A novel image recognition technique for 3-dimensional objects

The need for better image processing has lead to the emergence of many techniques, which aim to achieve faster and cheaper operations. Multiscale analysis for edge detection is a powerful approach to image recognition. However, this approach suffers huge computational and time cost which, consequently, jeopardise its efficiency. This paper presents a new technique in image processing that aims to reduce the high computational cost, to provide rapid 3-dimensional object recognition and which has a wide domain of applications. The novel automatic edge detection scheme (AEDS) combines neural network technology with multiscale analysis, to achieve automatic recognition of high and low contrast images that contain two or three-dimensional objects. The AEDS is based on applying scale space analysis using the Laplacian of a Gaussian edge detection operator, together with a neural net work model. This technique is applied to detect potential real life military targets. The AEDS is a fast, user-friendly and low-cost image recognition technique that offers great potential for applications in other fields such as the medical field or in industrial applications.