Novel method for patterned fabric inspection using Bollinger bands

Abstract

This paper introduces a new application of Bollinger bands for defect detection of patterned fabric. A literature review on previous designed methods for patterned fabric defect detection will be depicted. For data analysis, Bollinger bands are calculated based on standard deviation and are originally used in the financial market as an oversold or overbought indicator for stock. The Bollinger bands method is an efficient, fast and shift-invariant approach, that can segment out the defective regions on the patterned fabric with clear and crystal clean images. The new approach is immune of the alignment problem that often happens in previous methods. In this paper, the upper band and lower band of Bollinger bands, which are sensitive to any subtle change in the input data, have been developed for use to indicate the defective areas in patterned fabric. The number of standard deviation and length of time of Bollinger bands can be easily determined to obtain excellent detection results. The proposed method has been evaluated on three different patterned fabrics. In total, 165 defect-free and 171 defective images have been used in the evaluation, where 98.59% accuracy on inspection has been achieved.

Robust defect detection in plain and twill fabric using directional Bollinger bands

“…5 However, the second phase is newly added to evaluate the degree of success of the proposed method in detecting defects. Each image is of size 256 × 256 in 24-bit depth.…”

“…5, the final detection result is not greatly affected if the values of m and n are approximately equal to or greater than the lengths of the row and column of a repetitive unit. 5 Hence, it is observed that the original BB method can deal with most defect types, especially those with large defects such as dirty yarn [ Fig. 5 Fig.…”

“…AVI can be facilitated using either an on-loom or off-loom inspection machine equipped with overhead digital cameras to monitor the manufacturing product. The previous Bollinger bands (BB) method 5 was designed for other patterned fabrics in the p2, pmm, and p4m groups and has obtained satisfactory detection results. The traditional human inspection approach is controversial as it depends on the experience of skilled workers and only results in about 60% to 75% of defects 1 being eliminated.…”

Patterned fabric defect detection via convolutional matching pursuit dual-dictionary

“…[2][3][4][5][6][7][8][9][10] Many algorithms such as mathematical morphology method, 2 auto-correlation function method, 3 and co-occurrence matrixes method 4 have been designed for fabric defect detection. [2][3][4][5][6][7][8][9][10] Many algorithms such as mathematical morphology method, 2 auto-correlation function method, 3 and co-occurrence matrixes method 4 have been designed for fabric defect detection.…”

Development and implementation of a real time statistical control method to identify the start and end of the winter surge in demand for paediatric intensive care

“…They have also been used in completely different contexts such as identifying fabric defects during manufacturing (Ngan and Pang, 2006), although an academic literature search reveals few documented uses outside of finance and none in health care.…”