An algorithm for high-precision edge location of cannon barrel image based on human visual characteristics

A novel algorithm for high-precision edge location based on human visual properties is proposed considering characteristics of cannon barrel images, which improves the observation effect of spying bore images and diminishes the target image ambiguity caused by background and noise. The variable gray scale area method is applied according to the image feature diversity between the target and background/noise. The accuracy of edge detection and location is higher than 0.01 pixel when being applied for engineering. The imperfect images are correspondingly enhanced, and the target is thus shown clearly, which is convenient for observation by human eyes and actual measurement. The algorithm is more general-purpose and adaptive to different barrel image processing, and it can significantly inhibit noise for its glossy and enhanced effect.

[1]  Thomas O. Binford,et al.  On Detecting Edges , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Thomas O. Binford,et al.  Inferring Surfaces from Images , 1981, Artif. Intell..

[3]  Amir M. Tahmasebi,et al.  A novel adaptive approach to fingerprint enhancement filter design , 2002, Signal Process. Image Commun..

[4]  Gérard G. Medioni,et al.  Detection, Localization, and Estimation of Edges , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Tomaso A. Poggio,et al.  On Edge Detection , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Robert M. Haralick,et al.  Digital Step Edges from Zero Crossing of Second Directional Derivatives , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Owen Robert Mitchell,et al.  Edge Location to Subpixel Values in Digital Imagery , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Huang Lian-qing.  A Medical Image Processing Method Based on Human Eye Visual Property , 2001 .

[9]  Gérard G. Medioni,et al.  Detection of Intensity Changes with Subpixel Accuracy Using Laplacian-Gaussian Masks , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Manfred H. Hueckel.  A Local Visual Operator Which Recognizes Edges and Lines , 1973, JACM.

[11]  Martin A. Fischler,et al.  Detection of roads and linear structures in low-resolution aerial imagery using a multisource knowledge integration technique☆ , 1981 .

[12]  Gongzhu Hu,et al.  Subpixel edge detector using expectation of first-order derivatives , 1992, Electronic Imaging.