeler similar to Blender for a game i am making. Since programs like blender export very complicated file types with alot of unneeded data i wanted to write a simple editor for my game. what i cannot figure out is how to map a point from a 2d projection on the window to where i have clicked in the 3d world with the world being rotated.
If anyone knows any good tutorials on how to do this or the method any help would be appreciated. I know i could use ray tracing but that would be to complicated i think.

The two main methods of mouse picking are:
Intersection Testing
Color Picking
Intersection tests are the more popular of the two, and at the simplest level involves 'shooting' out a ray and checking if it has intersected any points. The ray can also be replaced by a polytope if one wants to achieve more sensitive picking (useful for choosing points on vertices).
Color picking involves disabling AA, blending, shadows, etc. and re-drawing the scene using solid colors for the objects. glReadPixels is then used to find the color at the point of the mouse and this color is used to determine if it clicked on an applicable object.
Ray Picking:
Mouse Ray Picking Explained
Picking, Alpha Blending, Alpha Testing, Sorting
Color Picking:
OpenGL Selection Using Unique Color IDs
Picking Tutorial

The term you are looking for is mouse picking.

The method you need is gluUnProject. You'll need window x,y and the depth.
I think, in your case, it might be a lot easier to write a simple exporter for Blender.

how to detect shapes in an image?

I want to detect a circle, rectangle shaped object in an image and read the information from that object. Is there any api in java which will be helpful to me?
Ex: Detect a round shaped coin in a white background and obtain information about that that coin like ( value of a coin, etc.)
Thanks.

Here's an answer to a similar question for C++.
For Java, you can use the OpenCV wrappers. However, once you understand the essence of the approach you should be able to solve your problem using whichever framework is available.

Circles are perfect targets for the Hough transform. Check this out Detect circles with HT and OpenCV
Rectangles are a bit harder since the Hough Transform is not rotation invariant. You can go into edge detection and fast fitting (Fast line and rectangle detection by clustering and grouping)