Diamond cutting camera automatic focusing method
By using a dot calibration plate and an autofocus algorithm in diamond cutting equipment, automatic camera focusing was achieved, solving the problems of accuracy and consistency in manual focusing and improving processing accuracy and efficiency.
CN122372837APending Publication Date: 2026-07-10INNOVISION INTELLIGENT TECH (HANGZHOU) CO LTD
0 Cites 0 Cited by
Patent Information
- Application Number
- CN202610469470.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-10
- Publication Date
- 2026-07-10
AI Technical Summary
Technical Problem
In existing diamond cutting equipment, camera focusing relies on manual adjustment, which makes it difficult to guarantee focusing accuracy and consistency, affecting processing precision and efficiency.
Method used
Using a dot calibration plate and an autofocus algorithm, the camera moves along the Z-axis to acquire images. Combining coarse positioning and fine search stages, the optimal focus position is automatically determined, and the sharpness score is calculated using ROI and the Brenner evaluation function.
Benefits of technology
It improves focusing accuracy and stability, enhances adaptability to scale changes, and significantly increases focusing speed and system response efficiency.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention discloses an automatic focusing method for a diamond cutting camera, and relates to the technical field of numerical control machining, and the method comprises the steps: placing a dot calibration plate on a rotary table, and controlling the camera to move from top to bottom along a Z axis to collect calibration plate images at different positions; performing zooming and de-noising processing on each image, detecting circular spots in the layered concentric recognition area, and selecting a spot closest to the center of the image to determine an ROI (Region of Interest); in the coarse positioning stage, a definition score sequence is obtained through the first stride, a focus candidate interval is determined, in the fine searching stage, the candidate interval is scored point by point through the second stride, and the position with the maximum score is determined as the focusing position. Through double-stage search and ROI self-adaptive selection based on a layered identification area, rapid convergence of the focusing process is realized, and the focusing precision and stability are improved; through image zooming and ROI local definition evaluation, the calculation amount is reduced, the focusing speed and the system response efficiency are improved, and meanwhile the accuracy and comparability of definition evaluation under different imaging scales are guaranteed.
Need to check novelty before this filing date? Find Prior Art