The PDF file you selected should load here if your Web browser has a PDF reader plug-in installed (for example, a recent version of Adobe Acrobat Reader).

If you would like more information about how to print, save, and work with PDFs, Highwire Press provides a helpful Frequently Asked Questions about PDFs.

Alternatively, you can download the PDF file directly to your computer, from where it can be opened using a PDF reader. To download the PDF, click the Download link above.

Fullscreen Fullscreen Off

   Subscribe/Renew Journal

Artificial Intelligence edge detection refers to a set of mathematical techniques used to recognize digital image locations. The picture brightness plays a vital role in detecting dissimilarities and making decisions. Edges are the sharp changes in pictures with respect to the brightness and are commonly categorized into a collection of curved line segments. The main focus of this paper is to find sharp corner edges and the false edges present in the MRI images. The canny edge algorithm is a popular method for detecting these types of edges. The traditional canny edge detection technique has various issues that are discussed in this paper. This study analyses the canny edge algorithm and enhances the smoothing filter, pixel identifier, and feature selection. The proposed Britwari technique, Tabu Search Heuristic Pattern Identifier (TSHPI) enhances the edge detection using SUSAN Filter. Feature Selection is performed to improvise the canny edge method. Deep Learning algorithm is used for classification of pre-trained neural networks to find a greater number of edge pixels. The implementation results show that the Britwari proposed technique (SUSAN Filter Tabu Search Heuristic Pattern Identifier Hill Climbing) reached better accuracy than the traditional Canny Edge Detection algorithms. The results produced better feature set selection using edge detection in MRI images.


Britwari Technique, Edge Detection, Deep Learning, Image Processing
Subscription Login to verify subscription
Font Size