Manual

Table Of Contents
DobotVisionStudio User Guide
Issue V4.1.2 (2022-06-08) User Guide Copyright © Yuejiang Technology Co., Ltd.
216
Feature Type
This parameter includes feature spectrum and feature histogram, and feature histogram
is more sensitive.
Intensity
Intensity reflects the effect of light on the image. If you need to keep the recognition
result more stable under the change of light, it is recommended to disable this parameter.
You can only enable or disable intensity when selecting feature histogram as feature
type. Intensity is always enabled when the feature type is feature spectrum.
When you run the flow after creating the template, loading the image and setting the ROI, the
software can output the recognition score for each category and the best recognition effect according
to the K value, as shown below. On the right side of the output result, the hue, saturation and
brightness contrast chart are displayed between model area and current area.
Running parameters of color recognition
K Value
This parameter means that the class with the largest number in the first K samples is
selected as the best recognition result.
KNN Distance
This parameter includes Euclidean distance, Manhattan distance and intersection
distance. There are slight differences among various distances. You can select it
according to actual conditions. Generally, you can select the default distance.
Defect Detection
OCV
The tool of OCV (Optical Character Verification) compares the target image with the standard image
to detect whether printed characters and patterns have defects like characters missing and redundant.
This tool is widely applied to packaging, printing, semiconductor and other manufacturing areas.
OCV is a process which compares the target image with the standard image, thus standard images
need to be trained before defect detection.
Steps:
1. Select the OCV tool, and double click to open it.