Back to papers
    edge detectionimage processingCanny filterhysteresis

    A Computational Approach to Edge Detection

    John F. Canny
    📅 1986🏛 IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679-698, DOI: 10.1109/TPAMI.1986.4767851
    Problem

    This paper formulates the edge detection problem by defining performance criteria (high detection rate, good localization, and single response) and develops an optimal filter that satisfies them.

    Method

    The Canny method consists of four stages: Gaussian smoothing, gradient magnitude and direction computation, non-maximum suppression, and double-thresholding with hysteresis for edge linking.

    Finding

    The Canny edge detector was shown to be statistically optimal and outperformed previous methods, becoming the gold standard for edge detection.

    Limitations

    The implementation is sensitive to parameter tuning (Gaussian sigma and thresholds), and images with high noise require additional preprocessing.

    Practical application

    Canny edge detection remains widely used in industrial, medical, and robotic vision systems. In the finger robot project, this algorithm helps extract boundaries of buttons, text, and widgets on the screen, improving the accuracy of subsequent detection and OCR stages.

    📇 Summary flashcard — 13 analytical fields for this paper

    خلاصه

    Canny's paper presents an optimal multi-stage algorithm for edge detection, including smoothing, gradient computation, non-maximum suppression, and hysteresis thresholding.

    نمای سریع

    The gold-standard edge detection algorithm with a multi-stage approach.

    یافته‌های کلیدی

    The Canny edge detector was shown to be statistically optimal and outperformed previous methods, becoming the gold standard for edge detection.

    هدف

    To develop an edge detection method with clearly defined performance criteria and optimal results.

    روش

    The Canny method consists of four stages: Gaussian smoothing, gradient magnitude and direction computation, non-maximum suppression, and double-thresholding with hysteresis for edge linking.

    نتایج

    The Canny algorithm produces high-quality edges with low noise across various image types.

    نتیجه‌گیری

    This method is a powerful and robust tool for edge extraction that remains widely used today.

    مفاهیم کلیدی

    edge detection، image processing، Canny filter، hysteresis

    مطالعه‌ی بیشتر

    https://ieeexplore.ieee.org/document/4767851

    تحلیل

    This is one of the most cited papers in image processing, highly influential due to its comprehensiveness and practical applicability.

    محدودیت‌ها

    The implementation is sensitive to parameter tuning (Gaussian sigma and thresholds), and images with high noise require additional preprocessing.

    کارهای آینده

    The author suggested extending the method to color images, video, and real-time systems.

    کاربرد عملی

    Canny edge detection remains widely used in industrial, medical, and robotic vision systems. In the finger robot project, this algorithm helps extract boundaries of buttons, text, and widgets on the screen, improving the accuracy of subsequent detection and OCR stages.

    References (this paper draws on) (0)

    No references recorded.

    Cited by (0) ▶

    No paper cites this one yet.

    Prerequisite learning path for this paper