Locate Features
This palette groups several visual inspection steps whose purpose is locating known features on an object under inspection. Common features include edge points along the boundary of an object, patterns on the object, and the entire object itself. You can use located features in the following ways:
- Determining the location of the object in the image.
- Linking the location of a region of interest to the feature so that the region moves within the image in relation to the object.
- Defining object landmarks on which you can base measurements. In most applications, you can make measurements based on points detected in the image or geometric fits to the detected points. Object features that are useful for measurements fall into three categories:
- Edge points along the boundary of an object
- Shapes or patterns within the object
- Pixels with uniform intensity values that you can easily distinguish from surrounding pixels
| Step Name | Description |
|---|---|
| Find Edges | Locates and counts edge points along a search line. For example, you can use this step to locate and count the edges of pins on a chip. Refer to Find Edges Concepts for related information. |
| Find Straight Edge | Locates a straight edge on the object. For example, you can use this step to find the left edge of a floppy disk and determine the orientation of the disk in the image. Refer to Find Straight Edge Concepts for related information. |
| Find Circular Edge | Locates a circular edge on the object under inspection. For example, you can use this step to locate and measure a hole drilled in a mechanical part. Refer to Find Circular Edge Concepts for related information. |
| Match Pattern | Locates regions of an image that match a predefined template of a pattern. Use this step when the feature you want to locate can only be described by its 2D intensity and edge info. For example, you can use Match Pattern to locate a company logo printed on a container. The Match Pattern step is indifferent to image noise, blur, and uniform lighting changes. Refer to Match Pattern Concepts for related information. |
| Geometric Matching | Locates regions in a grayscale image that match a model, or template, of a reference pattern. Geometric matching is specialized to locate templates that are characterized by distinct geometric or shape information. Geometric Matching finds templates regardless of lighting variation, blur, noise, occlusion, and geometric transformations such as shifting, rotation, or scaling of the template. Refer to Geometric Matching Concepts for related information. |
| Set Coordinate System | Creates a coordinate system based on points defined during previous steps. As the locations of these defined points vary from image to image, the coordinate system moves. You can use the coordinate system you create to reposition regions of interest during subsequent steps so that the region matches the position of the object under inspection. Refer to Set Coordinate System Concepts for related information. |
| Detect Objects | Locates area features whose pixels intensities are uniform and vary significantly from the intensities of background pixels. Use this step when you cannot distinguish the feature from the rest of the image by its edge or pattern information. Refer to Detect Objects Concepts for related information. |
| Match Color Pattern | Detects the presence of an object using a color template pattern that describes the edge information and color information of the object. Use this step if the object contains color information that is very different from the background, and you want to find the precise location of the object in the image or count the number of objects present in a region of the image. Also, use this step if the object is very similar to other objects in the image but has a distinct hue. Refer to Match Color Pattern Concepts for related information. |
| Adv. Straight Edge | Locates difficult to detect straight edges in an image. This step provides greater control over the edge detection algorithm used to detect straight edges and allows you to detect multiple straight edges within a region of interest. Refer to Adv. Straight Edge Concepts for related information. |