عنوان مقاله
الگوریتم لبه یابی بر اساس حاصل ضرب چند مقیاسی با تابع گاوسی
فهرست مطالب
چکیده
مقدمه
حاصل ضرب چند مقیاسی موجک
الگوریتم پیشنهاد شده
تحلیل آزمایش
نتیجه گیری
بخشی از مقاله
حاصل ضرب چند مقیاسی موجک
سطح خاکستری تصویر تحت رزولاسیون مختلف در یک صحنه، دارای عملکرد متفاوتی می باشد. لبه شی بزرگ به وضوح مشهود می باشد اما تراز شی کوچک تحت رزولاسیون پائین تحلیل می رود. اثر لبه در یک مقیاس ایده آل نیست، بنابراین لبه یابی در مقیاس متفاوت لازم می باشد.
کلمات کلیدی:
Edge Detection Algorithm Based on Multiscale Product with Gaussian Function Zhao Xiaoli∗ College of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620 Abstract According to Mallat multi-resolution analysis, A new edge detection algorithm based on multiscale product is presented, which uses Gaussian function and its first-derivative as lowpass and highpass filter to enhance edge and suppress noise, then detect edge embedded noise by gradient direction and updating search method. The experiments show that this approach has advantages of detecting edge in different gray contrast, high signal-noise ratio and pixel-level location accuracy. Keywords: multiscale product; Gaussian function; edge detection, ;gradient direction 1 Introduction Edge is the important characteristic of image. Edge detection technique specially address the problem of image enhancement, segmentation, recognition and registration. It is also an important research issue in computer vision and pattern recognition. Image edge is often buried by noise, so it’s significant to research edge detection algorithm. Traditional edge operators, such as SobeOǃRobertsǃPrewitt and canny etc, have conflict between suppressing noise and edge location because noise and edge are high frequency components. In recent years, some new theory are applied in edge detection such as morphology[1], neural network[2] and wavelet transform[3~4]. The researching results[3~4] indicate that multiscale product of edge increase exponentially ∗ Corresponding author. Tel.:+8613564034656 E-mail address: evawhy@163.com
