Research On Adaptive Edge Detection Viagray Value Differences Of Points

With computer science developing and the growing demand of various industries,digital images play an important role in many aspects of life.It is a method for capturing useful information for people from images.It is an important research field in feature extraction and useful for subsequent processing.Therefore,edge detection is a valuable research area in image processing.Improving accuracy of edges and exploring the application of in practical engineering are important research contents of it.Identifying points in image where brightness changes significantly is the main task;significant changes in the image properties usually reflect important events and changes in the properties,these changes include discontinuities in depth,discontinuities in surface orientation,changes in material properties,scenes and lighting.Edge detection has a long history,bearing various methods,but there are still some shortcomings;in some specific cases,the optimal edge of the target object cannot be detected.Therefore,improving the existing methods or designing new methods due to specific requirements is the main direction of research in the field of edge detection.In this paper,by computing gray value differences between each point and its each neighbor,the adaptive edge detection is proposed to measure the local gray value variation around a point,which can obtain edges with high precision and continuity.Different from operators based on first-order or second-order derivatives,proposed method use the gray value difference between two adjacent points as the metric function for edge detection.Proposed method calculates the gray value difference between the current point and its neighbor,and then reserving both of them where the difference reaches most as the primary edge point.In order to reduce the number of missing edges and ensure proper continuity of the edges,the proposed method first detect the 3 × 3 neighbors centered on each point and get the threshold by an adaptive strategy;then expand the range of neighbors to 5 × 5,filtering redundant points out using threshold obtained in the previous step.Finally,an endpoint selection strategy is proposed to get the more accurate edge detection results.The results show the method can obtain accurate and continuous edges of good quality.The contributions of this paper include three aspects:1.The gray value difference between each point and its neighbor point is used as the metric constraint,and the neighbor point with the largest difference is pre-selected as an edge point.The calculation is simple and easy to understand,some non-edge points can also be reduced.2.A novel adaptive threshold strategy is proposed,which can reduce the redundancy of edge points.At the same time,the threshold calculated on the 3 x 3 units is used to filter 5 x 5 units,retaining more meaningful weak edges.3.According to the area which the pre-selected edge point belongs to,a novel endpoint selection strategy is proposed to make edge positioning more accurate,and it can obtain better visual effects without edge refinement.In the experimental content,this paper uses Berkeley dataset and other data sets for experimental comparison,and uses a common edge detection index such as PR value and FOM value to carry out a series of image edge detection experiments.The experimental results show that compared with the traditional methods and some emerging multiple edge detection algorithms,the proposed algorithm can maintain the continuity of the edges,preserve the more detailed features of the image,and ensure the quality of the edge detection.Both aspects of quantitative data show significant advantages.