Scribd
Upload
306 views5 pages

Applications of Keyence IV3 Sensor

The document discusses three options for developing a vision system to detect defects: 1) Developing their own system using a camera, mini computer, and proprietary algorithm. The estimated total cost is 26,200 euros for the first 10 machines. 2) Purchasing a pre-built camera system from Keyence or Cognex. Keyence cameras over 5000 euros may exceed the cost of developing their own system. Cognex offers deep learning-based vision software. 3) Comparing smart cameras from different manufacturers, testing performance, and potentially modifying lighting if needed. Other options include developing a new lighting system to use with existing vision systems.

Uploaded by

k.nidhara
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
306 views5 pages

Applications of Keyence IV3 Sensor

The document discusses three options for developing a vision system to detect defects: 1) Developing their own system using a camera, mini computer, and proprietary algorithm. The estimated total cost is 26,200 euros for the first 10 machines. 2) Purchasing a pre-built camera system from Keyence or Cognex. Keyence cameras over 5000 euros may exceed the cost of developing their own system. Cognex offers deep learning-based vision software. 3) Comparing smart cameras from different manufacturers, testing performance, and potentially modifying lighting if needed. Other options include developing a new lighting system to use with existing vision systems.

Uploaded by

k.nidhara
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

Option 1:

Developing a new vision module with the help of NTS. (Including a camera, minicomputer to
process, our own algorithm developed with a licensed software).
Cost per Machine (Euros)
Fixed Cost (Euros) Per machine cost (Euros)
Electrical
35,000.00
Electrical components
30,000.00
PC 400.00
25,000.00
Camera 200.00
Cost

20,000.00
Electrical Testing 50.00
15,000.00

10,000.00
Illumination System 200.00
3274
5,000.00

Software -
0 10 20 30 40 50 60
Halcon License - Development 3,700.00
Expected number of machines with vision system
Halcon License - Run time 1,500.00
Software development (500hrs* 45 hourly
22,500.00
rate)

Mechanical
Mechanical parts/accessories 300.00
Mechanical testing 100.00

Total 26,200.00 2,750.00

Option 2: Purchasing a built in camera system.


1. Keyence AI camera : Tested camera was around 3500 euros. But it was not enough to
detect all the defects up to our expected level. As per Keyence, the improved camera
of similar series is between 5000 – 7000 Euros. According to the graph, if the unit
price exceeds 5000, it will be higher than system development cost for 10 machines
by ATD.

2. Cognex AI camera (Deep learning based software):

Vision Pro deep learning software (Datasheet is attached herewith)

 In sight D900 (Price requested, datasheet is attached)


 In sight 2800

VisionPro Deep Learning is an AI-based image analysis software designed for complex
applications. It automates tasks that are too complicated and time-consuming to program
with rule-based algorithms, while providing a consistency and speed that aren’t possible
with manual inspection. VisionPro Deep Learning tolerates natural variation and
differentiates between acceptable and unacceptable anomalies to simplify development of
highly variable applications including:
 Defect detection and segmentation
 Assembly verification and part location
 Material classification
 Character reading

According to the details given in the technical specifications, appearance based product
identification can be considered as the most suitable solution for our application.
3.

 Graph 2: Purchasing an in built camera Vs developing a camera system.


Option 3:
Compare the significant features of selected smart cameras and test the best camera to
identify its limitations. If the illumination of the camera is not suitable enough check the
possibility of modifying the lighting system of the camera.

Name of the Applications/ Special Features Link to Technical Remarks


Manufacturer/ specification/ example
technology used

Yolov5 network (detection algorithm) https://www.frontiersin.org/ lettuce defective leaves


articles/10.3389/
model fpls.2023.1242337/full identification

Yolov7 network tea leaf detection https://www.nature.com/articles/


s41598-023-33270-4
model

X Ray cameras Potato detection https://pepperequipmentco.com/


blog/smart-vision-accurate-potato-
defect-detection-using-x-ray-
cameras

Opencv, python Banana leaf detection


and image
processing

Other Solutions:
Developing a new lighting system by integrating different number of LEDs with specific
wavelengths to use with existing vision systems such as Keyence.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy