2d Geometric Shape and Color Recognition Using Digital Image Processing

The paper discusses an approach involving digital image processing and geometric logic for recognition of two dimensional shapes of objects such as squares, circles, rectangles and triangles as well as the color of the object. This approach can be extended to applications like robotic vision and computer intelligence. The methods involved are three dimensional RGB image to two dimensional black and white image conversion, color pixel classification for object-background separation, area based filtering and use of bounding box and its properties for calculating object metrics. The object metrics are compared with predetermined values that are characteristic of a particular object’s shape. The recognition of the shape of the objects is made invariant to their rotation. Further, the colors of the objects are recognized by analyzing RGB information of all pixels within each object. The algorithm was developed and simulated using MATLAB. A set of 180 images of the four basic 2D geometric shapes and the three primary colors (red, green and blue) were used for analysis and the results were 99% accurate.