Fabric Defect Detection Algorithm Based on Image Saliency Region and Similarity Location
TL;DR: In this paper , a defect detection method based on saliency region and similarity location is proposed to solve the problem of defect detection and to contour accurate segmentation of periodic texture fabric images.
read more
Abstract: In order to solve the problem of defect detection and to contour accurate segmentation of periodic texture fabric images, a fabric defect detection method based on saliency region and similarity location is proposed. Firstly, the image to be detected was processed by color space conversion, Gaussian filtering, and contrast enhancement, and a frequency-tuned (FT) salient region detection algorithm was used to estimate a saliency map of the enhanced image. The fabric image was divided into image blocks of the same size with overlapping areas through a sliding window, and then the statistical parameters of each image block were calculated. The outliers in the statistical parameters were filtered out using inter-quartile range (IQR). Through the positioning and processing of image defects, abnormal elimination was carried out, and the defect outline was finally obtained. The experimental results show that the method proposed in this paper has better performance in terms of qualitative characterization of Acc, Precision, Recall, and F1 score.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
PRC-Light YOLO: An Efficient Lightweight Model for Fabric Defect Detection
Baobao Liu,Heying Wang,Zifan Cao,Yu Wang,Lu Tao,Jingjing Yang,Kaibing Zhang +6 more
TL;DR: The PRC-Light YOLO model for fabric defect detection is proposed, and the YOLOv7 model is improved by integrating new convolution operators into the Extended-Efficient Layer Aggregation Network for optimized feature extraction, reducing computations while capturing spatial features effectively.
5
Textile defect detection based on multi‐proportion spatial attention mechanism and channel memory feature fusion network
Yaxin Ji,Lan Di +1 more
TL;DR: A multi‐proportion spatial attention mechanism (MPAM) is introduced, which employs multi-proportion convolution to improve the backbone network's capacity to detect non‐uniform structural defects and a channel attention mechanism‐based memory feature fusion network is developed.
1
PRC-Light YOLO: An Efficient Lightweight Model for Fabric Defect Detection
Baobao Liu,Heying Wang,Zhurong Cao,Ye Wang,Tiecheng Lu,Jingjing Yang,Kaibing Zhang +6 more
- 20 Dec 2023
TL;DR: The PRC-Light YOLO model is an efficient lightweight model for fabric defect detection that enhances accuracy and efficiency by introducing new convolution operators, multi-branch dilated convolutions feature pyramid, lightweight upsampling operators, HardSwish activation function, and Wise-IOU v3 bounding box loss function.
1
Low-cost ultrasonic sensors for in-field experimentation data collection
Fagner L. Theodoro,Arthur Carniato Sanches,Thiago A. C. da Cruz,Rodrigo Couto Santos,D. L. Flumignan,Fernanda Lamede Ferreira de Jesus +5 more
TL;DR: In this paper , the performance of HC-SR04 ultrasonic distance sensors coupled with a data acquisition system composed of an expansion board connected to a Raspberry minicomputer was evaluated in an in-loco experiment on Parshall flumes.
1
A Novel Method for Optimizing Color Selection Using The Hadamard Product Technique
TL;DR: A novel strategy for optimizing the color selection process using the Hadamard product technique is presented, and a remarkable increase in computational speed of 1.078.82 times faster has been observed.
References
Frequency-tuned salient region detection
Radhakrishna Achanta,Sheila S. Hemami,Francisco J. Estrada,Sabine Süsstrunk +3 more
- 20 Jun 2009
TL;DR: This paper introduces a method for salient region detection that outputs full resolution saliency maps with well-defined boundaries of salient objects that outperforms the five algorithms both on the ground-truth evaluation and on the segmentation task by achieving both higher precision and better recall.
Visual attention detection in video sequences using spatiotemporal cues
Yun Zhai,Mubarak Shah +1 more
- 23 Oct 2006
TL;DR: The proposed spatiotemporal video attention framework has been applied on over 20 testing video sequences, and attended regions are detected to highlight interesting objects and motions present in the sequences with very high user satisfaction rate.
1.1K
Computer-Vision-Based Fabric Defect Detection: A Survey
TL;DR: This paper attempts to present the first survey on fabric defect detection techniques presented in about 160 references, and suggests that the combination of statistical, spectral and model-based approaches can give better results than any single approach.
An Effective Method of Weld Defect Detection and Classification Based on Machine Vision
TL;DR: A weld defect detection and classification algorithm based on machine vision and a modified background subtraction method based on Gaussian mixture models can meet the requirements for the best real-time and continuous welding defect detection systems available nowadays.
202
Surface defect detection in tiling Industries using digital image processing methods: analysis and evaluation.
Mohammad Karimi,Davud Asemani +1 more
TL;DR: A survey has been made on the pattern recognition and image processing algorithms which have been used to detect surface defects and the existing algorithms in each subgroup appear to be limited for detecting some subgroup of defects.
116