A method for adaptable machining includes (a) providing one or more images with a digital imaging system of each of a series of work pieces, (b) for each of the work pieces, selectively modifying a preprogrammed cutting tool path with regard to the image of the respective work piece, and (c) for each of the work pieces, performing a machining operation according to the respective selectively modified preprogrammed cutting tool path.

A method for programming a robot in a vision base coordinate is provided. The method includes the following steps. A robot is drawn to an operation point. The coordinates of the operation point in a photo operation are set as a new point. A teaching image is captured and a vision base coordinate system is established. A new point is added according to the newly established vision base coordinate system. When the robot is operating, the robot is controlled to capture an image from a photo operation point. A comparison between the captured image and a teaching image is made. The image being the same as the teaching image is searched according to the comparison result. Whether the vision base coordinate system maintains the same corresponding relation as in the teaching process is checked. Thus, the robot can be precisely controlled.

The present disclosure relates to systems and methods that use computer-vision processing systems to improve patient safety during surgical procedures. Computer-vision processing systems may train machine-learning models using machine-learning techniques. The machine-learning techniques can be executed to train the machine-learning models to recognize, classify, and interpret objects within a live video feed. Certain embodiments of the present disclosure can control (or facilitate control of) surgical tools during surgical procedures using the trained machine-learning models.

The present disclosure relates to systems and methods that use computer-vision processing systems to improve patient safety during surgical procedures. Computer-vision processing systems may train machine-learning models using machine-learning techniques. The machine-learning techniques can be executed to train the machine-learning models to recognize, classify, and interpret objects within a live video feed. Certain embodiments of the present disclosure can control (or facilitate control of) surgical tools during surgical procedures using the trained machine-learning models.

A method for object distance detection and focal positioning in relation thereto. The method comprising the steps of: (a) identifying (via a computing device) a desired distance among a plurality of designated sites on an object; (b) adjusting a focus (via an autofocus device) onto the plurality of designated sites; (c) calculating (via an image recognition module) the actual distance among the plurality of designated sites; (d) determining (via the image recognition module) if error exist between the actual distance and the desired distance; and (e) wherein (in no particular order) repeating the steps of (b), (c), and (d) until no substantial error exists between the actual distance and the desired distance.

A method for adaptable machining includes (a) providing one or more images with a digital imaging system of each of a series of work pieces, (b) for each of the work pieces, selectively modifying a preprogrammed cutting tool path with regard to the image of the respective work piece, and (c) for each of the work pieces, performing a machining operation according to the respective selectively modified preprogrammed cutting tool path.

The present disclosure relates to systems and methods that use computer-vision processing systems to improve patient safety during surgical procedures. Computer-vision processing systems may train machine-learning models using machine-learning techniques. The machine-learning techniques can be executed to train the machine-learning models to recognize, classify, and interpret objects within a live video feed. Certain embodiments of the present disclosure can control (or facilitate control of) surgical tools during surgical procedures using the trained machine-learning models.

A positioning unit that performs positioning with respect to a predetermined sample, an imaging unit that obtains an image of the sample, and a processing unit, in which the imaging unit is moved by the positioning unit, and obtains a first image and a second image which is obtained later than the first image, and in which the processing unit obtains a first position shift trend from the first image and the second image, and determines whether or not the positioning is abnormal from a change of the first position shift trend.

A teaching method for a transfer mechanism is provided. The teaching method includes (a) placing a first substrate or an edge ring on a fork of the transfer mechanism, transferring the first substrate or the edge ring to a target position, and placing the first substrate or the edge ring onto the target position; (b) placing a second substrate having a position detection sensor on the fork, and transferring the second substrate to a position directly above or below the target position; (c) detecting an amount of deviation between the first substrate or the edge ring and the target position using the position detection sensor of the second substrate; and (d) correcting transfer position data of the transfer mechanism for the first substrate or the edge ring to be transferred next, based on the detected amount of deviation.

A method for programming a robot in a vision base coordinate is provided. The method includes the following steps. A robot is drawn to an operation point. The coordinates of the operation point in a photo operation are set as a new point. A teaching image is captured and a vision base coordinate system is established. A new point is added according to the newly established vision base coordinate system. When the robot is operating, the robot is controlled to capture an image from a photo operation point. A comparison between the captured image and a teaching image is made. The image being the same as the teaching image is searched according to the comparison result. Whether the vision base coordinate system maintains the same corresponding relation as in the teaching process is checked. Thus, the robot can be precisely controlled.