Image inspection apparatus and setting method for image inspection apparatus

1. An image inspection apparatus that makes a pass/fail determination of an inspection target based on an image of the inspection target captured by an imaging unit, the image inspection apparatus comprising:

a mode switching unit that switches a mode of the image inspection apparatus between a setting mode for setting the image inspection apparatus and a run mode for performing an inspection;

an imaging setting unit that receives a setting of an imaging condition of the imaging unit in the setting mode;

a master image registering unit that registers, as a master image, an image captured under the imaging condition set by the imaging setting unit in the setting mode;

an inspection type selecting unit that receives selection of either a rule-based inspection that causes a user to set a feature value of the image used for an inspection and makes a pass/fail determination based on the set feature value or a learning-based inspection that generates a distinguishing device and makes a pass/fail determination using the distinguishing device;

an image processing tool selecting unit that receives selection of an image processing tool in the setting mode in the rule-based inspection;

an inspection window setting unit that receives a setting of a rule-based inspection window for defining a range to which the image processing tool selected by the image processing tool selecting unit is applied on the master image registered by the master image registering unit in the setting mode in the rule-based inspection;

a parameter adjusting unit that receives adjustment of a parameter of the image processing tool selected by the image processing tool selecting unit in the setting mode in the rule-based inspection;

a learning image registering unit that registers a non-defective product image to which an attribute of a non-defective product is given by the user and a defective product image to which an attribute of a defective product is given by the user in the setting mode in the learning-based inspection; and

a distinguishing device generating unit that learns the non-defective product image and the defective product image registered by the learning image registering unit and generates the distinguishing device that distinguishes the non-defective product image from the defective product image in the setting mode in the learning-based inspection,

wherein, in the run mode, when the rule-based inspection is selected by the inspection type selecting unit, a pass/fail determination of the inspection target is made by setting the rule-based inspection window on an image newly captured by the imaging unit and applying the image processing tool selected by the image processing tool selecting unit to the image in the rule-based inspection window and,

when the learning-based inspection is selected by the inspection type selecting unit, a pass/fail determination of the inspection target is made by inputting the image newly captured by the imaging unit to the distinguishing device.

2. The image inspection apparatus according to claim 1 ,

wherein, when the inspection type selecting unit performs switching to the learning-based inspection and the mode switching unit selects the setting mode, the learning image registering unit registers, as non-defective product images, a plurality of images obtained by causing the imaging unit to capture the inspection target a plurality of times while changing the imaging condition.

3. The image inspection apparatus according to claim 2 ,

wherein, when the inspection type selecting unit performs switching to the learning-based inspection and the mode switching unit selects the setting mode, the learning image registering unit registers, as non-defective product images, a plurality of images obtained by causing the imaging unit to capture the inspection target a plurality of times while changing at least one of an illumination condition and an exposure time.

4. The image inspection apparatus according to claim 1 ,

wherein, when the inspection type selecting unit performs switching to the learning-based inspection and the mode switching unit selects the setting mode, the learning image registering unit automatically generates a plurality of non-defective product images based on an image obtained by causing the imaging unit to capture the inspection target and registers the generated non-defective product images.

5. The image inspection apparatus according to claim 1 , further comprising:

a display unit that displays the master image,

wherein the imaging setting unit generates an imaging condition setting user interface that enables brightness adjustment and focus adjustment of an image as the imaging condition and displays the imaging condition setting user interface in the display unit in the setting mode in the rule-based inspection and in the setting mode in the learning-based inspection.

6. The image inspection apparatus according to claim 1 ,

wherein the inspection window setting unit receives a setting of a learning-based inspection window for defining a range of difference detection on the master image registered by the master image registering unit in the setting mode in the learning-based inspection and

in the run mode, when the learning-based inspection is selected, the learning-based inspection window is set on an image newly captured by the imaging unit, difference detection of the image in the learning-based inspection window is performed, and a pass/fail determination of the inspection target is made based on a result of the difference detection.

7. A setting method for an image inspection apparatus that makes a pass/fail determination of an inspection target based on an image of the inspection target captured by an imaging unit, the setting method comprising:

an imaging condition setting step of setting an imaging condition of the imaging unit with a mode of the image inspection apparatus set to a setting mode for setting the image inspection apparatus;

a master image registering step of registering, as a master image, an image captured under the imaging condition set in the imaging condition setting step;

an image processing tool selecting step of causing a user to set a feature value of the image used for an inspection and selecting an image processing tool in the setting mode in a rule-based inspection that makes a pass/fail determination based on the set feature value;

an inspection window setting step of setting a rule-based inspection window for defining a range to which the image processing tool selected in the image processing tool selecting step is applied on the master image registered in the master image registering step in the setting mode in the rule-based inspection;

a parameter adjusting step of adjusting a parameter of the image processing tool selected in the image processing tool selecting step in the setting mode in the rule-based inspection;

a learning image registering step of registering a non-defective product image to which an attribute of a non-defective product is given by the user and a defective product image to which an attribute of a defective product is given by the user in the setting mode in a learning-based inspection that makes a pass/fail determination using a distinguishing device; and

a distinguishing device generating step of learning the non-defective product image and the defective product image registered in the learning image registering step and generating the distinguishing device that distinguishes the non-defective product image from the defective product image in the setting mode in the learning-based inspection,

wherein, in the run mode for performing the inspection, when the rule-based inspection is selected, a pass/fail determination of the inspection target is made by setting the rule-based inspection window on an image newly captured by the imaging unit and applying the image processing tool selected in the image processing tool selecting step to the image in the rule-based inspection window and

when the learning-based inspection is selected, a pass/fail determination of the inspection target is made by inputting the image newly captured by the imaging unit to the distinguishing device.

8. The setting method for an image inspection apparatus according to claim 7 ,

wherein the image inspection apparatus is put in the setting mode, either the rule-based inspection or the learning-based inspection is selected, and then the master image registering step is performed,

after the master image registering step is performed, the image processing tool selecting step, the inspection window setting step, and the parameter adjusting step are performed when the rule-based inspection is selected or

the learning image registering step and the distinguishing device generating step are performed when the learning-based inspection is selected.