5 Mins Read

Identifying carpet defects


Identifying carpet defects With Computer Vision

When it comes to manufacturing, quality control has always been an essential and costly task. The biggest problem for producers is that even a slight variation in production processes or materials can make the entire production function defective.

The advantages of detecting defects before they leave the manufacturing facility are clear. But, humans need extensive training to perform visual inspections and are prone to distraction and fatigue, that can result in grave and costly mistakes. Thus, these inspections can create bottlenecks in production and cause delays.

Defect detection can be automated by technologies such as Computer Vision, a subset of artificial intelligence (AI). Computer-based vision systems specialized in defect detection are more affordable than defect detection personnel and more accurate in detection and reporting.

What is Computer Vision?

Computer vision is a subfield of artificial intelligence and machine learning, which can process, analyze, and make sense of visual data (images or videos) like humans do.

In the past few years, we have been able to use computer vision and image processing (video processing) in industries such as automobiles, health, food, etc. to do things faster and more accurately.

The Need for AI Defect Detection in carpet Manufacturing

Carpet is a type of flooring made from weaved fibers. Carpets come in a variety of styles, patterns, and colors. A carpet defect is an imperfection on the surface of the carpet caused by the manufacturing process. Different imperfections can appear on the outer layer of texture because of yarn defects, improper operation, and over-stretching. If there are defects in the carpet, the price is affected. Thus, carpet imperfection identification is a fundamental step for quality control in textile manufacturing. Figure 1 shows a few types of common defects.

Figure 1. common types of defects (a) miss pattern (b) hole (c) 2 color-fiber

How Computer Vision Solved the Problem

The traditional method is based on time-consuming visual inspection by humans, which can result in inspectors inadvertently missing some defective products.

In recent years, with the help of digital image processing techniques and computer vision, automated fabric defect inspection has become popular and has gradually replaced the traditional method. Cameras are used to inspect carpets during production, and computer vision techniques look for defects in the products and report them. (Figure 2)

Figure 2. Fabric defect detection by (a) manual and (b) automated optical inspection methods [1], Source.

About the Project

To use computer vision to detect defects in the carpet industry, it is necessary to perform the following steps:

1- Collect sample pictures of defects

2- Identify and label all the defects on the images (Figure 3), A process known as annotating

3- Train the model with collected sample defects

At this stage, we have a computer vision model capable of  identifying, categorizing, and reporting fabric defects automatically.

(a) – Image by the author
(b) – Image by the author

Figure 3. annotating carpet defect (a) hole defect (b) color defect

For this project, we will use the AIEX platform to obtain the desired computer vision model. First, we upload all the sample images of carpet defects to our new project, then we annotate them one by one to indicate what the model should look for. The last step is to choose the type of training we want to use and start training our model. After training concluded, we have a model ready to detect carpet defects. We can test it by feeding the model with new images and inspecting the outcome (Figure 4).

Figure 4. Testing out the model using the AIEX platform and detect carpet defects


Manual inspection of product quality is a time-consuming task that increases production costs and material waste. With computer vision-based defect detection techniques that automate and optimize quality inspection processes, businesses can achieve higher efficiency, lower cost, minimal waste, and greater customer satisfaction.

Related articles
Computer vision is a critical component of self-driving cars, a hot topic in recent years. We examine this topic...
Smart farming and artificial intelligence
The fourth agricultural revolution is already under way with the adoption of smart farm technology such as artificial intelligence,...
waste management
This article discusses the integration of artificial intelligence in the field of recycling. We will also train a model...
traffic management
As urban areas continue to grow, the number of vehicles on the road is increasing, which leads to congested...
Thanks to advancements in artificial intelligence, particularly in computer vision, deep learning models can now be utilized in various...
Trauma Detection on Pelvic Radiographs using Computer Vision Algorithms
A timely and accurate diagnosis of the proximal femur and pelvis injuries in trauma patients is essential to saving...
Subscribe to our newsletter and get the latest practical content.

You can enter your email address and subscribe to our newsletter and get the latest practical content. You can enter your email address and subscribe to our newsletter.